WO2022236785A1 - Channel information feedback method, receiving end device, and transmitting end device - Google Patents

Channel information feedback method, receiving end device, and transmitting end device Download PDF

Info

Publication number
WO2022236785A1
WO2022236785A1 PCT/CN2021/093689 CN2021093689W WO2022236785A1 WO 2022236785 A1 WO2022236785 A1 WO 2022236785A1 CN 2021093689 W CN2021093689 W CN 2021093689W WO 2022236785 A1 WO2022236785 A1 WO 2022236785A1
Authority
WO
WIPO (PCT)
Prior art keywords
csi feedback
csi
cycles
bit streams
subband
Prior art date
Application number
PCT/CN2021/093689
Other languages
French (fr)
Chinese (zh)
Inventor
刘文东
田文强
肖寒
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to PCT/CN2021/093689 priority Critical patent/WO2022236785A1/en
Priority to CN202180094787.0A priority patent/CN116941198A/en
Publication of WO2022236785A1 publication Critical patent/WO2022236785A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received

Definitions

  • the embodiments of the present application relate to the communication field, and more specifically, relate to a channel information feedback method, a receiving device, and a sending device.
  • the channel state information (Channel State Information, CSI) can be fed back based on the codebook.
  • CSI Channel State Information
  • the codebook itself is a pre-set finite set, that is, the mapping process from the estimated channel to the channel in the codebook is quantized and lossy.
  • the fixed codebook design cannot be dynamically adjusted according to channel changes, which reduces the accuracy of the feedback channel information, thereby reducing the performance of precoding.
  • the embodiment of the present application provides a channel information feedback method, a receiving device and a transmitting device, which use the CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform
  • the CSI feedback can improve the CSI feedback accuracy and reduce the CSI feedback overhead.
  • a channel information feedback method including:
  • the receiving end device acquires target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; where N is a positive integer, and N ⁇ 2.
  • a channel information feedback method including:
  • the originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N ⁇ 2.
  • a receiving device configured to execute the method in the first aspect above.
  • the receiving end device includes a functional module for executing the method in the first aspect above.
  • an originating device configured to execute the method in the second aspect above.
  • the originating device includes a functional module for executing the method in the second aspect above.
  • a receiving device including a processor and a memory.
  • the memory is used to store a computer program
  • the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect above.
  • an originating device including a processor and a memory.
  • the memory is used to store a computer program
  • the processor is used to call and run the computer program stored in the memory to execute the method in the second aspect above.
  • an apparatus for implementing the method in any one of the first aspect to the second aspect above.
  • the device includes: a processor, configured to invoke and run a computer program from the memory, so that the device installed with the device executes the method in any one of the above first to second aspects.
  • a computer-readable storage medium for storing a computer program, and the computer program causes a computer to execute the method in any one of the above-mentioned first aspect to the second aspect.
  • a computer program product including computer program instructions, the computer program instructions causing a computer to execute the method in any one of the above first to second aspects.
  • a computer program which, when running on a computer, causes the computer to execute the method in any one of the above first to second aspects.
  • the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in N CSI feedback cycles, and the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in N CSI feedback cycles , to obtain the target channel vector of N CSI feedback cycles. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
  • FIG. 1 is a schematic diagram of a communication system architecture applied in an embodiment of the present application.
  • Fig. 2 is a schematic diagram of a neuron provided in the present application.
  • Fig. 3 is a schematic diagram of a neural network provided by the present application.
  • Fig. 4 is a schematic diagram of a convolutional neural network provided by the present application.
  • Fig. 5 is a schematic diagram of an LSTM unit provided in the present application.
  • Fig. 6 is a schematic diagram of channel information feedback provided by the present application.
  • Fig. 7 is a schematic diagram of another channel information feedback provided by the present application.
  • Fig. 8 is a schematic flowchart of a channel information feedback method provided according to an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a process of periodic CSI feedback provided according to an embodiment of the present application.
  • Fig. 10 is a schematic diagram of a CSI periodic feedback provided according to an embodiment of the present application.
  • Fig. 11 is a schematic diagram of an alternate configuration of primary feedback subbands and auxiliary feedback subbands according to an embodiment of the present application.
  • FIG. 12 is a schematic diagram of another CSI periodic feedback process provided according to an embodiment of the present application.
  • Fig. 13 is a schematic structural diagram of a CSI periodic feedback provided according to an embodiment of the present application.
  • Fig. 14 is a schematic diagram of a primary CSI feedback cycle and a secondary CSI feedback cycle provided according to an embodiment of the present application.
  • Fig. 15 is a schematic diagram of another CSI periodic feedback provided according to an embodiment of the present application.
  • Fig. 16 is a schematic diagram of another primary CSI feedback cycle and secondary CSI feedback cycle provided according to an embodiment of the present application.
  • Fig. 17 is a schematic structural diagram of another CSI periodic feedback provided according to an embodiment of the present application.
  • Fig. 18 is a schematic flowchart of another channel information feedback method provided according to an embodiment of the present application.
  • Fig. 19 is a schematic block diagram of a receiving device provided according to an embodiment of the present application.
  • Fig. 20 is a schematic block diagram of an originating device provided according to an embodiment of the present application.
  • Fig. 21 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
  • Fig. 22 is a schematic block diagram of a device provided according to an embodiment of the present application.
  • Fig. 23 is a schematic block diagram of a communication system provided according to an embodiment of the present application.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • NTN Non-Terrestrial Networks
  • UMTS Universal Mobile Telecommunications System
  • WLAN Wireless Local Area Networks
  • Wireless Fidelity Wireless Fidelity
  • D2D Device to Device
  • M2M Machine to Machine
  • MTC Machine Type Communication
  • V2V Vehicle to Vehicle
  • V2X Vehicle to everything
  • the communication system in the embodiment of the present application can be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, can also be applied to a dual connectivity (Dual Connectivity, DC) scenario, and can also be applied to an independent (Standalone, SA ) meshing scene.
  • Carrier Aggregation, CA Carrier Aggregation
  • DC Dual Connectivity
  • SA independent meshing scene
  • the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to a licensed spectrum, Wherein, the licensed spectrum can also be regarded as a non-shared spectrum.
  • the embodiments of the present application describe various embodiments in conjunction with network equipment and terminal equipment, wherein the terminal equipment may also be referred to as user equipment (User Equipment, UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
  • user equipment User Equipment, UE
  • access terminal user unit
  • user station mobile station
  • mobile station mobile station
  • remote station remote terminal
  • mobile device user terminal
  • terminal wireless communication device
  • wireless communication device user agent or user device
  • the terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital assistant (Personal Digital Assistant, PDA) devices, handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, next-generation communication systems such as terminal devices in NR networks, or future Terminal equipment in the evolved public land mobile network (Public Land Mobile Network, PLMN) network, etc.
  • PLMN Public Land Mobile Network
  • the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites) superior).
  • the terminal device may be a mobile phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (Virtual Reality, VR) terminal device, an augmented reality (Augmented Reality, AR) terminal Equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid , wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, or wireless terminal equipment in smart home.
  • a virtual reality (Virtual Reality, VR) terminal device an augmented reality (Augmented Reality, AR) terminal Equipment
  • wireless terminal equipment in industrial control wireless terminal equipment in self driving
  • wireless terminal equipment in remote medical wireless terminal equipment in smart grid
  • wireless terminal equipment in transportation safety wireless terminal equipment in smart city, or wireless terminal equipment in smart home.
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices, which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction.
  • Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets and smart jewelry for physical sign monitoring.
  • the network device may be a device for communicating with the mobile device, and the network device may be an access point (Access Point, AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA , or a base station (NodeB, NB) in WCDMA, or an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and an NR network A network device or a base station (gNB) in a network device or a network device in a future evolved PLMN network or a network device in an NTN network.
  • AP Access Point
  • BTS Base Transceiver Station
  • NodeB, NB base station
  • Evolutional Node B, eNB or eNodeB evolved base station
  • LTE Long Term Evolution
  • eNB evolved base station
  • gNB base station
  • the network device may have a mobile feature, for example, the network device may be a mobile device.
  • the network equipment may be a satellite, balloon station.
  • the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous earth orbit (geosynchronous earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite. ) Satellite etc.
  • the network device may also be a base station installed on land, in water, or other locations.
  • the network device may provide services for a cell, and the terminal device communicates with the network device through the transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell, and the cell may be a network device ( For example, a cell corresponding to a base station), the cell may belong to a macro base station, or may belong to a base station corresponding to a small cell (Small cell), and the small cell here may include: a metro cell (Metro cell), a micro cell (Micro cell), a pico cell ( Pico cell), Femto cell, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
  • the transmission resources for example, frequency domain resources, or spectrum resources
  • the cell may be a network device (
  • the cell may belong to a macro base station, or may belong to a base station corresponding to a small cell (Small cell)
  • the small cell here may include: a metro cell (Metro cell), a micro cell (Micro
  • the communication system 100 may include a network device 110, and the network device 110 may be a device for communicating with a terminal device 120 (or called a communication terminal, terminal).
  • the network device 110 can provide communication coverage for a specific geographical area, and can communicate with terminal devices located in the coverage area.
  • FIG. 1 exemplarily shows one network device and two terminal devices.
  • the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within the coverage area. This embodiment of the present application does not limit it.
  • the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment of the present application.
  • a device with a communication function in the network/system in the embodiment of the present application may be referred to as a communication device.
  • the communication equipment may include a network equipment 110 and a terminal equipment 120 with communication functions.
  • the network equipment 110 and the terminal equipment 120 may be the specific equipment described above, and will not be repeated here.
  • the communication device may also include other devices in the communication system 100, such as network controllers, mobility management entities and other network entities, which are not limited in this embodiment of the present application.
  • the "indication" mentioned in the embodiments of the present application may be a direct indication, may also be an indirect indication, and may also mean that there is an association relationship.
  • a indicates B which can mean that A directly indicates B, for example, B can be obtained through A; it can also indicate that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also indicate that there is an association between A and B relation.
  • the term "corresponding" may indicate that there is a direct or indirect correspondence between the two, or that there is an association between the two, or that it indicates and is indicated, configuration and is configuration etc.
  • predefined or “preconfigured” can be realized by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices).
  • the application does not limit its specific implementation.
  • pre-defined may refer to defined in the protocol.
  • the "protocol” may refer to a standard protocol in the communication field, for example, may include the LTE protocol, the NR protocol, and related protocols applied to future communication systems, which is not limited in the present application.
  • codebook-based eigenvector feedback is usually used to enable the base station to obtain downlink CSI.
  • the base station sends a downlink channel state information reference signal (Channel State Information Reference Signal, CSI-RS) to the terminal, and the terminal uses the CSI-RS to estimate the CSI of the downlink channel, and decomposes the eigenvalue of the estimated downlink channel to obtain The eigenvector corresponding to the downlink channel.
  • CSI-RS Channel State Information Reference Signal
  • the terminal calculates the matching codeword coefficients of the eigenvector in the preset codebook and performs quantization feedback, and the base station restores the eigenvector according to the quantized CSI fed back by the terminal.
  • the reporting types include periodic reporting, aperiodic reporting and semi-persistent reporting.
  • periodic CSI reporting and semi-persistent reporting on the Physical Uplink Control Channel Physical Uplink Control Channel
  • PUCCH Physical Uplink Control Channel
  • the period is configured by Radio Resource Control (RRC) parameters such as reportSlotConfig
  • RRC parameters such as reportSlotConfig
  • the allowed slot offset is configured by RRC parameters such as the slot offset list report (reportSlotOffsetList), by receiving the downlink control information ( Downlink Control Information, DCI) to trigger.
  • a neural network is an operational model composed of multiple neuron nodes connected to each other, in which the connection between nodes represents the weighted value from the input signal to the output signal, called weight; each node performs weighted summation of different input signals (summation, SUM), and output through a specific activation function (f).
  • the neuron structure is shown in Figure 2, for example.
  • a simple neural network is shown in Figure 3, which includes an input layer, a hidden layer and an output layer. Through different connection methods, weights and activation functions of multiple neurons, different outputs can be generated, and then fitted from input to output. Mapping relations.
  • Deep learning uses a deep neural network with multiple hidden layers, which greatly improves the ability of the network to learn features, and can fit complex nonlinear mappings from input to output, so it is widely used in the fields of speech and image processing.
  • deep learning also includes common basic structures such as convolutional neural network (CNN), recurrent neural network (Recurrent Neural Network, RNN).
  • CNN convolutional neural network
  • RNN Recurrent Neural Network
  • the basic structure of a convolutional neural network includes: an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4.
  • Each neuron of the convolution kernel in the convolution layer is locally connected to its input, and the local maximum or average feature of a certain layer is extracted by introducing a pooling layer, which effectively reduces the parameters of the network and mines local features. It enables the convolutional neural network to converge quickly and obtain excellent performance.
  • RNN is a neural network that models sequence data. It has achieved remarkable results in the field of natural language processing, such as machine translation and speech recognition. The specific performance is that the network memorizes the information of the past moment and uses it in the calculation of the current output, that is, the nodes between the hidden layers are no longer connected but connected, and the input of the hidden layer includes not only the input layer but also the Includes the output of the hidden layer at the previous moment.
  • Commonly used RNNs include structures such as Long Short-Term Memory (LSTM) and gated recurrent unit (GRU).
  • Figure 5 shows a basic LSTM cell structure, which can contain a tanh activation function. Unlike RNN, which only considers the nearest state, the cell state of LSTM will determine which states should be kept and which states should be forgotten, solving the traditional Shortcomings of RNN in long-term memory.
  • AI artificial intelligence
  • deep learning has achieved great success in computer vision, natural language processing, etc.
  • the field of communication has begun to try to use deep learning to solve technical problems that are difficult to solve by traditional communication methods, such as deep learning.
  • the neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from the actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal side as much as possible on the base station side. It is possible to reduce the CSI feedback overhead on the terminal side.
  • the CSI feedback based on deep learning regards the channel information as the image to be compressed, uses the deep learning self-encoder to compress the channel information, and reconstructs the compressed channel image at the sending end, which can preserve the channel information to a greater extent ,As shown in Figure 6.
  • a typical channel information feedback system is shown in FIG. 7 .
  • the entire feedback system is divided into encoder and decoder parts, which are deployed at the sending end and receiving end respectively.
  • the transmitting end obtains the channel information through channel estimation
  • the channel information matrix is compressed and encoded through the neural network of the encoder, and the compressed bit stream is fed back to the receiving end through the air interface feedback link, and the receiving end passes the decoder according to the feedback bit stream
  • the channel information is restored to obtain complete feedback channel information.
  • the encoder shown in Figure 7 uses the superposition of multiple fully connected layers, and the design of the convolutional layer and residual structure is used in the decoder. Under the condition that the encoding and decoding framework remains unchanged, the network model structure inside the encoder and decoder can be flexibly designed.
  • the CSI feedback in the 5G NR standard is a codebook-based feedback scheme.
  • the estimated channel is used to select the optimal feedback matrix and corresponding feedback from the codebook. coefficient.
  • the codebook itself is a pre-set finite set, that is, the mapping process from the estimated channel to the channel in the codebook is quantized and lossy.
  • the fixed codebook design cannot be dynamically adjusted according to channel changes, which reduces the accuracy of the feedback channel information, thereby reducing the performance of precoding.
  • the channel information feedback scheme based on deep learning uses deep neural network (DNN), convolutional neural network (CNN) to directly encode and compress the channel information obtained after channel estimation, compared with the traditional codebook-based channel Information feedback, significantly improving the feedback accuracy.
  • this feedback method is still a one-to-one mode, that is, the input of the encoder is the estimated channel vector of the nth subband at the tth moment, which is quantized and compressed into a bit stream and fed back to the decoder; the output of the decoder is corresponding to the tth The channel vector of the nth subband at time instant.
  • channels with different feedback periods have different degrees of time-domain correlation.
  • the time-domain correlation of channels is relatively high; Frequency domain correlation, for example, in a scenario where multipath influence is weak, channel frequency domain correlation is high. Therefore, under the fixed feedback bit overhead, the accuracy of one-to-one channel compression feedback and recovery is limited; in addition, for the CSI feedback process adopted by NR, the periodic, non-periodic and semi-persistent feedback methods adopted, because there is no By using the correlation of the channel in the time domain and the frequency domain, when a certain channel restoration accuracy is achieved, there are more redundant feedback bits, so the feedback bit overhead is also high. Therefore, how to effectively use the correlation between the time domain and the frequency domain of the channel in different channel scenarios, and effectively reduce the CSI feedback overhead while ensuring the accuracy of channel vector compression feedback and recovery, is an urgent technical problem to be solved.
  • this application proposes a CSI feedback scheme, which can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the CSI Feedback accuracy and reduce CSI feedback overhead.
  • FIG. 8 is a schematic flowchart of a channel information feedback method 200 according to an embodiment of the present application. As shown in FIG. 8 , the channel information feedback method 200 may include at least part of the following content:
  • the receiving end device acquires target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N ⁇ 2.
  • the originating device may perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles.
  • the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  • the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the CSI feedback accuracy and reduce the CSI feedback accuracy. overhead.
  • the process of periodic CSI feedback can be shown in Figure 9, for example; wherein, the period T indicates that the transmission of CSI-RS can be performed at intervals of T time slots, and the same CSI reporting can also be performed at intervals of T time slots,
  • the period T is configured by RRC signaling. Assuming that the number of CSI feedback bits each time is M, the downlink CSI-RS is sent and CSI is reported in the 0th time slot, then for the subsequent consecutive N*T time slots, a total of N times of CSI reporting are required, and N*M Number of feedback bits.
  • the receiving device obtains the CSI feedback periods of the N CSI feedback periods according to the CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback periods in the N CSI feedback periods through a neural network.
  • Target channel vector the CSI feedback periods of the N CSI feedback periods according to the CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback periods in the N CSI feedback periods through a neural network.
  • the receiving device is a terminal device, and the sending device is a network device; or, the receiving device is a network device, and the sending device is a terminal device.
  • the receiving device is a terminating device and the originating device is another terminating device.
  • the embodiment of the present application is applied to sidelink (sidelink, SL) communication.
  • the originating device is a network device
  • the receiving device is another network device.
  • the embodiment of the present application is applied to backhaul link (backhaul link) communication.
  • the K CSI feedback cycles in the N CSI feedback cycles perform downlink CSI-RS transmission and CSI reporting, and the CSI of the CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles Predicted by neural network, K is a positive integer, and K ⁇ N.
  • the receiving device receives K bit streams sent by the transmitting device, and the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles;
  • the receiving device decodes the K bit streams respectively to obtain K target channel vectors for the K CSI feedback cycles; the receiving device predicts the K target channel vectors through the first receiving neural network to obtain N-K target channel vectors of CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles.
  • the originating device may respectively encode the channel vectors of K CSI feedback periods in the N CSI feedback periods to obtain the K bit streams. For example, for each of the K CSI feedback cycles, the transmitting device performs channel estimation based on the CSI-RS to obtain channel information between the transmitting device and the receiving device; and performs eigendecomposition on the channel information to obtain the channel vector ; Then encode the channel vector to obtain the bit stream.
  • the first receiving-end neural network extracts the CSI time-domain correlation of different CSI feedback cycles, adopts sequence input and sequence output, therefore, the first receiving-end neural network can be based on LSTM, GRU, for example RNN is used as an example, or other neural networks with better predictive performance, which is not limited in this application.
  • the first receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
  • the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  • the receiving end device decodes the K bit streams respectively through the second receiving end neural network to obtain the K target channel vectors.
  • the second receiving neural network may be a neural network used for image processing, such as CNN or DNN, or other neural networks with better image processing performance, which is not limited in this application.
  • the second receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
  • the bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1; specifically, the receiving end device uses the second receiving end neural network pair from the i-Lth
  • the bit stream on the jth subband of the first CSI feedback period is decoded to the bitstream on the jth subband of the ith CSI feedback period, and the ith CSI feedback period from
  • the bit stream from the first sub-band to the S-th sub-band is decoded to obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, and L are all positive integers, and 1 ⁇ i ⁇ K , 1 ⁇ j ⁇ S, L ⁇ i; and the receiving device acquires the K target channel vectors according to the target channel vectors on the j-th subband of the i-th CSI feedback period.
  • the bit stream that the transmitting device needs to feed back includes information of S subbands.
  • the second receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the second receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
  • the second receiving-end neural network extracts the CSI time domain correlation of L CSI feedback cycles and the CSI frequency domain correlation of S subbands, it adopts sequence input and sequence output. Therefore, the first The neural network at the receiving end can be, for example, RNN such as LSTM and GRU, or other neural networks with better predictive performance, which is not limited in this application. Specifically, it may be shown in FIG. 10 .
  • bit stream (b iL,j ) on the j-th subband of the iL-th CSI feedback cycle to the bit stream (b i ,j ) on the j-th sub-band of the i-th CSI feedback cycle are respectively input to the second receiving end
  • the time-domain LSTM unit in the neural network, and the bit stream from the first subband (b i,1 ) to the bit stream (b i,S ) of the S subband in the i-th CSI feedback period are respectively input into the second
  • the frequency-domain LSTM unit in the receiving-end neural network, and the output of the time-domain LSTM unit and the frequency-domain LSTM unit pass through a fully connected layer, and finally obtain the target channel vector on the j-th subband of the i-th CSI feedback cycle
  • serial structure of L time-domain LSTM units shown in Figure 10 does not mean that the actual structure contains L different time-domain LSTM units, but the L-order sequence of the same time-domain LSTM unit The expansion of the input shows that in fact only one time-domain LSTM unit is included in the system.
  • serial structure of S frequency-domain LSTM units does not mean that the actual structure contains S different frequency-domain LSTM units, but an expanded representation of the S-order sequence input of the same frequency-domain LSTM unit. In fact, the system Contains only one frequency-domain LSTM unit in .
  • this embodiment is not limited to the configuration method of the main feedback subband and the auxiliary feedback subband in each CSI feedback period, nor is it limited to the configuration method of the main feedback subband and the auxiliary feedback subband in different CSI feedback periods , this embodiment can support other flexible configuration methods of primary feedback subbands and secondary feedback subbands with a certain periodicity principle, and configure them through RRC or DCI signaling, so as to reduce the overhead of CSI periodic feedback.
  • the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  • the network device configures the primary feedback subband and the secondary feedback subband among the S subbands through RRC signaling.
  • the network device configures the primary feedback subband and the secondary feedback subband among the S subbands through DCI signaling.
  • the network device jointly configures the primary feedback subband and the secondary feedback subband in the S subbands through RRC signaling and DCI signaling.
  • the values of K and N are determined from the group G ⁇ K, N ⁇ , G is a positive integer, and G ⁇ 2.
  • K K 1 and N 1 respectively, or the values of K and N may be K 2 and N 2 respectively, or the values of K and N may be K 3 and N 3 respectively.
  • the values of K and N are determined from the G group ⁇ K, N ⁇ according to channel scenarios.
  • G 3, that is, there are 3 sets of ⁇ K, N ⁇ configured, which are respectively recorded as ⁇ K 1 , N 1 ⁇ , ⁇ K 2 , N 2 ⁇ and ⁇ K 3 , N 3 ⁇ .
  • the values of K and N can be K 1 and N 1 respectively;
  • the values of K and N can be K 2 and N 2 respectively.
  • the values of K and N can be K 3 and N 3 respectively.
  • the G group ⁇ K, N ⁇ is configured by the network device through RRC signaling and/or DCI signaling.
  • the network device jointly configures the G group ⁇ K, N ⁇ through RRC signaling and DCI signaling.
  • the G group ⁇ K, N ⁇ is set by the network device through RRC signaling and/or DCI signaling bit configuration, where, Indicates rounding up.
  • the network device configures ⁇ K, N ⁇ for the terminal device through RRC signaling or DCI signaling.
  • the network device needs to configure 2 groups ⁇ K, N ⁇ .
  • the network device configures the 2 groups ⁇ K, N ⁇ through RRC signaling or 1 bit in DCI signaling.
  • the network device needs to configure 3 groups ⁇ K, N ⁇ .
  • the network device configures the 3 groups ⁇ K, N ⁇ through 2 bits in RRC signaling or DCI signaling.
  • the first K CSI feedback cycles in the N CSI feedback cycles perform downlink CSI-RS transmission and CSI reporting, and the CSI of the next N-K CSI feedback cycles is obtained by prediction through a neural network.
  • the structure can be shown in Figure 13.
  • the input of the encoder is the channel vector of the previous K CSI feedback cycles, and the output is a bit stream and reported to the network side through CSI;
  • the input of the decoder on the network side is the feedback bit stream of the previous K CSI feedback cycles,
  • the output is the estimated channel vector (ie, the target channel vector).
  • the estimated channel vectors of K CSI feedback periods are jointly used as the input of the predictor, and the output is the predicted channel vector (ie, the target channel vector) of the following N-K CSI feedback periods.
  • the predictor in Figure 13 extracts the time-domain correlation of CSI of different periods, adopts sequence input and sequence output, and can use RNN such as LSTM and GRU, which correspond to the above-mentioned first receiving end neural network;
  • the decoder can be Neural networks such as DNN and CNN are used, which correspond to the above-mentioned second receiving neural network;
  • the encoder usually adopts neural networks such as DNN and CNN. This embodiment does not limit the specific implementation scheme of the neural network inside each neural network, so as to design different functions according to different communication scenarios.
  • the encoder, decoder and calibrator in Figure 13 above are trained as follows:
  • the input training data and labels in this step are channel vector w
  • the loss function includes but not limited to estimated channel vector (ie the target channel vector) and the mean squared error (Mean Squared Error, MSE) or cosine similarity (GCS) of the channel vector w, etc.
  • MSE mean squared error
  • GCS cosine similarity
  • Predictor training Train the predictor by optimizing the loss function and fixing the network model and parameters of the encoder and decoder.
  • the input of the prediction neural network is set as the sequence of recovered target channel vectors in the first K CSI feedback cycles, and the output is the predicted channel vector (ie, the target channel vector) of the next NK CSI feedback cycles.
  • the above training method requires that the network parameters of the encoder and decoder have been fixed when training the predictor, in order to ensure that the output of the decoder during training matches the inference output of the decoder during actual deployment.
  • the encoder, decoder, and predictor can be deployed and trained offline or online.
  • the CSI of the next N-K CSI feedback cycles can use CSI time domain correlation, And a reasonable neural network is designed, so the feedback overhead is reduced to K/N of the periodic feedback scheme in the current NR system, and the CSI feedback overhead is reduced. Further, according to different channel scenarios, different combinations of ⁇ K, N ⁇ should be used to achieve a trade-off between feedback bit overhead and predicted CSI accuracy.
  • N CSI feedback cycles are classified to obtain P primary CSI feedback cycles and Q secondary CSI feedback cycles.
  • different neural networks are designed to restore the CSI of the main CSI feedback period and the auxiliary CSI feedback period.
  • the receiving device receives P bit streams and Q bit streams sent by the source device; wherein, the P bit streams are respectively generated by the P main CSI feedback cycles in the N CSI feedback cycles
  • the receiving end device decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback cycles; and the receiving end device respectively uses the third receiving end neural network for the Q bit streams
  • the first bit stream and the second bit stream in the P bit streams are decoded to obtain the Q target channel vectors of the Q secondary CSI feedback cycles; wherein, the secondary CSI feedback cycle corresponding to the
  • the source device can encode the channel vectors of the P main CSI feedback periods respectively to obtain P bit streams. For example, for each primary CSI feedback cycle in the P primary CSI feedback cycles, the transmitting device performs channel estimation according to the CSI-RS to obtain the channel information between the transmitting device and the receiving device; and performs eigendecomposition on the channel information to obtain channel vector; and then encode the channel vector to obtain a bit stream.
  • the originating device may respectively encode the channel vectors of the Q secondary CSI feedback periods to obtain Q bit streams.
  • the originating device may separately encode the difference between the channel vectors of Q secondary CSI feedback periods in the N CSI feedback periods and the channel vector of the corresponding primary CSI feedback period to obtain Q bit streams.
  • the third receiving-end neural network extracts the CSI time-domain correlation of different CSI feedback cycles, adopts sequence input and sequence output, therefore, the third receiving-end neural network can be based on LSTM, GRU, for example RNN is used as an example, or other neural networks with better predictive performance, which is not limited in this application.
  • the third receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as a fully connected layer, a convolutional layer, a recurrent neural network layer, and an activation function layer.
  • basic neural network structures such as a fully connected layer, a convolutional layer, a recurrent neural network layer, and an activation function layer.
  • the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams. That is, the number of bits occupied by the bit stream fed back in the secondary CSI feedback cycle is smaller than the number of bits occupied by the bit stream fed back in the primary CSI feedback cycle.
  • different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
  • one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  • N consecutive CSI feedback cycles within N consecutive CSI feedback cycles, it is classified into a configuration in which one primary CSI feedback cycle is accompanied by N-1 secondary CSI feedback cycles, wherein one primary CSI feedback cycle feeds back M bits, and N- Different ⁇ m 1 , m 2 , . . . , m N-1 ⁇ bits are fed back in one secondary CSI feedback cycle.
  • the source device feeds back the bit stream b 0 to the sink device in the primary CSI feedback cycle, and the source device feeds back b 1 , b 2 ,... in N-1 secondary CSI feedback cycles respectively ,b N-1 .
  • the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles associated with different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
  • the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
  • the network device jointly configures the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles through RRC signaling and DCI signaling.
  • the receiving-end device decodes the P bit streams respectively through the fourth receiving-end neural network to obtain P target channel vectors of the P main CSI feedback periods.
  • the fourth receiving neural network may be a neural network used for image processing, such as CNN or DNN, or other neural networks with better image processing performance, which is not limited in this application.
  • the fourth receiving neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
  • the bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1; specifically, the receiving end device uses the fourth receiving end neural network pair from the i-Lth
  • the bit stream on the jth subband of the first CSI feedback period is decoded to the bitstream on the jth subband of the ith CSI feedback period, and the fourth receiver neural network is used to decode the ith CSI feedback period from
  • the bit stream from the first sub-band to the S-th sub-band is decoded to obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, and L are all positive integers, and 1 ⁇ i ⁇ P , 1 ⁇ j ⁇ S, L ⁇ i; and the receiving device obtains P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the jth subband of the ith CSI feedback period.
  • the bit stream that the transmitting device needs to feed back includes information of S subbands.
  • the fourth receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the fourth receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
  • the fourth receiver neural network since the fourth receiver neural network extracts the CSI time-domain correlations of L main CSI feedback cycles and the CSI frequency-domain correlations of S subbands, it adopts sequence input and sequence output. Therefore, the The fourth receiving neural network may be, for example, an RNN such as LSTM or GRU, or other neural networks with better predictive performance, which is not limited in this application.
  • the number of bits fed back by the CSI of the originating device is M, and when the channel changes slowly, there is a strong time-domain correlation between channels in adjacent CSI feedback cycles, Therefore, a smaller number of bits m can be fed back in the second CSI feedback cycle, where m ⁇ M, the third receiver neural network is used to extract the time-domain correlation of CSI with the first CSI feedback cycle and restore the second CSI CSI for the feedback cycle.
  • the CSI feedback cycle that utilizes complete M bits for reporting during CSI feedback is called the primary CSI feedback cycle
  • the CSI feedback cycle that uses fewer m bits for reporting during CSI feedback is called secondary CSI Feedback period
  • design different neural networks to restore the CSI of the main CSI feedback period and the auxiliary CSI feedback period by extracting the time domain correlation between the main CSI feedback period and the auxiliary CSI feedback period Taking the first CSI feedback cycle as the primary CSI feedback cycle and the second CSI feedback cycle as the secondary CSI feedback cycle as an example, the specific architecture may be shown in FIG. 17 .
  • the input of the main CSI feedback cycle decoder (corresponding to the fourth receiving end neural network) is b 1
  • the input of the auxiliary CSI feedback cycle decoder (corresponding to the third receiving end neural network above) is [b 1 , b 2 ]
  • the auxiliary CSI feedback cycle decoder (corresponding to the third receiving end neural network) is [b 1 , b 2 ].
  • the CSI feedback cycle decoder may also adopt a DNN, CNN, etc. structure similar to that of the main CSI feedback cycle decoder.
  • its input is not limited to the channel vector w 2 , but can also be the difference between the channel vector w 2 and w 1 , or other features representing the difference between channels.
  • periodic feedback based on CSI time-frequency domain joint correlation.
  • the receiving end device receives N bit streams sent by the sending end device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1; the receiving end The device decodes the bit stream from the jth subband of the i-Lth CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and through the fifth receiving terminal The terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1 ⁇ i ⁇ N, 1 ⁇ j ⁇ S, L ⁇ i; and the receiving device obtains the N according to the target channel vector on the jth subband of the ith CSI feedback period The target channel vector of CSI feedback periods.
  • the bit stream that the transmitting device needs to feed back includes information of S subbands.
  • the fifth receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the fifth receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
  • the fifth receiving-end neural network extracts the CSI time domain correlation of L CSI feedback cycles and the CSI frequency domain correlation of S subbands, it adopts sequence input and sequence output. Therefore, the first The five-receiver neural network can be, for example, RNN such as LSTM and GRU, or other neural networks with better predictive performance, which is not limited in this application.
  • the CSI of the j-th subband in the i-th feedback cycle can be passed through the CSI of the j-1th sub-band and the j+1-th sub-band in the i-th feedback cycle, and the i-1th sub-band
  • the CSI of the jth sub-band of the first feedback cycle is obtained by extracting the joint correlation of the time domain and the frequency domain, and using a neural network.
  • the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles
  • the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles.
  • the CSI correlation among them is used to obtain the target channel vector of N CSI feedback periods. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
  • This application includes but is not limited to the technical solutions given in the above embodiments.
  • the specific structural design inside each neural network, as well as configuration parameters such as N, K, and L, etc. can be based on different communication scenarios, such as terminal moving speed , Channel delay expansion and other characteristics adaptive adjustment to optimize transmission performance.
  • the embodiment of the present application is not limited to the channel vector compression and feedback between the base station and the terminal, and the embodiment of the present application can also be applied between the terminal and the terminal (such as Sidelink), and between the base station and the base station (such as the backhaul link ( backhaul link)) possible CSI feedback overhead reduction requirements.
  • the embodiments of the present application focus on protecting the AI-based method for reducing the overhead of periodic CSI feedback.
  • FIG. 18 is a schematic flowchart of a channel information feedback method 300 according to an embodiment of the present application. As shown in FIG. 18 , the channel information feedback method 300 may include at least part of the following content:
  • the transmitting device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N ⁇ 2.
  • the receiving end device acquires the target channel vectors of the N CSI feedback periods according to the CSI correlation between different CSI feedback periods in the N CSI feedback periods.
  • the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  • the above S310 may specifically include:
  • the originating device encodes the channel vectors of K CSI feedback periods in the N CSI feedback periods through the first originating neural network to obtain K bit streams; and the originating device does not divide the N CSI feedback periods
  • the channel vectors of the CSI feedback periods other than the K CSI feedback periods are encoded; the transmitting device sends the K bit streams to the receiving device respectively.
  • the bit streams in the K bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  • the values of K and N are determined from the group G ⁇ K, N ⁇ , G is a positive integer, and G ⁇ 2.
  • the values of K and N are determined from the G group ⁇ K, N ⁇ according to the channel scenario.
  • the G group ⁇ K, N ⁇ is configured by the network device through RRC signaling or DCI signaling.
  • the G group ⁇ K, N ⁇ is set by the network device through RRC signaling and/or DCI signaling bit configuration, where, Indicates rounding up.
  • the above S310 may specifically include:
  • the originating device respectively encodes the channel vectors of the P main CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain P bit streams;
  • the originating device respectively encodes the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;
  • the bit streams in the P bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  • different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
  • one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  • the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
  • the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
  • the above S310 may specifically include:
  • the originating device respectively encodes the channel vectors of the N CSI feedback cycles through a third originating neural network to obtain N bit streams;
  • the originating device sends the N bit streams to the receiving device respectively.
  • the bit streams in the N bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  • the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles
  • the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles.
  • the CSI correlation among them is used to obtain the target channel vector of N CSI feedback periods. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
  • Fig. 19 shows a schematic block diagram of a receiving device 400 according to an embodiment of the present application.
  • the receiving end device 400 includes:
  • the processing unit 410 is configured to acquire target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N ⁇ 2.
  • the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  • the receiving device 400 includes a communication unit 420, wherein,
  • the communication unit 420 is configured to receive K bit streams sent by the originating device, the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles, and K is a positive integer , and K ⁇ N;
  • the processing unit 410 is configured to respectively decode the K bit streams to obtain K target channel vectors for the K CSI feedback cycles;
  • the processing unit 410 is configured to predict the K target channel vectors through the first receiving-end neural network, and obtain N-K target channel vectors of CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles .
  • the processing unit 410 is specifically used for:
  • the K bit streams are respectively decoded by the second receiving-end neural network to obtain the K target channel vectors.
  • bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1; the processing unit 410 is specifically used for:
  • the terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1 ⁇ i ⁇ K, 1 ⁇ j ⁇ S, L ⁇ i;
  • the K target channel vectors are acquired according to the target channel vectors on the j th subband of the i th CSI feedback period.
  • the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  • the values of K and N are determined from the group G ⁇ K, N ⁇ , G is a positive integer, and G ⁇ 2.
  • the values of K and N are determined from the G group ⁇ K, N ⁇ according to the channel scenario.
  • the G group ⁇ K, N ⁇ is configured by the network device through radio resource control RRC signaling and/or downlink control information DCI signaling.
  • the G group ⁇ K, N ⁇ is set by the network device through RRC signaling or DCI signaling bit configuration, where, Indicates rounding up.
  • the receiving device 400 includes a communication unit 420, wherein,
  • the communication unit 420 is configured to receive P bit streams and Q bit streams sent by the originating device; wherein, the P bit streams are respectively encoded by the channel vectors of the P main CSI feedback cycles in the N CSI feedback cycles Obtained later, the Q bit streams are respectively obtained by encoding the channel vectors of the Q secondary CSI feedback cycles in the N CSI feedback cycles, or the Q bit streams are respectively obtained by the N CSI feedback cycles
  • the processing unit 410 is configured to respectively decode the P bit streams to obtain P target channel vectors of the P main CSI feedback cycles;
  • the processing unit 410 is configured to respectively decode the first bit stream in the Q bit streams and the second bit stream in the P bit streams through the third receiving-end neural network to obtain the Q secondary CSI feedback cycles Q target channel vectors; wherein, the secondary CSI feedback cycle corresponding to the first bit stream is the secondary CSI feedback cycle accompanying the primary CSI feedback cycle corresponding to the second bit stream.
  • the processing unit 410 is specifically used for:
  • the P bit streams are respectively decoded by the fourth receiving-end neural network to obtain P target channel vectors of the P main CSI feedback cycles.
  • bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1; the processing unit 410 is specifically used for:
  • the bit stream on the jth subband of the i-Lth CSI feedback period to the bitstream on the jth subband of the ith CSI feedback period is decoded through the fourth receiving end neural network, and through the fourth receiving end
  • the terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1 ⁇ i ⁇ P, 1 ⁇ j ⁇ S, L ⁇ i;
  • the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  • different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
  • one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  • the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
  • the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
  • the receiving device 400 includes a communication unit 420, wherein,
  • the communication unit 420 is configured to receive N bit streams sent by the originating device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1;
  • the processing unit 410 is configured to decode the bit stream from the jth subband of the i-L CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and Decode the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle through the fifth receiving-end neural network, and obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle , i, j, L are all positive integers, and 1 ⁇ i ⁇ N, 1 ⁇ j ⁇ S, L ⁇ i;
  • the processing unit 410 is configured to acquire the target channel vectors of the N CSI feedback periods according to the target channel vectors on the jth subband of the i-th CSI feedback period.
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is less than the at least one auxiliary feedback subband The number of bits occupied by the information of the main feedback subband in one main feedback subband.
  • the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  • the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip.
  • the aforementioned processing unit may be one or more processors.
  • the receiving end device 400 may correspond to the receiving end device in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the receiving end device 300 are respectively in order to realize the For the sake of brevity, the corresponding process of the receiving device in the shown method 200 is not repeated here.
  • Fig. 20 shows a schematic block diagram of an originating device 500 according to an embodiment of the present application.
  • the originating device 500 includes:
  • the processing unit 510 is configured to perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; wherein, N is a positive integer, and N ⁇ 2.
  • the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  • the originating device 500 further includes a communication unit 520, wherein,
  • the processing unit 510 is configured to respectively encode the channel vectors of the K CSI feedback cycles in the N CSI feedback cycles through the first sending-end neural network to obtain K bit streams; and the processing unit does not encode the N CSI feedback cycles
  • the channel vectors of the CSI feedback cycles other than the K CSI feedback cycles are encoded;
  • the communication unit 520 is configured to respectively send the K bit streams to the receiving device.
  • the bit streams in the K bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  • the values of K and N are determined from the group G ⁇ K, N ⁇ , G is a positive integer, and G ⁇ 2.
  • the values of K and N are determined from the G group ⁇ K, N ⁇ according to the channel scenario.
  • the G group ⁇ K, N ⁇ is configured by the network device through radio resource control RRC signaling or downlink control information DCI signaling.
  • the G group ⁇ K, N ⁇ is set by the network device through RRC signaling and/or DCI signaling bit configuration.
  • the originating device 500 further includes a communication unit 520, wherein,
  • the processing unit 510 is configured to respectively encode the channel vectors of the P main CSI feedback cycles in the N CSI feedback cycles through the second sending-end neural network to obtain P bit streams;
  • the processing unit 510 is configured to respectively encode the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;
  • the bit streams in the P bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  • different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
  • one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  • the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
  • the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
  • the originating device 500 further includes a communication unit 520, wherein,
  • the processing unit 510 is configured to respectively encode the channel vectors of the N CSI feedback cycles through the third originating neural network to obtain N bit streams;
  • the communication unit 520 is configured to respectively send the N bit streams to the receiving device.
  • the bit streams in the N bit streams include information of S subbands
  • the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband
  • the number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
  • the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  • the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip.
  • the aforementioned processing unit may be one or more processors.
  • the originating device 500 may correspond to the originating device in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the originating device 500 are for realizing the method shown in FIG. 18 For the sake of brevity, the corresponding process of the originating device in 300 will not be repeated here.
  • FIG. 21 is a schematic structural diagram of a communication device 600 provided by an embodiment of the present application.
  • the communication device 600 shown in FIG. 21 includes a processor 610, and the processor 610 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.
  • the communication device 600 may further include a memory 620 .
  • the processor 610 can invoke and run a computer program from the memory 620, so as to implement the method in the embodiment of the present application.
  • the memory 620 may be an independent device independent of the processor 610 , or may be integrated in the processor 610 .
  • the communication device 600 may further include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or Receive messages or data from other devices.
  • the transceiver 630 may include a transmitter and a receiver.
  • the transceiver 630 may further include antennas, and the number of antennas may be one or more.
  • the communication device 600 may specifically be the originating device in the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the originating device in each method of the embodiment of the present application. For the sake of brevity, the Let me repeat.
  • the communication device 600 may specifically be the receiving device of the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the receiving device in each method of the embodiment of the present application. For brevity, the This will not be repeated here.
  • Fig. 22 is a schematic structural diagram of a device according to an embodiment of the present application.
  • the apparatus 700 shown in FIG. 22 includes a processor 710, and the processor 710 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.
  • the device 700 may further include a memory 720 .
  • the processor 710 can invoke and run a computer program from the memory 720, so as to implement the method in the embodiment of the present application.
  • the memory 720 may be an independent device independent of the processor 710 , or may be integrated in the processor 710 .
  • the device 700 may further include an input interface 730 .
  • the processor 710 can control the input interface 730 to communicate with other devices or chips, specifically, can obtain information or data sent by other devices or chips.
  • the device 700 may further include an output interface 740 .
  • the processor 710 can control the output interface 740 to communicate with other devices or chips, specifically, can output information or data to other devices or chips.
  • the apparatus can be applied to the originating device in the embodiments of the present application, and the apparatus can implement the corresponding processes implemented by the originating device in the methods of the embodiments of the present application. For the sake of brevity, details are not repeated here.
  • the device can be applied to the receiving device in the embodiments of the present application, and the device can implement the corresponding processes implemented by the receiving device in the methods of the embodiments of the present application. For the sake of brevity, no further repeat.
  • the device mentioned in the embodiment of the present application may also be a chip.
  • it may be a system-on-a-chip, a system-on-a-chip, a system-on-a-chip, or a system-on-a-chip.
  • FIG. 23 is a schematic block diagram of a communication system 800 provided by an embodiment of the present application. As shown in FIG. 23 , the communication system 800 includes an originating device 810 and a receiving device 820 .
  • the originating device 810 can be used to realize the corresponding functions realized by the originating device in the above method
  • the receiving device 820 can be used to realize the corresponding functions realized by the receiving device in the above method. Let me repeat.
  • the processor in the embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • each step of the above-mentioned method embodiments may be completed by an integrated logic circuit of hardware in a processor or instructions in the form of software.
  • the above-mentioned processor can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other available Program logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories.
  • the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electronically programmable Erase Programmable Read-Only Memory (Electrically EPROM, EEPROM) or Flash.
  • the volatile memory can be Random Access Memory (RAM), which acts as external cache memory.
  • RAM Static Random Access Memory
  • SRAM Static Random Access Memory
  • DRAM Dynamic Random Access Memory
  • Synchronous Dynamic Random Access Memory Synchronous Dynamic Random Access Memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM, DDR SDRAM enhanced synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM synchronous connection dynamic random access memory
  • Synchlink DRAM, SLDRAM Direct Memory Bus Random Access Memory
  • Direct Rambus RAM Direct Rambus RAM
  • the memory in the embodiment of the present application may also be a static random access memory (static RAM, SRAM), a dynamic random access memory (dynamic RAM, DRAM), Synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection Dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is, the memory in the embodiments of the present application is intended to include, but not be limited to, these and any other suitable types of memory.
  • the embodiment of the present application also provides a computer-readable storage medium for storing computer programs.
  • the computer-readable storage medium can be applied to the originating device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the originating device in the methods of the embodiments of the present application. For brevity, I won't repeat them here.
  • the computer-readable storage medium can be applied to the terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the terminal device in the methods of the embodiments of the present application, in order It is concise and will not be repeated here.
  • the embodiment of the present application also provides a computer program product, including computer program instructions.
  • the computer program product can be applied to the originating device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the originating device in the various methods of the embodiments of the present application. For brevity, the This will not be repeated here.
  • the computer program product can be applied to the receiving device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the receiving device in the methods of the embodiments of the present application.
  • the computer program instructions cause the computer to execute the corresponding processes implemented by the receiving device in the methods of the embodiments of the present application.
  • the embodiment of the present application also provides a computer program.
  • the computer program can be applied to the originating device in the embodiment of the present application.
  • the computer program executes the corresponding process implemented by the originating device in each method of the embodiment of the present application, For the sake of brevity, details are not repeated here.
  • the computer program can be applied to the receiving device in the embodiments of the present application.
  • the computer program executes the corresponding functions implemented by the receiving device in the methods of the embodiments of the present application. For the sake of brevity, the process will not be repeated here.
  • the disclosed systems, devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

Embodiments of the present application provide a channel information feedback method, a receiving end device, and a transmitting end device. CSI feedback is performed by using CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback periods in N CSI feedback periods, so that the feedback precision of CSI can be improved and CSI feedback overhead is reduced. The channel information feedback method comprises: the receiving end device obtains a target channel vector of the N CSI feedback periods according to CSI correlation between different CSI feedback periods in the N CSI feedback periods, wherein N is a positive integer, and N≥2.

Description

信道信息的反馈方法、收端设备和发端设备Channel information feedback method, receiving device and sending device 技术领域technical field
本申请实施例涉及通信领域，并且更具体地，涉及一种信道信息的反馈方法、收端设备和发端设备。The embodiments of the present application relate to the communication field, and more specifically, relate to a channel information feedback method, a receiving device, and a sending device.
背景技术Background technique
在新空口(New Radio，NR)***中，信道状态信息(Channel State Information，CSI)可以基于码本进行反馈，具体的，根据高层信令配置，周期性、非周期性或者半持续地，利用估计出的信道从码本中挑选最优的反馈矩阵和对应的反馈系数。但是，由于码本本身是预先设定的有限集合，即从估计出的信道到码本中的信道的映射过程是量化有损的。同时，固定的码本设计无法根据信道的变化而进行动态的调整，这使得反馈的信道信息精确度下降，进而降低了预编码的性能。In the New Radio (NR) system, the channel state information (Channel State Information, CSI) can be fed back based on the codebook. Specifically, according to the high-level signaling configuration, periodically, aperiodically or semi-persistently, using The estimated channel selects the optimal feedback matrix and corresponding feedback coefficients from the codebook. However, since the codebook itself is a pre-set finite set, that is, the mapping process from the estimated channel to the channel in the codebook is quantized and lossy. At the same time, the fixed codebook design cannot be dynamically adjusted according to channel changes, which reduces the accuracy of the feedback channel information, thereby reducing the performance of precoding.
发明内容Contents of the invention
本申请实施例提供了一种信道信息的反馈方法、收端设备和发端设备，利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。The embodiment of the present application provides a channel information feedback method, a receiving device and a transmitting device, which use the CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform The CSI feedback can improve the CSI feedback accuracy and reduce the CSI feedback overhead.
第一方面，提供了一种信道信息的反馈方法，该方法包括：In the first aspect, a channel information feedback method is provided, the method including:
收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取该N个CSI反馈周期的目标信道向量；其中，N为正整数，且N≥2。The receiving end device acquires target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; where N is a positive integer, and N≥2.
第二方面，提供了一种信道信息的反馈方法，该方法包括：In a second aspect, a channel information feedback method is provided, the method including:
发端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈；其中，N为正整数，且N≥2。The originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N≥2.
第三方面，提供了一种收端设备，用于执行上述第一方面中的方法。In a third aspect, a receiving device is provided, configured to execute the method in the first aspect above.
具体地，该收端设备包括用于执行上述第一方面中的方法的功能模块。Specifically, the receiving end device includes a functional module for executing the method in the first aspect above.
第四方面，提供了一种发端设备，用于执行上述第二方面中的方法。In a fourth aspect, an originating device is provided, configured to execute the method in the second aspect above.
具体地，该发端设备包括用于执行上述第二方面中的方法的功能模块。Specifically, the originating device includes a functional module for executing the method in the second aspect above.
第五方面，提供了一种收端设备，包括处理器和存储器。该存储器用于存储计算机程序，该处理器用于调用并运行该存储器中存储的计算机程序，执行上述第一方面中的方法。In a fifth aspect, a receiving device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect above.
第六方面，提供了一种发端设备，包括处理器和存储器。该存储器用于存储计算机程序，该处理器用于调用并运行该存储器中存储的计算机程序，执行上述第二方面中的方法。In a sixth aspect, an originating device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the second aspect above.
第七方面，提供了一种装置，用于实现上述第一方面至第二方面中的任一方面中的方法。In a seventh aspect, an apparatus is provided for implementing the method in any one of the first aspect to the second aspect above.
具体地，该装置包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有该装置的设备执行如上述第一方面至第二方面中的任一方面中的方法。Specifically, the device includes: a processor, configured to invoke and run a computer program from the memory, so that the device installed with the device executes the method in any one of the above first to second aspects.
第八方面，提供了一种计算机可读存储介质，用于存储计算机程序，该计算机程序使得计算机执行上述第一方面至第二方面中的任一方面中的方法。In an eighth aspect, there is provided a computer-readable storage medium for storing a computer program, and the computer program causes a computer to execute the method in any one of the above-mentioned first aspect to the second aspect.
第九方面，提供了一种计算机程序产品，包括计算机程序指令，所述计算机程序指令使得计算机执行上述第一方面至第二方面中的任一方面中的方法。In a ninth aspect, a computer program product is provided, including computer program instructions, the computer program instructions causing a computer to execute the method in any one of the above first to second aspects.
第十方面，提供了一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面至第二方面中的任一方面中的方法。In a tenth aspect, a computer program is provided, which, when running on a computer, causes the computer to execute the method in any one of the above first to second aspects.
通过上述技术方案，发端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，以及收端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取N个CSI反馈周期的目标信道向量。也即，本申请实施例可以利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。Through the above technical solution, the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in N CSI feedback cycles, and the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in N CSI feedback cycles , to obtain the target channel vector of N CSI feedback cycles. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
附图说明Description of drawings
图1是本申请实施例应用的一种通信***架构的示意性图。FIG. 1 is a schematic diagram of a communication system architecture applied in an embodiment of the present application.
图2是本申请提供的一种神经元的示意性图。Fig. 2 is a schematic diagram of a neuron provided in the present application.
图3是本申请提供的一种神经网络的示意性图。Fig. 3 is a schematic diagram of a neural network provided by the present application.
图4是本申请提供的一种卷积神经网络的示意性图。Fig. 4 is a schematic diagram of a convolutional neural network provided by the present application.
图5是本申请提供的一种LSTM单元的示意性图。Fig. 5 is a schematic diagram of an LSTM unit provided in the present application.
图6是本申请提供的一种信道信息反馈的示意性图。Fig. 6 is a schematic diagram of channel information feedback provided by the present application.
图7是本申请提供的另一种信道信息反馈的示意性图。Fig. 7 is a schematic diagram of another channel information feedback provided by the present application.
图8是根据本申请实施例提供的一种信道信息的反馈方法的示意性流程图。Fig. 8 is a schematic flowchart of a channel information feedback method provided according to an embodiment of the present application.
图9是根据本申请实施例提供的一种CSI周期性反馈的流程的示意性图。FIG. 9 is a schematic diagram of a process of periodic CSI feedback provided according to an embodiment of the present application.
图10是根据本申请实施例提供的一种CSI周期性反馈的示意性图。Fig. 10 is a schematic diagram of a CSI periodic feedback provided according to an embodiment of the present application.
图11是根据本申请实施例提供的一种主反馈子带与辅反馈子带交替配置的示意性图。Fig. 11 is a schematic diagram of an alternate configuration of primary feedback subbands and auxiliary feedback subbands according to an embodiment of the present application.
图12是根据本申请实施例提供的另一种CSI周期性反馈的流程的示意性图。FIG. 12 is a schematic diagram of another CSI periodic feedback process provided according to an embodiment of the present application.
图13是根据本申请实施例提供的一种CSI周期性反馈的示意性结构图。Fig. 13 is a schematic structural diagram of a CSI periodic feedback provided according to an embodiment of the present application.
图14是根据本申请实施例提供的一种主CSI反馈周期与辅CSI反馈周期的示意性图。Fig. 14 is a schematic diagram of a primary CSI feedback cycle and a secondary CSI feedback cycle provided according to an embodiment of the present application.
图15是根据本申请实施例提供的另一种CSI周期性反馈的示意性图。Fig. 15 is a schematic diagram of another CSI periodic feedback provided according to an embodiment of the present application.
图16是根据本申请实施例提供的另一种主CSI反馈周期与辅CSI反馈周期的示意性图。Fig. 16 is a schematic diagram of another primary CSI feedback cycle and secondary CSI feedback cycle provided according to an embodiment of the present application.
图17是根据本申请实施例提供的另一种CSI周期性反馈的示意性结构图。Fig. 17 is a schematic structural diagram of another CSI periodic feedback provided according to an embodiment of the present application.
图18是根据本申请实施例提供的另一种信道信息的反馈方法的示意性流程图。Fig. 18 is a schematic flowchart of another channel information feedback method provided according to an embodiment of the present application.
图19是根据本申请实施例提供的一种收端设备的示意性框图。Fig. 19 is a schematic block diagram of a receiving device provided according to an embodiment of the present application.
图20是根据本申请实施例提供的一种发端设备的示意性框图。Fig. 20 is a schematic block diagram of an originating device provided according to an embodiment of the present application.
图21是根据本申请实施例提供的一种通信设备的示意性框图。Fig. 21 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
图22是根据本申请实施例提供的一种装置的示意性框图。Fig. 22 is a schematic block diagram of a device provided according to an embodiment of the present application.
图23是根据本申请实施例提供的一种通信***的示意性框图。Fig. 23 is a schematic block diagram of a communication system provided according to an embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。针对本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. With regard to the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
本申请实施例的技术方案可以应用于各种通信***，例如：全球移动通讯(Global System of Mobile communication，GSM)***、码分多址(Code Division Multiple Access，CDMA)***、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)***、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)***、先进的长期演进(Advanced long term evolution，LTE-A)***、新空口(New Radio，NR)***、NR***的演进***、非授权频谱上的LTE(LTE-based access to unlicensed spectrum，LTE-U)***、非授权频谱上的NR(NR-based access to unlicensed spectrum，NR-U)***、非地面通信网络(Non-Terrestrial Networks，NTN)***、通用移动通信***(Universal Mobile Telecommunication System，UMTS)、无线局域网(Wireless Local Area Networks，WLAN)、无线保真(Wireless Fidelity，WiFi)、第五代通信(5th-Generation，5G)***、第六代通信(6th-Generation，6G)***或其他后续演进的通信***等。The technical solution of the embodiment of the present application can be applied to various communication systems, such as: Global System of Mobile communication (Global System of Mobile communication, GSM) system, code division multiple access (Code Division Multiple Access, CDMA) system, broadband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system , New Radio (NR) system, evolution system of NR system, LTE (LTE-based access to unlicensed spectrum, LTE-U) system on unlicensed spectrum, NR (NR-based access to unlicensed spectrum) on unlicensed spectrum unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system, sixth-generation communication (6th-Generation, 6G) system or other subsequent evolution communication systems, etc.
通常来说，传统的通信***支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信***将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信，或车联网(Vehicle to everything，V2X)通信等，本申请实施例也可以应用于这些通信***。Generally speaking, the number of connections supported by traditional communication systems is limited and easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication, but also support, for example, Device to Device (Device to Device, D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication, or Vehicle to everything (V2X) communication, etc. , the embodiments of the present application may also be applied to these communication systems.
在一些实施例中，本申请实施例中的通信***可以应用于载波聚合(Carrier Aggregation，CA)场景，也可以应用于双连接(Dual Connectivity，DC)场景，还可以应用于独立(Standalone，SA)布网场景。In some embodiments, the communication system in the embodiment of the present application can be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, can also be applied to a dual connectivity (Dual Connectivity, DC) scenario, and can also be applied to an independent (Standalone, SA ) meshing scene.
在一些实施例中，本申请实施例中的通信***可以应用于非授权频谱，其中，非授权频谱也可以认为是共享频谱；或者，本申请实施例中的通信***也可以应用于授权频谱，其中，授权频谱也可以认为是非共享频谱。In some embodiments, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to a licensed spectrum, Wherein, the licensed spectrum can also be regarded as a non-shared spectrum.
本申请实施例结合网络设备和终端设备描述了各个实施例，其中，终端设备也可以称为用户设备(User Equipment，UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置等。The embodiments of the present application describe various embodiments in conjunction with network equipment and terminal equipment, wherein the terminal equipment may also be referred to as user equipment (User Equipment, UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
终端设备可以是WLAN中的站点(STATION，ST)，可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字助理(Personal Digital Assistant，PDA)设备、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备、下一代通信***例如NR网络中的终端设备，或者未来演进的公共陆地移动网络(Public Land Mobile Network，PLMN)网络中的终端设备等。The terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital assistant (Personal Digital Assistant, PDA) devices, handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, next-generation communication systems such as terminal devices in NR networks, or future Terminal equipment in the evolved public land mobile network (Public Land Mobile Network, PLMN) network, etc.
在本申请实施例中，终端设备可以部署在陆地上，包括室内或室外、手持、穿戴或车载；也可以部署在水面上(如轮船等)；还可以部署在空中(例如飞机、气球和卫星上等)。In the embodiment of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites) superior).
在本申请实施例中，终端设备可以是手机(Mobile Phone)、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(Virtual Reality，VR)终端设备、增强现实(Augmented Reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(remote medical)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备或智慧家庭(smart home)中的无线终端设备等。In this embodiment of the application, the terminal device may be a mobile phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (Virtual Reality, VR) terminal device, an augmented reality (Augmented Reality, AR) terminal Equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid , wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, or wireless terminal equipment in smart home.
作为示例而非限定，在本申请实施例中，该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。As an example but not a limitation, in this embodiment of the present application, the terminal device may also be a wearable device. Wearable devices can also be called wearable smart devices, which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction. Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets and smart jewelry for physical sign monitoring.
在本申请实施例中，网络设备可以是用于与移动设备通信的设备，网络设备可以是WLAN中的接入点(Access Point，AP)，GSM或CDMA中的基站(Base Transceiver Station，BTS)，也可以是WCDMA中的基站(NodeB，NB)，还可以是LTE中的演进型基站(Evolutional Node B，eNB或eNodeB)，或者中继站或接入点，或者车载设备、可穿戴设备以及NR网络中的网络设备或者基站(gNB)或者未来演进的PLMN网络中的网络设备或者NTN网络中的网络设备等。In the embodiment of the present application, the network device may be a device for communicating with the mobile device, and the network device may be an access point (Access Point, AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA , or a base station (NodeB, NB) in WCDMA, or an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and an NR network A network device or a base station (gNB) in a network device or a network device in a future evolved PLMN network or a network device in an NTN network.
作为示例而非限定，在本申请实施例中，网络设备可以具有移动特性，例如网络设备可以为移动的设备。在一些实施例中，网络设备可以为卫星、气球站。例如，卫星可以为低地球轨道(low earth orbit，LEO)卫星、中地球轨道(medium earth orbit，MEO)卫星、地球同步轨道(geostationary earth orbit，GEO)卫星、高椭圆轨道(High Elliptical Orbit，HEO)卫星等。在一些实施例中，网络设备还可以为设置在陆地、水域等位置的基站。As an example but not a limitation, in this embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. In some embodiments, the network equipment may be a satellite, balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous earth orbit (geosynchronous earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite. ) Satellite etc. In some embodiments, the network device may also be a base station installed on land, in water, or other locations.
在本申请实施例中，网络设备可以为小区提供服务，终端设备通过该小区使用的传输资源(例如，频域资源，或者说，频谱资源)与网络设备进行通信，该小区可以是网络设备(例如基站)对应的小区，小区可以属于宏基站，也可以属于小小区(Small cell)对应的基站，这里的小小区可以包括：城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等，这些小小区具有覆盖范围小、发射功率低的特点，适用于提供高速率的数据传输服务。In this embodiment of the present application, the network device may provide services for a cell, and the terminal device communicates with the network device through the transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell, and the cell may be a network device ( For example, a cell corresponding to a base station), the cell may belong to a macro base station, or may belong to a base station corresponding to a small cell (Small cell), and the small cell here may include: a metro cell (Metro cell), a micro cell (Micro cell), a pico cell ( Pico cell), Femto cell, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
示例性的，本申请实施例应用的一种通信***可以如图1所示。如图1所示，该通信***100可以包括网络设备110，网络设备110可以是与终端设备120(或称为通信终端、终端)通信的设备。网络设备110可以为特定的地理区域提供通信覆盖，并且可以与位于该覆盖区域内的终端设备进行通信。Exemplarily, a communication system applied in this embodiment of the application may be shown in FIG. 1 . As shown in FIG. 1 , the communication system 100 may include a network device 110, and the network device 110 may be a device for communicating with a terminal device 120 (or called a communication terminal, terminal). The network device 110 can provide communication coverage for a specific geographical area, and can communicate with terminal devices located in the coverage area.
图1示例性地示出了一个网络设备和两个终端设备，在一些实施例中，该通信***100可以包括多个网络设备并且每个网络设备的覆盖范围内可以包括其它数量的终端设备，本申请实施例对此不做限定。FIG. 1 exemplarily shows one network device and two terminal devices. In some embodiments, the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within the coverage area. This embodiment of the present application does not limit it.
在一些实施例中，该通信***100还可以包括网络控制器、移动管理实体等其他网络实体，本申请实施例对此不作限定。In some embodiments, the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment of the present application.
应理解，本申请实施例中网络/***中具有通信功能的设备可称为通信设备。以图1示出的通信***100为例，通信设备可包括具有通信功能的网络设备110和终端设备120，网络设备110和终端设备120可以为上文所述的具体设备，此处不再赘述；通信设备还可包括通信***100中的其他设备，例如网络控制器、移动管理实体等其他网络实体，本申请实施例中对此不做限定。It should be understood that a device with a communication function in the network/system in the embodiment of the present application may be referred to as a communication device. Taking the communication system 100 shown in FIG. 1 as an example, the communication equipment may include a network equipment 110 and a terminal equipment 120 with communication functions. The network equipment 110 and the terminal equipment 120 may be the specific equipment described above, and will not be repeated here. The communication device may also include other devices in the communication system 100, such as network controllers, mobility management entities and other network entities, which are not limited in this embodiment of the present application.
应理解，本文中术语“***”和“网络”在本文中常被可互换使用。本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.
本申请的实施方式部分使用的术语仅用于对本申请的具体实施例进行解释，而非旨在限定本申请。本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。The terms used in the embodiments of the present application are only used to explain specific embodiments of the present application, and are not intended to limit the present application. The terms "first", "second", "third" and "fourth" in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order . Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion.
应理解，在本申请的实施例中提到的“指示”可以是直接指示，也可以是间接指示，还可以是表示具有关联关系。举例说明，A指示B，可以表示A直接指示B，例如B可以通过A获取；也可以表示A间接指示B，例如A指示C，B可以通过C获取；还可以表示A和B之间具有关联关系。It should be understood that the "indication" mentioned in the embodiments of the present application may be a direct indication, may also be an indirect indication, and may also mean that there is an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also indicate that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also indicate that there is an association between A and B relation.
在本申请实施例的描述中，术语“对应”可表示两者之间具有直接对应或间接对应的关系，也可以表示两者之间具有关联关系，也可以是指示与被指示、配置与被配置等关系。In the description of the embodiments of the present application, the term "corresponding" may indicate that there is a direct or indirect correspondence between the two, or that there is an association between the two, or that it indicates and is indicated, configuration and is configuration etc.
本申请实施例中，“预定义”或“预配置”可以通过在设备(例如，包括终端设备和网络设备)中预先保存相应的代码、表格或其他可用于指示相关信息的方式来实现，本申请对于其具体的实现方式不做限定。比如预定义可以是指协议中定义的。In this embodiment of the application, "predefined" or "preconfigured" can be realized by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices). The application does not limit its specific implementation. For example, pre-defined may refer to defined in the protocol.
本申请实施例中，所述“协议”可以指通信领域的标准协议，例如可以包括LTE协议、NR协议以及应用于未来的通信***中的相关协议，本申请对此不做限定。In the embodiment of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, may include the LTE protocol, the NR protocol, and related protocols applied to future communication systems, which is not limited in the present application.
为便于更好的理解本申请实施例，对本申请相关的NR***中的CSI反馈方案与上报配置进行说明。In order to better understand the embodiments of the present application, the CSI feedback scheme and reporting configuration in the NR system related to the present application will be described.
在NR***中，针对CSI反馈方案，通常采用基于码本的特征向量反馈使得基站获取下行CSI。具体地，基站向终端发送下行信道状态信息参考信号(Channel State Information Reference Signal，CSI-RS)，终端利用CSI-RS估计得到下行信道的CSI，并对估计得到的下行信道进行特征值分解，得到该下行信道对应的特征向量。终端按照一定规则，计算该特征向量在预先设定的码本中对应匹配的码字系数并进行量化反馈，基站根据终端反馈的量化后的CSI恢复特征向量。而对于CSI上报配置，其上报类型包括周期性上报、非周期性上报和半持续上报。对于周期性CSI上报和物理上行控制信道(Physical Uplink Control Channel，PUCCH)上的半持续上报，通过PUCCH反馈，周期由无线资源控制(Radio Resource Control，RRC)参数如时隙配置报告(reportSlotConfig)配置；对于物理上行共享信道(Physical Uplink Shared Channel，PUSCH)上的半持续和非周期上报，允许的时隙偏移由RRC参数如时隙偏移列表报告(reportSlotOffsetList)配置，通过接收下行控制信息(Downlink Control Information，DCI)进行触发。In the NR system, for the CSI feedback scheme, codebook-based eigenvector feedback is usually used to enable the base station to obtain downlink CSI. Specifically, the base station sends a downlink channel state information reference signal (Channel State Information Reference Signal, CSI-RS) to the terminal, and the terminal uses the CSI-RS to estimate the CSI of the downlink channel, and decomposes the eigenvalue of the estimated downlink channel to obtain The eigenvector corresponding to the downlink channel. According to certain rules, the terminal calculates the matching codeword coefficients of the eigenvector in the preset codebook and performs quantization feedback, and the base station restores the eigenvector according to the quantized CSI fed back by the terminal. As for the CSI reporting configuration, the reporting types include periodic reporting, aperiodic reporting and semi-persistent reporting. For periodic CSI reporting and semi-persistent reporting on the Physical Uplink Control Channel (Physical Uplink Control Channel, PUCCH), through PUCCH feedback, the period is configured by Radio Resource Control (RRC) parameters such as reportSlotConfig ; For semi-persistent and aperiodic reporting on the Physical Uplink Shared Channel (PUSCH), the allowed slot offset is configured by RRC parameters such as the slot offset list report (reportSlotOffsetList), by receiving the downlink control information ( Downlink Control Information, DCI) to trigger.
为便于更好的理解本申请实施例，对本申请相关的神经网络与深度学习进行说明。In order to facilitate a better understanding of the embodiments of the present application, the neural network and deep learning related to the present application will be described.
神经网络是一种由多个神经元节点相互连接构成的运算模型，其中节点间的连接代表从输入信号到输出信号的加权值，称为权重；每个节点对不同的输入信号进行加权求和(summation，SUM)，并通过特定的激活函数(f)输出。神经元结构例如如图2所示。一个简单的神经网络如图3所示，包含输入层、隐藏层和输出层，通过多个神经元不同的连接方式，权重和激活函数，可以产生不同的输出，进而拟合从输入到输出的映射关系。A neural network is an operational model composed of multiple neuron nodes connected to each other, in which the connection between nodes represents the weighted value from the input signal to the output signal, called weight; each node performs weighted summation of different input signals (summation, SUM), and output through a specific activation function (f). The neuron structure is shown in Figure 2, for example. A simple neural network is shown in Figure 3, which includes an input layer, a hidden layer and an output layer. Through different connection methods, weights and activation functions of multiple neurons, different outputs can be generated, and then fitted from input to output. Mapping relations.
深度学习采用多隐藏层的深度神经网络，极大提升了网络学习特征的能力，能够拟合从输入到输出的复杂的非线性映射，因而语音和图像处理领域得到广泛的应用。除了深度神经网络，面对不同任务，深度学习还包括卷积神经网络(Convolutional Neural Network，CNN)、循环神经网络(Recurrent Neural Network，RNN)等常用基本结构。Deep learning uses a deep neural network with multiple hidden layers, which greatly improves the ability of the network to learn features, and can fit complex nonlinear mappings from input to output, so it is widely used in the fields of speech and image processing. In addition to deep neural networks, in the face of different tasks, deep learning also includes common basic structures such as convolutional neural network (CNN), recurrent neural network (Recurrent Neural Network, RNN).
一个卷积神经网络的基本结构包括：输入层、多个卷积层、多个池化层、全连接层及输出层，如图4所示。卷积层中卷积核的每个神经元与其输入进行局部连接，并通过引入池化层提取某一层局部的最大值或者平均值特征，有效减少了网络的参数，并挖掘了局部特征，使得卷积神经网络能够快速收敛，获得优异的性能。The basic structure of a convolutional neural network includes: an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4. Each neuron of the convolution kernel in the convolution layer is locally connected to its input, and the local maximum or average feature of a certain layer is extracted by introducing a pooling layer, which effectively reduces the parameters of the network and mines local features. It enables the convolutional neural network to converge quickly and obtain excellent performance.
RNN是一种对序列数据建模的神经网络，在自然语言处理领域，如机器翻译、语音识别等应用取得显著成绩。具体表现为，网络对过去时刻的信息进行记忆，并用于当前输出的计算中，即隐藏层之间的节点不再是无连接的而是有连接的，并且隐藏层的输入不仅包括输入层还包括上一时刻隐藏层的输出。常用的RNN包括长短期记忆网络(Long Short-Term Memory，LSTM)和门控循环单元(gated recurrent unit，GRU)等结构。图5所示为一个基本的LSTM单元结构，其可以包含tanh激活函数，不同于RNN只考虑最近的状态，LSTM的细胞状态会决定哪些状态应该被留下来，哪些状态应该被遗忘，解决了传统RNN在长期记忆上存在的缺陷。RNN is a neural network that models sequence data. It has achieved remarkable results in the field of natural language processing, such as machine translation and speech recognition. The specific performance is that the network memorizes the information of the past moment and uses it in the calculation of the current output, that is, the nodes between the hidden layers are no longer connected but connected, and the input of the hidden layer includes not only the input layer but also the Includes the output of the hidden layer at the previous moment. Commonly used RNNs include structures such as Long Short-Term Memory (LSTM) and gated recurrent unit (GRU). Figure 5 shows a basic LSTM cell structure, which can contain a tanh activation function. Unlike RNN, which only considers the nearest state, the cell state of LSTM will determine which states should be kept and which states should be forgotten, solving the traditional Shortcomings of RNN in long-term memory.
为便于更好的理解本申请实施例，对本申请相关的基于深度学习的信道信息反馈方法进行说明。In order to facilitate a better understanding of the embodiments of the present application, the deep learning-based channel information feedback method related to the present application will be described.
鉴于人工智能(Artificial Intelligence，AI)技术，尤其是深度学习在计算机视觉、自然语言处理等方面取得了巨大的成功，通信领域开始尝试利用深度学习来解决传统通信方法难以解决的技术难题，例如深度学习。深度学习中常用的神经网络架构是非线性且是数据驱动的，可以对实际信道矩阵数据进行特征提取并在基站侧尽可能还原终端侧压缩反馈的信道矩阵信息，在保证还原信道信息的同时也为终端侧降低CSI反馈开销提供了可能性。基于深度学习的CSI反馈将信道信息视作待压缩图像，利用深度学习自编码器对信道信息进行压缩反馈，并在发送端对压缩后的信道图像进行重构，可以更大程度地保留信道信息，如图6所示。In view of artificial intelligence (AI) technology, especially deep learning has achieved great success in computer vision, natural language processing, etc., the field of communication has begun to try to use deep learning to solve technical problems that are difficult to solve by traditional communication methods, such as deep learning. study. The neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from the actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal side as much as possible on the base station side. It is possible to reduce the CSI feedback overhead on the terminal side. The CSI feedback based on deep learning regards the channel information as the image to be compressed, uses the deep learning self-encoder to compress the channel information, and reconstructs the compressed channel image at the sending end, which can preserve the channel information to a greater extent ,As shown in Figure 6.
一种典型的信道信息反馈***如图7所示。整个反馈***分为编码器及解码器部分，分别部署在发送端与接收端。发送端通过信道估计得到信道信息后，通过编码器的神经网络对信道信息矩阵进行压缩编码，并将压缩后的比特流通过空口反馈链路反馈给接收端，接收端通过解码器根据反馈比特流 对信道信息进行恢复，以获得完整的反馈信道信息。图7中所示的编码器采用了多层全连接层的叠加，解码器中采用了卷积层与残差结构的设计。在该编解码框架不变的情况下，编码器和解码器内部的网络模型结构可进行灵活设计。A typical channel information feedback system is shown in FIG. 7 . The entire feedback system is divided into encoder and decoder parts, which are deployed at the sending end and receiving end respectively. After the transmitting end obtains the channel information through channel estimation, the channel information matrix is compressed and encoded through the neural network of the encoder, and the compressed bit stream is fed back to the receiving end through the air interface feedback link, and the receiving end passes the decoder according to the feedback bit stream The channel information is restored to obtain complete feedback channel information. The encoder shown in Figure 7 uses the superposition of multiple fully connected layers, and the design of the convolutional layer and residual structure is used in the decoder. Under the condition that the encoding and decoding framework remains unchanged, the network model structure inside the encoder and decoder can be flexibly designed.
为便于更好的理解本申请实施例，对本申请相关的技术及存在的问题进行说明。In order to facilitate a better understanding of the embodiments of the present application, technologies and existing problems related to the present application are described.
5G NR标准中的CSI反馈为基于码本的反馈方案根据高层信令配置，周期性、非周期性或者半持续地，利用估计出的信道从码本中挑选最优的反馈矩阵和对应的反馈系数。但是，由于码本本身是预先设定的有限集合，即从估计出的信道到码本中的信道的映射过程是量化有损的。同时，固定的码本设计无法根据信道的变化而进行动态的调整，这使得反馈的信道信息精确度下降，进而降低了预编码的性能。The CSI feedback in the 5G NR standard is a codebook-based feedback scheme. According to the high-level signaling configuration, periodically, aperiodically or semi-persistently, the estimated channel is used to select the optimal feedback matrix and corresponding feedback from the codebook. coefficient. However, since the codebook itself is a pre-set finite set, that is, the mapping process from the estimated channel to the channel in the codebook is quantized and lossy. At the same time, the fixed codebook design cannot be dynamically adjusted according to channel changes, which reduces the accuracy of the feedback channel information, thereby reducing the performance of precoding.
进一步地，基于深度学习的信道信息反馈方案虽然利用深度神经网络(DNN)、卷积神经网络(CNN)等对信道估计后得到的信道信息进行直接编码压缩反馈，相比传统基于码本的信道信息反馈，显著提升了反馈精度。然而该反馈方法仍然是一对一的模式，即在编码器输入为第t时刻第n个子带的估计得到的信道向量，通过量化压缩为比特流反馈至解码端；解码器输出为对应第t时刻第n个子带的信道向量。但是在实际通信环境下，不同反馈周期的信道间具有不同程度的时域相关性，如终端低速移动场景下，信道的时域相关性较高；同时，不同子带间的信道具有不同程度的频域相关性，如在多径影响较弱的场景下，信道频域相关性较高。因此在固定的反馈比特开销下，一对一的信道压缩反馈与恢复的精度受限；另外，对于NR所采用的CSI反馈过程，采用的周期性、非周期性和半持续反馈方法，由于没有利用信道在时域和频域的相关性，因此在达到一定的信道恢复精度时，存在较多冗余的反馈比特，因此其反馈比特开销也较高。因此，如何在不同的信道场景下，有效利用信道在时域与频域的相关性，在保证信道向量压缩反馈与恢复的精度的同时有效降低CSI反馈开销，是一项亟待解决的技术问题。Furthermore, although the channel information feedback scheme based on deep learning uses deep neural network (DNN), convolutional neural network (CNN) to directly encode and compress the channel information obtained after channel estimation, compared with the traditional codebook-based channel Information feedback, significantly improving the feedback accuracy. However, this feedback method is still a one-to-one mode, that is, the input of the encoder is the estimated channel vector of the nth subband at the tth moment, which is quantized and compressed into a bit stream and fed back to the decoder; the output of the decoder is corresponding to the tth The channel vector of the nth subband at time instant. However, in the actual communication environment, channels with different feedback periods have different degrees of time-domain correlation. For example, in the scenario of low-speed terminal movement, the time-domain correlation of channels is relatively high; Frequency domain correlation, for example, in a scenario where multipath influence is weak, channel frequency domain correlation is high. Therefore, under the fixed feedback bit overhead, the accuracy of one-to-one channel compression feedback and recovery is limited; in addition, for the CSI feedback process adopted by NR, the periodic, non-periodic and semi-persistent feedback methods adopted, because there is no By using the correlation of the channel in the time domain and the frequency domain, when a certain channel restoration accuracy is achieved, there are more redundant feedback bits, so the feedback bit overhead is also high. Therefore, how to effectively use the correlation between the time domain and the frequency domain of the channel in different channel scenarios, and effectively reduce the CSI feedback overhead while ensuring the accuracy of channel vector compression feedback and recovery, is an urgent technical problem to be solved.
基于上述问题，本申请提出了一种CSI反馈方案，可以利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。Based on the above problems, this application proposes a CSI feedback scheme, which can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the CSI Feedback accuracy and reduce CSI feedback overhead.
以下通过具体实施例详述本申请的技术方案。The technical scheme of the present application is described in detail below through specific examples.
图8是根据本申请实施例的信道信息的反馈方法200的示意性流程图，如图8所示，该信道信息的反馈方法200可以包括如下内容中的至少部分内容：FIG. 8 is a schematic flowchart of a channel information feedback method 200 according to an embodiment of the present application. As shown in FIG. 8 , the channel information feedback method 200 may include at least part of the following content:
S210，收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取该N个CSI反馈周期的目标信道向量；其中，N为正整数，且N≥2。S210. The receiving end device acquires target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N≥2.
在本申请实施例中，发端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈。In the embodiment of the present application, the originating device may perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles.
在一些实施例中，该CSI相关性包括CSI时域相关性和/或CSI频域相关性。In some embodiments, the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
考虑到当用户速度较慢时(例如典型的用户移动速度小于3km/h场景)，信道变化较慢，不同时隙的CSI相关度较高，周期性地进行CSI上报存在冗余。因此，本申请实施例可以利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。Considering that when the user speed is slow (for example, the typical user moving speed is less than 3km/h), the channel changes slowly, and the CSI correlation of different time slots is high, and there is redundancy in periodic CSI reporting. Therefore, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the CSI feedback accuracy and reduce the CSI feedback accuracy. overhead.
在一些实施例中，CSI周期性反馈的流程例如可以如图9所示；其中，周期T表示CSI-RS的发送可以间隔T个时隙进行，同样的CSI上报也间隔T个时隙进行，该周期T由RRC信令配置。假设每次CSI反馈比特数为M，在第0个时隙发送了下行CSI-RS并进行CSI上报，则对于后续连续的N*T个时隙，共需要N次CSI上报，N*M个反馈比特数。In some embodiments, the process of periodic CSI feedback can be shown in Figure 9, for example; wherein, the period T indicates that the transmission of CSI-RS can be performed at intervals of T time slots, and the same CSI reporting can also be performed at intervals of T time slots, The period T is configured by RRC signaling. Assuming that the number of CSI feedback bits each time is M, the downlink CSI-RS is sent and CSI is reported in the 0th time slot, then for the subsequent consecutive N*T time slots, a total of N times of CSI reporting are required, and N*M Number of feedback bits.
在一些实施例中，收端设备通过神经网络，并根据N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，获取该N个CSI反馈周期的目标信道向量。In some embodiments, the receiving device obtains the CSI feedback periods of the N CSI feedback periods according to the CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback periods in the N CSI feedback periods through a neural network. Target channel vector.
在一些实施例中，该收端设备是终端设备，以及该发端设备是网络设备；或者，该收端设备是网络设备，以及该发端设备是终端设备。In some embodiments, the receiving device is a terminal device, and the sending device is a network device; or, the receiving device is a network device, and the sending device is a terminal device.
在又一些实施例中，该收端设备是一个终端设备，以及该发端设备是另一个终端设备。如本申请实施例应用于侧行链路(sidelink，SL)通信。In yet other embodiments, the receiving device is a terminating device and the originating device is another terminating device. For example, the embodiment of the present application is applied to sidelink (sidelink, SL) communication.
在再一些实施例中，该发端设备为网络设备，该收端设备为另一网络设备。如本申请实施例应用于回传链路(backhaul link)通信。In still some embodiments, the originating device is a network device, and the receiving device is another network device. For example, the embodiment of the present application is applied to backhaul link (backhaul link) communication.
在一些实施例中，N个CSI反馈周期中的K个CSI反馈周期进行下行的CSI-RS发送与CSI上报，N个CSI反馈周期中除该K个CSI反馈周期之外的CSI反馈周期的CSI通过神经网络进行预测得到，K为正整数，且K＜N。In some embodiments, the K CSI feedback cycles in the N CSI feedback cycles perform downlink CSI-RS transmission and CSI reporting, and the CSI of the CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles Predicted by neural network, K is a positive integer, and K<N.
在一些实现方式中，该收端设备接收发端设备发送的K条比特流，该K条比特流分别是由该N 个CSI反馈周期中的K个CSI反馈周期的信道向量经编码之后得到的；该收端设备分别对该K条比特流进行解码，得到该K个CSI反馈周期的K个目标信道向量；该收端设备通过第一收端神经网络对该K个目标信道向量进行预测，得到该N个CSI反馈周期中除该K个CSI反馈周期之外的CSI反馈周期的N-K个目标信道向量。In some implementation manners, the receiving device receives K bit streams sent by the transmitting device, and the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles; The receiving device decodes the K bit streams respectively to obtain K target channel vectors for the K CSI feedback cycles; the receiving device predicts the K target channel vectors through the first receiving neural network to obtain N-K target channel vectors of CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles.
也即，该发端设备可以分别对该N个CSI反馈周期中的K个CSI反馈周期的信道向量进行编码，得到该K条比特流。例如，对于K个CSI反馈周期中的每个CSI反馈周期，发端设备根据CSI-RS进行信道估计，得到发端设备与收端设备之间的信道信息；以及对信道信息进行特征分解，得到信道向量；再对信道向量进行编码，得到比特流。That is, the originating device may respectively encode the channel vectors of K CSI feedback periods in the N CSI feedback periods to obtain the K bit streams. For example, for each of the K CSI feedback cycles, the transmitting device performs channel estimation based on the CSI-RS to obtain channel information between the transmitting device and the receiving device; and performs eigendecomposition on the channel information to obtain the channel vector ; Then encode the channel vector to obtain the bit stream.
在一些实现方式中，该第一收端神经网络由于提取了不同CSI反馈周期的CSI时域相关性，采用序列输入，序列输出，因此，该第一收端神经网络例如可以是以LSTM、GRU为例的RNN，或者其他预测性能较优的神经网络，本申请对此并不限定。In some implementations, the first receiving-end neural network extracts the CSI time-domain correlation of different CSI feedback cycles, adopts sequence input and sequence output, therefore, the first receiving-end neural network can be based on LSTM, GRU, for example RNN is used as an example, or other neural networks with better predictive performance, which is not limited in this application.
例如，第一收端神经网络包括但不限于基于全连接层、卷积层、循环神经网络层、激活函数层等基本神经网络结构中的一种或者多种进行构造实现。For example, the first receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
在一些实现方式中，该K个CSI反馈周期为该N个CSI反馈周期中的前K个连续的CSI反馈周期。In some implementation manners, the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
在一些实现方式中，该收端设备通过第二收端神经网络分别对该K条比特流进行解码，得到该K个目标信道向量。In some implementation manners, the receiving end device decodes the K bit streams respectively through the second receiving end neural network to obtain the K target channel vectors.
在一些实现方式中，该第二收端神经网络可以是用于图像处理的神经网络，例如可以是CNN或DNN等，或者其他图像处理性能较优的神经网络，本申请对此并不限定。In some implementations, the second receiving neural network may be a neural network used for image processing, such as CNN or DNN, or other neural networks with better image processing performance, which is not limited in this application.
例如，第二收端神经网络包括但不限于基于全连接层、卷积层、循环神经网络层、激活函数层等基本神经网络结构中的一种或者多种进行构造实现。For example, the second receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
在一些实现方式中，该K条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；具体的，该收端设备通过该第二收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第二收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤K，1≤j≤S，L＜i；以及该收端设备根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该K个目标信道向量。In some implementation manners, the bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1; specifically, the receiving end device uses the second receiving end neural network pair from the i-Lth The bit stream on the jth subband of the first CSI feedback period is decoded to the bitstream on the jth subband of the ith CSI feedback period, and the ith CSI feedback period from The bit stream from the first sub-band to the S-th sub-band is decoded to obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, and L are all positive integers, and 1≤i≤K , 1≤j≤S, L<i; and the receiving device acquires the K target channel vectors according to the target channel vectors on the j-th subband of the i-th CSI feedback period.
也即，对于该K个CSI反馈周期中的每个CSI反馈周期，发端设备需要反馈的比特流中包含了S个子带的信息。此种情况下，第二收端神经网络提取了从第i-L个CSI反馈周期的第j个子带至第i个CSI反馈周期的第j个子带的CSI时域相关性，以及第二收端神经网络提取了第i个CSI反馈周期内从第一个子带至第S个子带的CSI频域相关性，对第i个CSI反馈周期的第j个子带上的CSI进行联合恢复(即确定第i个CSI反馈周期的第j个子带上的目标信道向量)。That is, for each CSI feedback period in the K CSI feedback periods, the bit stream that the transmitting device needs to feed back includes information of S subbands. In this case, the second receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the second receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
在此种情况下，该第二收端神经网络由于提取了L个CSI反馈周期的CSI时域相关性，以及S个子带的CSI频域相关性，采用序列输入，序列输出，因此，该第二收端神经网络例如可以是以LSTM、GRU为例的RNN，或者其他预测性能较优的神经网络，本申请对此并不限定。具体可以如图10所示。从第i-L个CSI反馈周期的第j个子带上的比特流(b i-L,j)至第i个CSI反馈周期的第j个子带上的比特流(b i,j)分别输入第二收端神经网络中的时域LSTM单元，以及第i个CSI反馈周期内从第一个子带的比特流(b i,1)至第S个子带的比特流(b i,S)分别输入第二收端神经网络中的频域LSTM单元，并且时域LSTM单元与频域LSTM单元的输出通过一个全连接层，最终得到第i个CSI反馈周期的第j个子带上的目标信道向量
Figure PCTCN2021093689-appb-000001
In this case, since the second receiving-end neural network extracts the CSI time domain correlation of L CSI feedback cycles and the CSI frequency domain correlation of S subbands, it adopts sequence input and sequence output. Therefore, the first The neural network at the receiving end can be, for example, RNN such as LSTM and GRU, or other neural networks with better predictive performance, which is not limited in this application. Specifically, it may be shown in FIG. 10 . From the bit stream (b iL,j ) on the j-th subband of the iL-th CSI feedback cycle to the bit stream (b i ,j ) on the j-th sub-band of the i-th CSI feedback cycle are respectively input to the second receiving end The time-domain LSTM unit in the neural network, and the bit stream from the first subband (b i,1 ) to the bit stream (b i,S ) of the S subband in the i-th CSI feedback period are respectively input into the second The frequency-domain LSTM unit in the receiving-end neural network, and the output of the time-domain LSTM unit and the frequency-domain LSTM unit pass through a fully connected layer, and finally obtain the target channel vector on the j-th subband of the i-th CSI feedback cycle
Figure PCTCN2021093689-appb-000001
需要注意的是，如图10所示的L个时域LSTM单元的串行结构不代表实际的结构中包含L个不同的时域LSTM单元，而是对同一个时域LSTM单元的L次序列输入的展开表示，实际上***中只包含一个时域LSTM单元。同理，S个频域LSTM单元的串行结构不代表实际的结构中包含S个不同的频域LSTM单元，而是对同一个频域LSTM单元的S次序列输入的展开表示，实际上***中只包含一个频域LSTM单元。It should be noted that the serial structure of L time-domain LSTM units shown in Figure 10 does not mean that the actual structure contains L different time-domain LSTM units, but the L-order sequence of the same time-domain LSTM unit The expansion of the input shows that in fact only one time-domain LSTM unit is included in the system. Similarly, the serial structure of S frequency-domain LSTM units does not mean that the actual structure contains S different frequency-domain LSTM units, but an expanded representation of the S-order sequence input of the same frequency-domain LSTM unit. In fact, the system Contains only one frequency-domain LSTM unit in .
在一些实现方式中，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数。例如，S＝4，相邻CSI反馈周期的主反馈子带与辅反馈子带交替配置，如图11所示。In some implementations, the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the at least one auxiliary feedback subband The number of bits occupied by the information of the main feedback subband in one main feedback subband. For example, if S=4, primary feedback subbands and auxiliary feedback subbands of adjacent CSI feedback periods are alternately configured, as shown in FIG. 11 .
需要说明的是，本实施例不限制于主反馈子带与辅反馈子带在每个CSI反馈周期的配置方法，也不限制主反馈子带与辅反馈子带在不同CSI反馈周期的配置方法，本实施例可以支持一定周期性原则的其他灵活的主反馈子带与辅反馈子带的配置方法，并通过RRC或DCI信令进行配置，以降低CSI 周期性反馈的开销。It should be noted that this embodiment is not limited to the configuration method of the main feedback subband and the auxiliary feedback subband in each CSI feedback period, nor is it limited to the configuration method of the main feedback subband and the auxiliary feedback subband in different CSI feedback periods , this embodiment can support other flexible configuration methods of primary feedback subbands and secondary feedback subbands with a certain periodicity principle, and configure them through RRC or DCI signaling, so as to reduce the overhead of CSI periodic feedback.
在一些实现方式中，该S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。In some implementation manners, the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
例如，网络设备通过RRC信令配置该S个子带中的主反馈子带和辅反馈子带。For example, the network device configures the primary feedback subband and the secondary feedback subband among the S subbands through RRC signaling.
又例如，网络设备通过DCI信令配置该S个子带中的主反馈子带和辅反馈子带。For another example, the network device configures the primary feedback subband and the secondary feedback subband among the S subbands through DCI signaling.
再例如，网络设备通过RRC信令和DCI信令联合配置该S个子带中的主反馈子带和辅反馈子带。For another example, the network device jointly configures the primary feedback subband and the secondary feedback subband in the S subbands through RRC signaling and DCI signaling.
在一些实现方式中，K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。In some implementation manners, the values of K and N are determined from the group G {K, N}, G is a positive integer, and G≥2.
例如，G＝3，即配置有3组{K，N}，分别记为{K 1，N 1}、{K 2，N 2}和{K 3，N 3}，此种情况下，K和N的取值可以分别是K 1和N 1，或者，K和N的取值可以分别是K 2和N 2，或者，K和N的取值可以分别是K 3和N 3。 For example, G=3, that is, there are 3 sets of {K, N} configured, which are recorded as {K 1 , N 1 }, {K 2 , N 2 } and {K 3 , N 3 }, in this case, K The values of K and N may be K 1 and N 1 respectively, or the values of K and N may be K 2 and N 2 respectively, or the values of K and N may be K 3 and N 3 respectively.
在一些实现方式中，K和N的取值是根据信道场景从该G组{K，N}中确定的。In some implementation manners, the values of K and N are determined from the G group {K, N} according to channel scenarios.
例如，G＝3，即配置有3组{K，N}，分别记为{K 1，N 1}、{K 2，N 2}和{K 3，N 3}，此种情况下，对于信道场景A(如用户移动速度为v 1的场景)，K和N的取值可以分别是K 1和N 1；对于信道场景B(如用户移动速度为v 2的场景)，K和N的取值可以分别是K 2和N 2，对于信道场景C(如用户移动速度为v 3的场景)，K和N的取值可以分别是K 3和N 3。 For example, G=3, that is, there are 3 sets of {K, N} configured, which are respectively recorded as {K 1 , N 1 }, {K 2 , N 2 } and {K 3 , N 3 }. In this case, for Channel scenario A (such as the scenario where the user’s moving speed is v 1 ), the values of K and N can be K 1 and N 1 respectively; for channel scenario B (such as the scenario where the user’s moving speed is v 2 ), the values of K and N The values of K and N can be K 2 and N 2 respectively. For channel scenario C (for example, the scenario where the user's moving speed is v 3 ), the values of K and N can be K 3 and N 3 respectively.
在一些实现方式中，该G组{K，N}是网络设备通过RRC信令和/或DCI信令配置的。例如，网络设备通过RRC信令和DCI信令联合配置该G组{K，N}。In some implementation manners, the G group {K, N} is configured by the network device through RRC signaling and/or DCI signaling. For example, the network device jointly configures the G group {K, N} through RRC signaling and DCI signaling.
在一些实现方式中，该G组{K，N}是网络设备通过RRC信令和/或DCI信令中的
Figure PCTCN2021093689-appb-000002
个比特配置的，其中，
Figure PCTCN2021093689-appb-000003
表示向上取整。例如，如图12所示，网络设备通过RRC信令或DCI信令为终端设备配置{K，N}。 In some implementations, the G group {K, N} is set by the network device through RRC signaling and/or DCI signaling
Figure PCTCN2021093689-appb-000002
bit configuration, where,
Figure PCTCN2021093689-appb-000003
Indicates rounding up. For example, as shown in FIG. 12 , the network device configures {K, N} for the terminal device through RRC signaling or DCI signaling.
例如，网络设备需要配置2组{K，N}，此种情况下，网络设备通过RRC信令或DCI信令中的1比特配置该2组{K，N}。For example, the network device needs to configure 2 groups {K, N}. In this case, the network device configures the 2 groups {K, N} through RRC signaling or 1 bit in DCI signaling.
又例如，网络设备需要配置3组{K，N}，此种情况下，网络设备通过RRC信令或DCI信令中的2比特配置该3组{K，N}。For another example, the network device needs to configure 3 groups {K, N}. In this case, the network device configures the 3 groups {K, N} through 2 bits in RRC signaling or DCI signaling.
在一些实现方式中，具体的，假设N个CSI反馈周期中的前K个CSI反馈周期进行下行的CSI-RS发送与CSI上报，后面N-K个CSI反馈周期的CSI通过神经网络进行预测得到，其结构可以如图13所示。其中，编码器的输入分别为前K个CSI反馈周期的信道向量，输出为比特流并通过CSI上报反馈至网络侧；网络侧的解码器的输入为前K个CSI反馈周期的反馈比特流，输出为估计信道向量(即目标信道向量)。进一步的，将K个CSI反馈周期的估计信道向量联合作为预测器的输入，输出为后面N-K个CSI反馈周期的预测信道向量(即目标信道向量)。图13中的预测器由于提取了不同周期的CSI的时域相关性，采用序列输入，序列输出，可以采用以LSTM、GRU为例的RNN，其对应上述第一收端神经网络；解码器可以采用DNN、CNN等神经网络，其对应上述第二收端神经网络；编码器通常采用DNN、CNN等神经网络。本实施例并不限制每个神经网络内部的神经网络具体实现方案，以便于依据不同的通信场景设计不同的功能。In some implementations, specifically, it is assumed that the first K CSI feedback cycles in the N CSI feedback cycles perform downlink CSI-RS transmission and CSI reporting, and the CSI of the next N-K CSI feedback cycles is obtained by prediction through a neural network. The structure can be shown in Figure 13. Among them, the input of the encoder is the channel vector of the previous K CSI feedback cycles, and the output is a bit stream and reported to the network side through CSI; the input of the decoder on the network side is the feedback bit stream of the previous K CSI feedback cycles, The output is the estimated channel vector (ie, the target channel vector). Further, the estimated channel vectors of K CSI feedback periods are jointly used as the input of the predictor, and the output is the predicted channel vector (ie, the target channel vector) of the following N-K CSI feedback periods. The predictor in Figure 13 extracts the time-domain correlation of CSI of different periods, adopts sequence input and sequence output, and can use RNN such as LSTM and GRU, which correspond to the above-mentioned first receiving end neural network; the decoder can be Neural networks such as DNN and CNN are used, which correspond to the above-mentioned second receiving neural network; the encoder usually adopts neural networks such as DNN and CNN. This embodiment does not limit the specific implementation scheme of the neural network inside each neural network, so as to design different functions according to different communication scenarios.
在一些实现方式中，上述图13中的编码器、解码器和校准器的训练方法如下：In some implementations, the encoder, decoder and calibrator in Figure 13 above are trained as follows:
编码器与解码器的联合训练：该步骤中输入的训练数据与标签均为信道向量w，损失函数包括但不限于估计信道向量
Figure PCTCN2021093689-appb-000004
(即目标信道向量)与信道向量w的均值平方差(Mean Squared Error，MSE)或余弦相似度(GCS)等指标，
Figure PCTCN2021093689-appb-000005
其中，要求编码器的输出与解码器的输入均为固定长度为M的比特流，其中M为空口上用于信道向量压缩反馈的比特开销。 Joint training of encoder and decoder: the input training data and labels in this step are channel vector w, and the loss function includes but not limited to estimated channel vector
Figure PCTCN2021093689-appb-000004
(ie the target channel vector) and the mean squared error (Mean Squared Error, MSE) or cosine similarity (GCS) of the channel vector w, etc.,
Figure PCTCN2021093689-appb-000005
Among them, the output of the encoder and the input of the decoder are both required to be a bit stream with a fixed length of M, where M is the bit overhead used for channel vector compression feedback on the air interface.
预测器训练：通过优化损失函数，固定编码器与解码器的网络模型和参数，对预测器进行训练。设定预测神经网络的输入为前K个CSI反馈周期个已恢复的目标信道向量的序列，输出为后N-K个CSI反馈周期的预测信道向量(即目标信道向量)
Figure PCTCN2021093689-appb-000006
标签为后N-K个CSI反馈周期的信道向量w＝[w K+1…w N]，通过优化
Figure PCTCN2021093689-appb-000007
与w的损失函数，完成对预测器的训练。 Predictor training: Train the predictor by optimizing the loss function and fixing the network model and parameters of the encoder and decoder. The input of the prediction neural network is set as the sequence of recovered target channel vectors in the first K CSI feedback cycles, and the output is the predicted channel vector (ie, the target channel vector) of the next NK CSI feedback cycles
Figure PCTCN2021093689-appb-000006
The label is the channel vector w=[w K+1 ... w N ] of the last NK CSI feedback cycles, and by optimizing
Figure PCTCN2021093689-appb-000007
With the loss function of w, the training of the predictor is completed.
上述训练方法要求在训练预测器时，编码器与解码器的网络参数已经固定，是为了保证训练过程中的解码器的输出与实际部署时解码器的推理输出相匹配。在本实施例中，编码器、解码器与预测器，可以采用离线与在线部署训练。The above training method requires that the network parameters of the encoder and decoder have been fixed when training the predictor, in order to ensure that the output of the decoder during training matches the inference output of the decoder during actual deployment. In this embodiment, the encoder, decoder, and predictor can be deployed and trained offline or online.
在本实施例中，在连续的N个CSI反馈周期内，只有前K个CSI反馈周期需要进行CSI-RS的发送与CSI上报，后面N-K个CSI反馈周期的CSI可以利用CSI时域相关性，并设计合理的神经网络获得，因此反馈开销降低为目前NR***中的周期性反馈方案的K/N，降低了CSI反馈开销。进一步 地，根据不同的信道场景，应该采用不同的{K，N}的组合，取得反馈比特开销和预测的CSI准确度的折衷。In this embodiment, in the consecutive N CSI feedback cycles, only the first K CSI feedback cycles need to send CSI-RS and CSI reporting, and the CSI of the next N-K CSI feedback cycles can use CSI time domain correlation, And a reasonable neural network is designed, so the feedback overhead is reduced to K/N of the periodic feedback scheme in the current NR system, and the CSI feedback overhead is reduced. Further, according to different channel scenarios, different combinations of {K, N} should be used to achieve a trade-off between feedback bit overhead and predicted CSI accuracy.
在一些实施例中，对N个CSI反馈周期进行分级，得到P个主CSI反馈周期和Q个辅CSI反馈周期。通过提取主CSI反馈周期和辅CSI反馈周期之间的时域相关性分别设计不同的神经网络恢复主CSI反馈周期和辅CSI反馈周期的CSI。In some embodiments, N CSI feedback cycles are classified to obtain P primary CSI feedback cycles and Q secondary CSI feedback cycles. By extracting the time-domain correlation between the main CSI feedback period and the auxiliary CSI feedback period, different neural networks are designed to restore the CSI of the main CSI feedback period and the auxiliary CSI feedback period.
在一些实现方式中，该收端设备接收发端设备发送的P条比特流和Q条比特流；其中，该P条比特流分别是由该N个CSI反馈周期中的P个主CSI反馈周期的信道向量经编码之后得到的，该Q条比特流分别是由该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量经编码之后得到的，或者，该Q条比特流分别是由该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量与对应的主CSI反馈周期的信道向量的差值经编码之后得到的，P和Q均为正整数，且P+Q＝N；该收端设备分别对该P条比特流进行解码，得到该P个主CSI反馈周期的P个目标信道向量；以及该收端设备通过第三收端神经网络分别对该Q条比特流中的第一比特流和该P条比特流中的第二比特流进行解码，得到该Q个辅CSI反馈周期的Q个目标信道向量；其中，该第一比特流对应的辅CSI反馈周期为该第二比特流对应的主CSI反馈周期伴随的辅CSI反馈周期。In some implementations, the receiving device receives P bit streams and Q bit streams sent by the source device; wherein, the P bit streams are respectively generated by the P main CSI feedback cycles in the N CSI feedback cycles The channel vectors are obtained after encoding, the Q bit streams are respectively obtained by encoding the channel vectors of the Q secondary CSI feedback cycles in the N CSI feedback cycles, or the Q bit streams are respectively obtained by the The difference between the channel vectors of the Q auxiliary CSI feedback periods in the N CSI feedback periods and the channel vector of the corresponding main CSI feedback period is obtained after encoding, P and Q are both positive integers, and P+Q=N; The receiving end device decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback cycles; and the receiving end device respectively uses the third receiving end neural network for the Q bit streams The first bit stream and the second bit stream in the P bit streams are decoded to obtain the Q target channel vectors of the Q secondary CSI feedback cycles; wherein, the secondary CSI feedback cycle corresponding to the first bit stream is the first The secondary CSI feedback cycle accompanying the primary CSI feedback cycle corresponding to the two bit streams.
也即，发端设备可以分别对P个主CSI反馈周期的信道向量进行编码，得到P条比特流。例如，对于P个主CSI反馈周期中的每个主CSI反馈周期，发端设备根据CSI-RS进行信道估计，得到发端设备与收端设备之间的信道信息；以及对信道信息进行特征分解，得到信道向量；再对信道向量进行编码，得到比特流。That is, the source device can encode the channel vectors of the P main CSI feedback periods respectively to obtain P bit streams. For example, for each primary CSI feedback cycle in the P primary CSI feedback cycles, the transmitting device performs channel estimation according to the CSI-RS to obtain the channel information between the transmitting device and the receiving device; and performs eigendecomposition on the channel information to obtain channel vector; and then encode the channel vector to obtain a bit stream.
发端设备可以分别对Q个辅CSI反馈周期的信道向量进行编码，得到Q条比特流。或者，发端设备可以分别对N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量与对应的主CSI反馈周期的信道向量的差值进行编码，得到Q条比特流。The originating device may respectively encode the channel vectors of the Q secondary CSI feedback periods to obtain Q bit streams. Alternatively, the originating device may separately encode the difference between the channel vectors of Q secondary CSI feedback periods in the N CSI feedback periods and the channel vector of the corresponding primary CSI feedback period to obtain Q bit streams.
在一些实现方式中，该第三收端神经网络由于提取了不同CSI反馈周期的CSI时域相关性，采用序列输入，序列输出，因此，该第三收端神经网络例如可以是以LSTM、GRU为例的RNN，或者其他预测性能较优的神经网络，本申请对此并不限定。In some implementations, the third receiving-end neural network extracts the CSI time-domain correlation of different CSI feedback cycles, adopts sequence input and sequence output, therefore, the third receiving-end neural network can be based on LSTM, GRU, for example RNN is used as an example, or other neural networks with better predictive performance, which is not limited in this application.
例如，该第三收端神经网络包括但不限于基于全连接层、卷积层、循环神经网络层、激活函数层等基本神经网络结构中的一种或者多种进行构造实现。For example, the third receiving-end neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as a fully connected layer, a convolutional layer, a recurrent neural network layer, and an activation function layer.
在一些实现方式中，该Q条比特流中的一条比特流占用的比特数小于该P条比特流中的一条比特流占用的比特数。也即，辅CSI反馈周期反馈的比特流所占用的比特数小于主CSI反馈周期反馈的比特流所占用的比特数。In some implementation manners, the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams. That is, the number of bits occupied by the bit stream fed back in the secondary CSI feedback cycle is smaller than the number of bits occupied by the bit stream fed back in the primary CSI feedback cycle.
在一些实现方式中，该Q条比特流中的不同的比特流占用的比特数不同，或者，该Q条比特流中的不同的比特流占用的比特数相同。In some implementation manners, different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
在一些实现方式中，该N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。In some implementations, one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
例如，如图14所示，在连续的N个CSI反馈周期内，分级为一个主CSI反馈周期伴随N-1个辅CSI反馈周期的配置，其中一个主CSI反馈周期反馈M个比特，N-1个辅CSI反馈周期反馈各自不同的{m 1,m 2,…,m N-1}个比特。此种情况下，N个CSI反馈周期中，发端设备在主CSI反馈周期向收端设备反馈比特流b 0，以及发端设备在N-1个辅CSI反馈周期分别反馈b 1,b 2,…,b N-1。如图15所示，将比特流b 0和b 1输入第三收端神经网络中的LSTM单元，得到目标信道向量
Figure PCTCN2021093689-appb-000008
将比特流b 0和b 2输入第三收端神经网络中的LSTM单元，得到目标信道向量
Figure PCTCN2021093689-appb-000009
将比特流b 0和b N-1输入第三收端神经网络中的LSTM单元，得到目标信道向量
Figure PCTCN2021093689-appb-000010
For example, as shown in Figure 14, within N consecutive CSI feedback cycles, it is classified into a configuration in which one primary CSI feedback cycle is accompanied by N-1 secondary CSI feedback cycles, wherein one primary CSI feedback cycle feeds back M bits, and N- Different {m 1 , m 2 , . . . , m N-1 } bits are fed back in one secondary CSI feedback cycle. In this case, in N CSI feedback cycles, the source device feeds back the bit stream b 0 to the sink device in the primary CSI feedback cycle, and the source device feeds back b 1 , b 2 ,… in N-1 secondary CSI feedback cycles respectively ,b N-1 . As shown in Figure 15, input the bit stream b 0 and b 1 into the LSTM unit in the third receiving neural network to obtain the target channel vector
Figure PCTCN2021093689-appb-000008
Input the bit stream b 0 and b 2 into the LSTM unit in the third receiving neural network to get the target channel vector
Figure PCTCN2021093689-appb-000009
Input the bit stream b 0 and b N-1 into the LSTM unit in the third receiving end neural network to obtain the target channel vector
Figure PCTCN2021093689-appb-000010
需要注意的是，如图15所示的N-1个LSTM单元的串行结构不代表实际的结构中包含N-1个不同的LSTM单元，而是对同一个LSTM单元的N-1次序列输入的展开表示，实际上***中只包含一个LSTM单元。It should be noted that the serial structure of N-1 LSTM units shown in Figure 15 does not mean that the actual structure contains N-1 different LSTM units, but the N-1 sequence of the same LSTM unit The expanded representation of the input, actually contains only one LSTM unit in the system.
又例如，在连续的N个CSI反馈周期内，也可分级为多个主CSI反馈周期伴随多个辅CSI反馈周期的配置，其中多个主CSI反馈周期可以支持相邻或者间隔配置，如图16所示，为在N＝5的配置下，2个主CSI反馈周期伴随3个辅CSI反馈周期，并且2个主CSI反馈周期间隔2个辅CSI反馈周期配置的情况。For another example, in consecutive N CSI feedback cycles, it can also be classified into multiple primary CSI feedback cycles accompanied by multiple secondary CSI feedback cycle configurations, where the multiple primary CSI feedback cycles can support adjacent or spaced configurations, as shown in the figure As shown in 16, under the configuration of N=5, 2 primary CSI feedback cycles are accompanied by 3 secondary CSI feedback cycles, and 2 primary CSI feedback cycles are configured at intervals of 2 secondary CSI feedback cycles.
在一些实现方式中，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。In some implementations, the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles associated with different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
在一些实现方式中，该N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。例如，网络设备通过RRC信令和DCI信令联合配置该N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期。In some implementation manners, the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling. For example, the network device jointly configures the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles through RRC signaling and DCI signaling.
在一些实现方式中，该收端设备通过第四收端神经网络分别对该P条比特流进行解码，得到该P个主CSI反馈周期的P个目标信道向量。In some implementation manners, the receiving-end device decodes the P bit streams respectively through the fourth receiving-end neural network to obtain P target channel vectors of the P main CSI feedback periods.
在一些实现方式中，该第四收端神经网络可以是用于图像处理的神经网络，例如可以是CNN或DNN等，或者其他图像处理性能较优的神经网络，本申请对此并不限定。In some implementations, the fourth receiving neural network may be a neural network used for image processing, such as CNN or DNN, or other neural networks with better image processing performance, which is not limited in this application.
例如，第四收端神经网络包括但不限于基于全连接层、卷积层、循环神经网络层、激活函数层等基本神经网络结构中的一种或者多种进行构造实现。For example, the fourth receiving neural network includes but is not limited to constructing and implementing based on one or more of basic neural network structures such as fully connected layers, convolutional layers, recurrent neural network layers, and activation function layers.
在一些实现方式中，该P条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；具体的，该收端设备通过该第四收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第四收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤P，1≤j≤S，L＜i；以及该收端设备根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该P个主CSI反馈周期的P个目标信道向量。In some implementation manners, the bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1; specifically, the receiving end device uses the fourth receiving end neural network pair from the i-Lth The bit stream on the jth subband of the first CSI feedback period is decoded to the bitstream on the jth subband of the ith CSI feedback period, and the fourth receiver neural network is used to decode the ith CSI feedback period from The bit stream from the first sub-band to the S-th sub-band is decoded to obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, and L are all positive integers, and 1≤i≤P , 1≤j≤S, L<i; and the receiving device obtains P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the jth subband of the ith CSI feedback period.
也即，对于该P个主CSI反馈周期中的每个主CSI反馈周期，发端设备需要反馈的比特流中包含了S个子带的信息。此种情况下，第四收端神经网络提取了从第i-L个CSI反馈周期的第j个子带至第i个CSI反馈周期的第j个子带的CSI时域相关性，以及第四收端神经网络提取了第i个CSI反馈周期内从第一个子带至第S个子带的CSI频域相关性，对第i个CSI反馈周期的第j个子带上的CSI进行联合恢复(即确定第i个CSI反馈周期的第j个子带上的目标信道向量)。That is, for each primary CSI feedback cycle in the P primary CSI feedback cycles, the bit stream that the transmitting device needs to feed back includes information of S subbands. In this case, the fourth receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the fourth receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
在此种情况下，该第四收端神经网络由于提取了L个主CSI反馈周期的CSI时域相关性，以及S个子带的CSI频域相关性，采用序列输入，序列输出，因此，该第四收端神经网络例如可以是以LSTM、GRU为例的RNN，或者其他预测性能较优的神经网络，本申请对此并不限定。具体的，从第i-L个CSI反馈周期的第j个子带上的比特流(b i-L,j)至第i个CSI反馈周期的第j个子带上的比特流(b i,j)分别输入第四收端神经网络中的时域LSTM单元，以及第i个主CSI反馈周期内从第一个子带的比特流(b i,1)至第S个子带的比特流(b i,S)分别输入第四收端神经网络中的频域LSTM单元，并且时域LSTM单元与频域LSTM单元的输出通过一个全连接层，最终得到第i个CSI反馈周期的第j个子带上的目标信道向量
Figure PCTCN2021093689-appb-000011
具体可以参考上述实施例中关于图10的描述，为了简洁，在此不再赘述。 In this case, since the fourth receiver neural network extracts the CSI time-domain correlations of L main CSI feedback cycles and the CSI frequency-domain correlations of S subbands, it adopts sequence input and sequence output. Therefore, the The fourth receiving neural network may be, for example, an RNN such as LSTM or GRU, or other neural networks with better predictive performance, which is not limited in this application. Specifically, from the bit stream (b iL,j ) on the jth subband of the iL-th CSI feedback period to the bitstream (bi,j ) on the jth subband of the i-th CSI feedback period are respectively input into the The time-domain LSTM unit in the four-receiver neural network, and the bit stream from the first sub-band (bi ,1 ) to the bit stream (bi ,S ) of the S-th sub-band in the i-th main CSI feedback cycle Input the frequency-domain LSTM unit in the fourth receiver neural network respectively, and the output of the time-domain LSTM unit and the frequency-domain LSTM unit pass through a fully connected layer, and finally obtain the target channel on the j-th sub-band of the i-th CSI feedback cycle vector
Figure PCTCN2021093689-appb-000011
For details, reference may be made to the description about FIG. 10 in the foregoing embodiments, and for the sake of brevity, details are not repeated here.
在一些实现方式中，具体的，在第1个CSI反馈周期，发端设备CSI反馈的比特数为M，当信道变化不快时，相邻CSI反馈周期内的信道存在较强的时域相关性，因此在第2个CSI反馈周期可以反馈较少的比特数m，其中，m<M，利用第三收端神经网络提取与第1个CSI反馈周期的CSI时域相关性并恢复第2个CSI反馈周期的CSI。以此类推，本实施例将CSI反馈时利用完整M个比特进行上报的CSI反馈周期称为主CSI反馈周期，将CSI反馈时利用较少的m个比特进行上报的CSI反馈周期称为辅CSI反馈周期，并通过提取主CSI反馈周期和辅CSI反馈周期间的时域相关性分别设计不同的神经网络恢复主CSI反馈周期和辅CSI反馈周期的CSI。以第1个CSI反馈周期为主CSI反馈周期，第2个CSI反馈周期为辅CSI反馈周期为例，其具体架构可以如图17所示。主CSI反馈周期解码器(对应上述第四收端神经网络)的输入为b 1，辅CSI反馈周期解码器(对应上述第三收端神经网络)的输入为[b 1,b 2]，辅CSI反馈周期解码器也可采用与主CSI反馈周期解码器相似的DNN，CNN等结构。实际上，对于辅周期编码器，其输入不限制为信道向量w 2，还可以是信道向量w 2与w 1的差，或其他表征信道之间差异的特征。 In some implementations, specifically, in the first CSI feedback cycle, the number of bits fed back by the CSI of the originating device is M, and when the channel changes slowly, there is a strong time-domain correlation between channels in adjacent CSI feedback cycles, Therefore, a smaller number of bits m can be fed back in the second CSI feedback cycle, where m<M, the third receiver neural network is used to extract the time-domain correlation of CSI with the first CSI feedback cycle and restore the second CSI CSI for the feedback cycle. By analogy, in this embodiment, the CSI feedback cycle that utilizes complete M bits for reporting during CSI feedback is called the primary CSI feedback cycle, and the CSI feedback cycle that uses fewer m bits for reporting during CSI feedback is called secondary CSI Feedback period, and design different neural networks to restore the CSI of the main CSI feedback period and the auxiliary CSI feedback period by extracting the time domain correlation between the main CSI feedback period and the auxiliary CSI feedback period. Taking the first CSI feedback cycle as the primary CSI feedback cycle and the second CSI feedback cycle as the secondary CSI feedback cycle as an example, the specific architecture may be shown in FIG. 17 . The input of the main CSI feedback cycle decoder (corresponding to the fourth receiving end neural network) is b 1 , the input of the auxiliary CSI feedback cycle decoder (corresponding to the third receiving end neural network above) is [b 1 , b 2 ], and the auxiliary CSI feedback cycle decoder (corresponding to the third receiving end neural network) is [b 1 , b 2 ]. The CSI feedback cycle decoder may also adopt a DNN, CNN, etc. structure similar to that of the main CSI feedback cycle decoder. In fact, for the sub-periodic encoder, its input is not limited to the channel vector w 2 , but can also be the difference between the channel vector w 2 and w 1 , or other features representing the difference between channels.
需要说明的是，本实施例中关于编码器和解码器的训练可以参考上述实施例中的关于描述，为了简洁，在此不再赘述。It should be noted that, for the training of the encoder and the decoder in this embodiment, reference may be made to the descriptions in the foregoing embodiments, and for the sake of brevity, details are not repeated here.
在一些实施例中，基于CSI时频域联合相关性的周期性反馈。In some embodiments, periodic feedback based on CSI time-frequency domain joint correlation.
在一些实现方式中，该收端设备接收发端设备发送的N条比特流；其中，该N条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；该收端设备通过第五收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第五收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤N，1≤j≤S，L＜i；以及该收端设备根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该N个CSI反馈周期的目标信道向量。In some implementations, the receiving end device receives N bit streams sent by the sending end device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1; the receiving end The device decodes the bit stream from the jth subband of the i-Lth CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and through the fifth receiving terminal The terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1≤i≤N, 1≤j≤S, L<i; and the receiving device obtains the N according to the target channel vector on the jth subband of the ith CSI feedback period The target channel vector of CSI feedback periods.
也即，对于该N个CSI反馈周期中的每个CSI反馈周期，发端设备需要反馈的比特流中包含了S个子带的信息。此种情况下，第五收端神经网络提取了从第i-L个CSI反馈周期的第j个子带至第i个CSI反馈周期的第j个子带的CSI时域相关性，以及第五收端神经网络提取了第i个CSI反馈周期内从第一个子带至第S个子带的CSI频域相关性，对第i个CSI反馈周期的第j个子带上的CSI进行联合恢复(即确定第i个CSI反馈周期的第j个子带上的目标信道向量)。That is, for each CSI feedback period in the N CSI feedback periods, the bit stream that the transmitting device needs to feed back includes information of S subbands. In this case, the fifth receiver neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback cycle to the j-th sub-band of the i-th CSI feedback cycle, and the fifth receiver neural network The network extracts the CSI frequency domain correlation from the first subband to the S subband in the i-th CSI feedback cycle, and jointly recovers the CSI on the j-th sub-band in the i-th CSI feedback cycle (that is, determines the The target channel vector on the jth subband of the i CSI feedback period).
在此种情况下，该第五收端神经网络由于提取了L个CSI反馈周期的CSI时域相关性，以及S个子带的CSI频域相关性，采用序列输入，序列输出，因此，该第五收端神经网络例如可以是以LSTM、GRU为例的RNN，或者其他预测性能较优的神经网络，本申请对此并不限定。具体的，从第i-L个CSI反馈周期的第j个子带上的比特流(b i-L,j)至第i个CSI反馈周期的第j个子带上的比特流(b i,j)分别输入第五收端神经网络中的时域LSTM单元，以及第i个CSI反馈周期内从第一个子带的比特流(b i,1)至第S个子带的比特流(b i,S)分别输入第五收端神经网络中的频域LSTM单元，并且时域LSTM单元与频域LSTM单元的输出通过一个全连接层，最终得到第i个CSI反馈周期的第j个子带上的目标信道向量
Figure PCTCN2021093689-appb-000012
具体可以参考上述实施例中关于图10的描述，为了简洁，在此不再赘述。 In this case, since the fifth receiving-end neural network extracts the CSI time domain correlation of L CSI feedback cycles and the CSI frequency domain correlation of S subbands, it adopts sequence input and sequence output. Therefore, the first The five-receiver neural network can be, for example, RNN such as LSTM and GRU, or other neural networks with better predictive performance, which is not limited in this application. Specifically, from the bit stream (b iL,j ) on the jth subband of the iL-th CSI feedback period to the bitstream (bi,j ) on the jth subband of the i-th CSI feedback period are respectively input into the The time-domain LSTM unit in the five-receiving neural network, and the bit stream from the first sub-band (bi ,1 ) to the bit stream (bi ,S ) of the S-th sub-band in the i-th CSI feedback cycle are respectively Input the frequency-domain LSTM unit in the fifth receiving-end neural network, and the output of the time-domain LSTM unit and the frequency-domain LSTM unit pass through a fully connected layer, and finally obtain the target channel vector on the j-th subband of the i-th CSI feedback cycle
Figure PCTCN2021093689-appb-000012
For details, reference may be made to the description about FIG. 10 in the foregoing embodiments, and for the sake of brevity, details are not repeated here.
在一些实现方式中，第i个反馈周期的第j个子带的CSI可以通过第i个反馈周期内相邻的第j-1个子带和第j+1个子带的CSI，以及第i-1个反馈周期的第j个子带的CSI，通过提取时域和频域的联合相关性，采用神经网络得到。In some implementations, the CSI of the j-th subband in the i-th feedback cycle can be passed through the CSI of the j-1th sub-band and the j+1-th sub-band in the i-th feedback cycle, and the i-1th sub-band The CSI of the jth sub-band of the first feedback cycle is obtained by extracting the joint correlation of the time domain and the frequency domain, and using a neural network.
因此，在本申请实施例中，发端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，以及收端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取N个CSI反馈周期的目标信道向量。也即，本申请实施例可以利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。Therefore, in this embodiment of the application, the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles, and the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles. The CSI correlation among them is used to obtain the target channel vector of N CSI feedback periods. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
本申请包括但不限于以上实施例中所给出的技术方案，例如，每个神经网络内部的具体结构设计，以及N，K，L等配置参数都可以依据通信场景的不同，如终端移动速度，信道时延扩展等特性自适应调整，以优化传输性能。以及，本申请实施例不限于基站与终端间的信道向量压缩与反馈，本申请实施例也可适用于终端与终端之间(如Sidelink)、以及基站与基站之间(如回传链路(backhaul link))可能存在的CSI反馈开销降低需求。本申请实施例着重保护的是基于AI的CSI周期性反馈开销降低方法。This application includes but is not limited to the technical solutions given in the above embodiments. For example, the specific structural design inside each neural network, as well as configuration parameters such as N, K, and L, etc., can be based on different communication scenarios, such as terminal moving speed , Channel delay expansion and other characteristics adaptive adjustment to optimize transmission performance. And, the embodiment of the present application is not limited to the channel vector compression and feedback between the base station and the terminal, and the embodiment of the present application can also be applied between the terminal and the terminal (such as Sidelink), and between the base station and the base station (such as the backhaul link ( backhaul link)) possible CSI feedback overhead reduction requirements. The embodiments of the present application focus on protecting the AI-based method for reducing the overhead of periodic CSI feedback.
上文结合图8至图17，详细描述了本申请的收端设备侧的实施例，下文结合图18，详细描述本申请的发端设备侧的实施例，应理解，发端设备侧的实施例与收端设备侧的实施例相互对应，类似的描述可以参照收端设备侧的实施例。The above describes in detail the embodiment of the receiving device side of this application with reference to Figures 8 to 17, and the following describes in detail the embodiment of the originating device side of this application in conjunction with Figure 18. It should be understood that the embodiment of the originating device side is the same as The embodiments on the receiving device side correspond to each other, and similar descriptions may refer to the embodiments on the receiving device side.
图18是根据本申请实施例的信道信息的反馈方法300的示意性流程图，如图18所示，该信道信息的反馈方法300可以包括如下内容中的至少部分内容：FIG. 18 is a schematic flowchart of a channel information feedback method 300 according to an embodiment of the present application. As shown in FIG. 18 , the channel information feedback method 300 may include at least part of the following content:
S310，发端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈；其中，N为正整数，且N≥2。S310. The transmitting device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N≥2.
在一些实施例中，收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取该N个CSI反馈周期的目标信道向量。In some embodiments, the receiving end device acquires the target channel vectors of the N CSI feedback periods according to the CSI correlation between different CSI feedback periods in the N CSI feedback periods.
在一些实施例中，该CSI相关性包括CSI时域相关性和/或CSI频域相关性。In some embodiments, the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
在一些实施例中，上述S310具体可以包括：In some embodiments, the above S310 may specifically include:
该发端设备通过第一发端神经网络分别对该N个CSI反馈周期中的K个CSI反馈周期的信道向量进行编码，得到K条比特流；以及该发端设备不对该N个CSI反馈周期中除该K个CSI反馈周期之外的CSI反馈周期的信道向量进行编码；该发端设备分别向收端设备发送该K条比特流。The originating device encodes the channel vectors of K CSI feedback periods in the N CSI feedback periods through the first originating neural network to obtain K bit streams; and the originating device does not divide the N CSI feedback periods The channel vectors of the CSI feedback periods other than the K CSI feedback periods are encoded; the transmitting device sends the K bit streams to the receiving device respectively.
在一些实施例中，该K条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the K bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该K个CSI反馈周期为该N个CSI反馈周期中的前K个连续的CSI反馈周期。In some embodiments, the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
在一些实施例中，K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。In some embodiments, the values of K and N are determined from the group G {K, N}, G is a positive integer, and G≥2.
在一些实施例中，K和N的取值是根据信道场景从该G组{K，N}中确定的。In some embodiments, the values of K and N are determined from the G group {K, N} according to the channel scenario.
在一些实施例中，该G组{K，N}是网络设备通过RRC信令或DCI信令配置的。In some embodiments, the G group {K, N} is configured by the network device through RRC signaling or DCI signaling.
在一些实施例中，该G组{K，N}是网络设备通过RRC信令和/或DCI信令中的
Figure PCTCN2021093689-appb-000013
个比特配置的，其中，
Figure PCTCN2021093689-appb-000014
表示向上取整。 In some embodiments, the G group {K, N} is set by the network device through RRC signaling and/or DCI signaling
Figure PCTCN2021093689-appb-000013
bit configuration, where,
Figure PCTCN2021093689-appb-000014
Indicates rounding up.
在一些实施例中，上述S310具体可以包括：In some embodiments, the above S310 may specifically include:
该发端设备通过第二发端神经网络分别对该N个CSI反馈周期中的P个主CSI反馈周期的信道向量进行编码，得到P条比特流；The originating device respectively encodes the channel vectors of the P main CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain P bit streams;
该发端设备通过该第二发端神经网络分别对该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量进行编码，得到Q条比特流；The originating device respectively encodes the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;
该发端设备分别向收端设备发送该P条比特流和该Q条比特流；其中，P和Q均为正整数，且 P+Q＝N。The transmitting device sends the P bit streams and the Q bit streams to the receiving device respectively; wherein, both P and Q are positive integers, and P+Q=N.
在一些实施例中，该P条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the P bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该Q条比特流中的一条比特流占用的比特数小于该P条比特流中的一条比特流占用的比特数。In some embodiments, the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
在一些实施例中，该Q条比特流中的不同的比特流占用的比特数不同，或者，该Q条比特流中的不同的比特流占用的比特数相同。In some embodiments, different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
在一些实施例中，该N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。In some embodiments, one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
在一些实施例中，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。In some embodiments, the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
在一些实施例中，该N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
在一些实施例中，上述S310具体可以包括：In some embodiments, the above S310 may specifically include:
该发端设备通过第三发端神经网络分别对该N个CSI反馈周期的信道向量进行编码，得到N条比特流；The originating device respectively encodes the channel vectors of the N CSI feedback cycles through a third originating neural network to obtain N bit streams;
该发端设备分别向收端设备发送该N条比特流。The originating device sends the N bit streams to the receiving device respectively.
在一些实施例中，该N条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the N bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
因此，在本申请实施例中，发端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，以及收端设备可以根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取N个CSI反馈周期的目标信道向量。也即，本申请实施例可以利用N个CSI反馈周期中不同CSI反馈周期之间的CSI时域相关性和/或CSI频域相关性，进行CSI反馈，能够提高CSI的反馈精度，并降低CSI反馈开销。Therefore, in this embodiment of the application, the transmitting device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles, and the receiving device can perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles. The CSI correlation among them is used to obtain the target channel vector of N CSI feedback periods. That is to say, the embodiment of the present application can use the CSI time-domain correlation and/or CSI frequency-domain correlation between different CSI feedback cycles in N CSI feedback cycles to perform CSI feedback, which can improve the accuracy of CSI feedback and reduce the CSI Feedback overhead.
上文结合图8至图18，详细描述了本申请的方法实施例，下文结合图19至图23，详细描述本申请的装置实施例，应理解，装置实施例与方法实施例相互对应，类似的描述可以参照方法实施例。The method embodiment of the present application is described in detail above with reference to FIG. 8 to FIG. 18 , and the device embodiment of the present application is described in detail below in conjunction with FIG. 19 to FIG. 23 . It should be understood that the device embodiment and the method embodiment correspond to each other, similar to The description can refer to the method embodiment.
图19示出了根据本申请实施例的收端设备400的示意性框图。如图19所示，该收端设备400包括：Fig. 19 shows a schematic block diagram of a receiving device 400 according to an embodiment of the present application. As shown in Figure 19, the receiving end device 400 includes:
处理单元410，用于根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取该N个CSI反馈周期的目标信道向量；其中，N为正整数，且N≥2。The processing unit 410 is configured to acquire target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles; wherein, N is a positive integer, and N≥2.
在一些实施例中，该CSI相关性包括CSI时域相关性和/或CSI频域相关性。In some embodiments, the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
在一些实施例中，该收端设备400包括通信单元420，其中，In some embodiments, the receiving device 400 includes a communication unit 420, wherein,
该通信单元420用于接收发端设备发送的K条比特流，该K条比特流分别是由该N个CSI反馈周期中的K个CSI反馈周期的信道向量经编码之后得到的，K为正整数，且K＜N；The communication unit 420 is configured to receive K bit streams sent by the originating device, the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles, and K is a positive integer , and K<N;
该处理单元410用于分别对该K条比特流进行解码，得到该K个CSI反馈周期的K个目标信道向量；The processing unit 410 is configured to respectively decode the K bit streams to obtain K target channel vectors for the K CSI feedback cycles;
该处理单元410用于通过第一收端神经网络对该K个目标信道向量进行预测，得到该N个CSI反馈周期中除该K个CSI反馈周期之外的CSI反馈周期的N-K个目标信道向量。The processing unit 410 is configured to predict the K target channel vectors through the first receiving-end neural network, and obtain N-K target channel vectors of CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles .
在一些实施例中，该处理单元410具体用于：In some embodiments, the processing unit 410 is specifically used for:
通过第二收端神经网络分别对该K条比特流进行解码，得到该K个目标信道向量。The K bit streams are respectively decoded by the second receiving-end neural network to obtain the K target channel vectors.
在一些实施例中，该K条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；该处理单元410具体用于：In some embodiments, the bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1; the processing unit 410 is specifically used for:
通过该第二收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第二收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤K，1≤j≤S，L＜i；Decode the bit stream from the jth subband of the i-Lth CSI feedback period to the jth subband of the ith CSI feedback period through the second receiving neural network, and through the second receiving end The terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1≤i≤K, 1≤j≤S, L<i;
根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该K个目标信道向量。The K target channel vectors are acquired according to the target channel vectors on the j th subband of the i th CSI feedback period.
在一些实施例中，该K个CSI反馈周期为该N个CSI反馈周期中的前K个连续的CSI反馈周期。In some embodiments, the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
在一些实施例中，K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。In some embodiments, the values of K and N are determined from the group G {K, N}, G is a positive integer, and G≥2.
在一些实施例中，K和N的取值是根据信道场景从该G组{K，N}中确定的。In some embodiments, the values of K and N are determined from the G group {K, N} according to the channel scenario.
在一些实施例中，该G组{K，N}是网络设备通过无线资源控制RRC信令和/或下行控制信息DCI信令配置的。In some embodiments, the G group {K, N} is configured by the network device through radio resource control RRC signaling and/or downlink control information DCI signaling.
在一些实施例中，该G组{K，N}是网络设备通过RRC信令或DCI信令中的
Figure PCTCN2021093689-appb-000015
个比特配置的，其中，
Figure PCTCN2021093689-appb-000016
表示向上取整。 In some embodiments, the G group {K, N} is set by the network device through RRC signaling or DCI signaling
Figure PCTCN2021093689-appb-000015
bit configuration, where,
Figure PCTCN2021093689-appb-000016
Indicates rounding up.
在一些实施例中，该收端设备400包括通信单元420，其中，In some embodiments, the receiving device 400 includes a communication unit 420, wherein,
该通信单元420用于接收发端设备发送的P条比特流和Q条比特流；其中，该P条比特流分别是由该N个CSI反馈周期中的P个主CSI反馈周期的信道向量经编码之后得到的，该Q条比特流分别是由该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量经编码之后得到的，或者，该Q条比特流分别是由该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量与对应的主CSI反馈周期的信道向量的差值经编码之后得到的，P和Q均为正整数，且P+Q＝N；The communication unit 420 is configured to receive P bit streams and Q bit streams sent by the originating device; wherein, the P bit streams are respectively encoded by the channel vectors of the P main CSI feedback cycles in the N CSI feedback cycles Obtained later, the Q bit streams are respectively obtained by encoding the channel vectors of the Q secondary CSI feedback cycles in the N CSI feedback cycles, or the Q bit streams are respectively obtained by the N CSI feedback cycles The difference between the channel vectors of the Q auxiliary CSI feedback periods in the period and the channel vector of the corresponding main CSI feedback period is obtained after encoding, where P and Q are both positive integers, and P+Q=N;
该处理单元410用于分别对该P条比特流进行解码，得到该P个主CSI反馈周期的P个目标信道向量；The processing unit 410 is configured to respectively decode the P bit streams to obtain P target channel vectors of the P main CSI feedback cycles;
该处理单元410用于通过第三收端神经网络分别对该Q条比特流中的第一比特流和该P条比特流中的第二比特流进行解码，得到该Q个辅CSI反馈周期的Q个目标信道向量；其中，该第一比特流对应的辅CSI反馈周期为该第二比特流对应的主CSI反馈周期伴随的辅CSI反馈周期。The processing unit 410 is configured to respectively decode the first bit stream in the Q bit streams and the second bit stream in the P bit streams through the third receiving-end neural network to obtain the Q secondary CSI feedback cycles Q target channel vectors; wherein, the secondary CSI feedback cycle corresponding to the first bit stream is the secondary CSI feedback cycle accompanying the primary CSI feedback cycle corresponding to the second bit stream.
在一些实施例中，该处理单元410具体用于：In some embodiments, the processing unit 410 is specifically used for:
通过第四收端神经网络分别对该P条比特流进行解码，得到该P个主CSI反馈周期的P个目标信道向量。The P bit streams are respectively decoded by the fourth receiving-end neural network to obtain P target channel vectors of the P main CSI feedback cycles.
在一些实施例中，该P条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；该处理单元410具体用于：In some embodiments, the bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1; the processing unit 410 is specifically used for:
通过该第四收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第四收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤P，1≤j≤S，L＜i；The bit stream on the jth subband of the i-Lth CSI feedback period to the bitstream on the jth subband of the ith CSI feedback period is decoded through the fourth receiving end neural network, and through the fourth receiving end The terminal neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, j, L are all positive integers, and 1≤i≤P, 1≤j≤S, L<i;
根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该P个主CSI反馈周期的P个目标信道向量。According to the target channel vector on the j th subband of the i th CSI feedback cycle, P target channel vectors for the P main CSI feedback cycles are obtained.
在一些实施例中，该Q条比特流中的一条比特流占用的比特数小于该P条比特流中的一条比特流占用的比特数。In some embodiments, the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
在一些实施例中，该Q条比特流中的不同的比特流占用的比特数不同，或者，该Q条比特流中的不同的比特流占用的比特数相同。In some embodiments, different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
在一些实施例中，该N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。In some embodiments, one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
在一些实施例中，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。In some embodiments, the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
在一些实施例中，该N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
在一些实施例中，该收端设备400包括通信单元420，其中，In some embodiments, the receiving device 400 includes a communication unit 420, wherein,
该通信单元420用于接收发端设备发送的N条比特流；其中，该N条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The communication unit 420 is configured to receive N bit streams sent by the originating device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1;
该处理单元410用于通过第五收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过该第五收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤N，1≤j≤S，L＜i；The processing unit 410 is configured to decode the bit stream from the jth subband of the i-L CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and Decode the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle through the fifth receiving-end neural network, and obtain the target channel vector on the j-th sub-band of the i-th CSI feedback cycle , i, j, L are all positive integers, and 1≤i≤N, 1≤j≤S, L<i;
该处理单元410用于根据该第i个CSI反馈周期的第j个子带上的目标信道向量，获取该N个CSI反馈周期的目标信道向量。The processing unit 410 is configured to acquire the target channel vectors of the N CSI feedback periods according to the target channel vectors on the jth subband of the i-th CSI feedback period.
在一些实施例中，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数。In some embodiments, the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is less than the at least one auxiliary feedback subband The number of bits occupied by the information of the main feedback subband in one main feedback subband.
在一些实施例中，该S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
在一些实施例中，上述通信单元可以是通信接口或收发器，或者是通信芯片或者片上***的输入输出接口。上述处理单元可以是一个或多个处理器。In some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.
应理解，根据本申请实施例的收端设备400可对应于本申请方法实施例中的收端设备，并且收端设备300中的各个单元的上述和其它操作和/或功能分别为了实现图8所示方法200中收端设备的相应流程，为了简洁，在此不再赘述。It should be understood that the receiving end device 400 according to the embodiment of the present application may correspond to the receiving end device in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the receiving end device 300 are respectively in order to realize the For the sake of brevity, the corresponding process of the receiving device in the shown method 200 is not repeated here.
图20示出了根据本申请实施例的发端设备500的示意性框图。如图20所示，该发端设备500包括：Fig. 20 shows a schematic block diagram of an originating device 500 according to an embodiment of the present application. As shown in Figure 20, the originating device 500 includes:
处理单元510，用于根据N个信道状态信息CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈；其中，N为正整数，且N≥2。The processing unit 510 is configured to perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; wherein, N is a positive integer, and N≥2.
在一些实施例中，该CSI相关性包括CSI时域相关性和/或CSI频域相关性。In some embodiments, the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
在一些实施例中，该发端设备500还包括通信单元520，其中，In some embodiments, the originating device 500 further includes a communication unit 520, wherein,
该处理单元510用于通过第一发端神经网络分别对该N个CSI反馈周期中的K个CSI反馈周期的信道向量进行编码，得到K条比特流；以及该处理单元不对该N个CSI反馈周期中除该K个CSI反馈周期之外的CSI反馈周期的信道向量进行编码；The processing unit 510 is configured to respectively encode the channel vectors of the K CSI feedback cycles in the N CSI feedback cycles through the first sending-end neural network to obtain K bit streams; and the processing unit does not encode the N CSI feedback cycles The channel vectors of the CSI feedback cycles other than the K CSI feedback cycles are encoded;
该通信单元520用于分别向收端设备发送该K条比特流。The communication unit 520 is configured to respectively send the K bit streams to the receiving device.
在一些实施例中，该K条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the K bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该K个CSI反馈周期为该N个CSI反馈周期中的前K个连续的CSI反馈周期。In some embodiments, the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
在一些实施例中，K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。In some embodiments, the values of K and N are determined from the group G {K, N}, G is a positive integer, and G≥2.
在一些实施例中，K和N的取值是根据信道场景从该G组{K，N}中确定的。In some embodiments, the values of K and N are determined from the G group {K, N} according to the channel scenario.
在一些实施例中，该G组{K，N}是网络设备通过无线资源控制RRC信令或下行控制信息DCI信令配置的。In some embodiments, the G group {K, N} is configured by the network device through radio resource control RRC signaling or downlink control information DCI signaling.
在一些实施例中，该G组{K，N}是网络设备通过RRC信令和/或DCI信令中的
Figure PCTCN2021093689-appb-000017
个比特配置的。 In some embodiments, the G group {K, N} is set by the network device through RRC signaling and/or DCI signaling
Figure PCTCN2021093689-appb-000017
bit configuration.
在一些实施例中，该发端设备500还包括通信单元520，其中，In some embodiments, the originating device 500 further includes a communication unit 520, wherein,
该处理单元510用于通过第二发端神经网络分别对该N个CSI反馈周期中的P个主CSI反馈周期的信道向量进行编码，得到P条比特流；The processing unit 510 is configured to respectively encode the channel vectors of the P main CSI feedback cycles in the N CSI feedback cycles through the second sending-end neural network to obtain P bit streams;
该处理单元510用于通过该第二发端神经网络分别对该N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量进行编码，得到Q条比特流；The processing unit 510 is configured to respectively encode the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;
该通信单元520用于分别向收端设备发送该P条比特流和该Q条比特流；其中，P和Q均为正整数，且P+Q＝N。The communication unit 520 is configured to respectively send the P bit streams and the Q bit streams to the receiving device; wherein, both P and Q are positive integers, and P+Q=N.
在一些实施例中，该P条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the P bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该Q条比特流中的一条比特流占用的比特数小于该P条比特流中的一条比特流占用的比特数。In some embodiments, the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
在一些实施例中，该Q条比特流中的不同的比特流占用的比特数不同，或者，该Q条比特流中的不同的比特流占用的比特数相同。In some embodiments, different bit streams in the Q bit streams occupy different numbers of bits, or different bit streams in the Q bit streams occupy the same number of bits.
在一些实施例中，该N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。In some embodiments, one primary CSI feedback cycle among the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
在一些实施例中，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，该N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。In some embodiments, the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or the secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles The number is different.
在一些实施例中，该N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are configured by the network device through RRC signaling and/or DCI signaling.
在一些实施例中，该发端设备500还包括通信单元520，其中，In some embodiments, the originating device 500 further includes a communication unit 520, wherein,
该处理单元510用于通过第三发端神经网络分别对该N个CSI反馈周期的信道向量进行编码，得到N条比特流；The processing unit 510 is configured to respectively encode the channel vectors of the N CSI feedback cycles through the third originating neural network to obtain N bit streams;
该通信单元520用于分别向收端设备发送该N条比特流。The communication unit 520 is configured to respectively send the N bit streams to the receiving device.
在一些实施例中，该N条比特流中的比特流包括S个子带的信息，该S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，该至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于该至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。In some embodiments, the bit streams in the N bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the at least one auxiliary feedback subband The number of bits occupied by the information of the auxiliary feedback subband in the at least one main feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, S is a positive integer, and S>1.
在一些实施例中，该S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。In some embodiments, the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
在一些实施例中，上述通信单元可以是通信接口或收发器，或者是通信芯片或者片上***的输入输出接口。上述处理单元可以是一个或多个处理器。In some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.
应理解，根据本申请实施例的发端设备500可对应于本申请方法实施例中的发端设备，并且发端设备500中的各个单元的上述和其它操作和/或功能分别为了实现图18所示方法300中发端设备的相应流程，为了简洁，在此不再赘述。It should be understood that the originating device 500 according to the embodiment of the present application may correspond to the originating device in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the originating device 500 are for realizing the method shown in FIG. 18 For the sake of brevity, the corresponding process of the originating device in 300 will not be repeated here.
图21是本申请实施例提供的一种通信设备600示意性结构图。图21所示的通信设备600包括处理器610，处理器610可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。FIG. 21 is a schematic structural diagram of a communication device 600 provided by an embodiment of the present application. The communication device 600 shown in FIG. 21 includes a processor 610, and the processor 610 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.
在一些实施例中，如图21所示，通信设备600还可以包括存储器620。其中，处理器610可以从存储器620中调用并运行计算机程序，以实现本申请实施例中的方法。In some embodiments, as shown in FIG. 21 , the communication device 600 may further include a memory 620 . Wherein, the processor 610 can invoke and run a computer program from the memory 620, so as to implement the method in the embodiment of the present application.
其中，存储器620可以是独立于处理器610的一个单独的器件，也可以集成在处理器610中。Wherein, the memory 620 may be an independent device independent of the processor 610 , or may be integrated in the processor 610 .
在一些实施例中，如图21所示，通信设备600还可以包括收发器630，处理器610可以控制该收发器630与其他设备进行通信，具体地，可以向其他设备发送信息或数据，或接收其他设备发送的信息或数据。In some embodiments, as shown in FIG. 21 , the communication device 600 may further include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or Receive messages or data from other devices.
其中，收发器630可以包括发射机和接收机。收发器630还可以进一步包括天线，天线的数量可以为一个或多个。Wherein, the transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include antennas, and the number of antennas may be one or more.
在一些实施例中，该通信设备600具体可为本申请实施例的发端设备，并且该通信设备600可以实现本申请实施例的各个方法中由发端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the communication device 600 may specifically be the originating device in the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the originating device in each method of the embodiment of the present application. For the sake of brevity, the Let me repeat.
在一些实施例中，该通信设备600具体可为本申请实施例的收端设备，并且该通信设备600可以实现本申请实施例的各个方法中由收端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the communication device 600 may specifically be the receiving device of the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the receiving device in each method of the embodiment of the present application. For brevity, the This will not be repeated here.
图22是本申请实施例的装置的示意性结构图。图22所示的装置700包括处理器710，处理器710可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。Fig. 22 is a schematic structural diagram of a device according to an embodiment of the present application. The apparatus 700 shown in FIG. 22 includes a processor 710, and the processor 710 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.
在一些实施例中，如图22所示，装置700还可以包括存储器720。其中，处理器710可以从存储器720中调用并运行计算机程序，以实现本申请实施例中的方法。In some embodiments, as shown in FIG. 22 , the device 700 may further include a memory 720 . Wherein, the processor 710 can invoke and run a computer program from the memory 720, so as to implement the method in the embodiment of the present application.
其中，存储器720可以是独立于处理器710的一个单独的器件，也可以集成在处理器710中。Wherein, the memory 720 may be an independent device independent of the processor 710 , or may be integrated in the processor 710 .
在一些实施例中，该装置700还可以包括输入接口730。其中，处理器710可以控制该输入接口730与其他设备或芯片进行通信，具体地，可以获取其他设备或芯片发送的信息或数据。In some embodiments, the device 700 may further include an input interface 730 . Wherein, the processor 710 can control the input interface 730 to communicate with other devices or chips, specifically, can obtain information or data sent by other devices or chips.
在一些实施例中，该装置700还可以包括输出接口740。其中，处理器710可以控制该输出接口740与其他设备或芯片进行通信，具体地，可以向其他设备或芯片输出信息或数据。In some embodiments, the device 700 may further include an output interface 740 . Wherein, the processor 710 can control the output interface 740 to communicate with other devices or chips, specifically, can output information or data to other devices or chips.
在一些实施例中，该装置可应用于本申请实施例中的发端设备，并且该装置可以实现本申请实施例的各个方法中由发端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the apparatus can be applied to the originating device in the embodiments of the present application, and the apparatus can implement the corresponding processes implemented by the originating device in the methods of the embodiments of the present application. For the sake of brevity, details are not repeated here.
在一些实施例中，该装置可应用于本申请实施例中的收端设备，并且该装置可以实现本申请实施例的各个方法中由收端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the device can be applied to the receiving device in the embodiments of the present application, and the device can implement the corresponding processes implemented by the receiving device in the methods of the embodiments of the present application. For the sake of brevity, no further repeat.
在一些实施例中，本申请实施例提到的装置也可以是芯片。例如可以是***级芯片，***芯片，芯片***或片上***芯片等。In some embodiments, the device mentioned in the embodiment of the present application may also be a chip. For example, it may be a system-on-a-chip, a system-on-a-chip, a system-on-a-chip, or a system-on-a-chip.
图23是本申请实施例提供的一种通信***800的示意性框图。如图23所示，该通信***800包括发端设备810和收端设备820。FIG. 23 is a schematic block diagram of a communication system 800 provided by an embodiment of the present application. As shown in FIG. 23 , the communication system 800 includes an originating device 810 and a receiving device 820 .
其中，该发端设备810可以用于实现上述方法中由发端设备实现的相应的功能，以及该收端设备820可以用于实现上述方法中由收端设备实现的相应的功能为了简洁，在此不再赘述。Wherein, the originating device 810 can be used to realize the corresponding functions realized by the originating device in the above method, and the receiving device 820 can be used to realize the corresponding functions realized by the receiving device in the above method. Let me repeat.
应理解，本申请实施例的处理器可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。It should be understood that the processor in the embodiment of the present application may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above-mentioned method embodiments may be completed by an integrated logic circuit of hardware in a processor or instructions in the form of software. The above-mentioned processor can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other available Program logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可 编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)。应注意，本文描述的***和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。It can be understood that the memory in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electronically programmable Erase Programmable Read-Only Memory (Electrically EPROM, EEPROM) or Flash. The volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (Synchlink DRAM, SLDRAM ) and Direct Memory Bus Random Access Memory (Direct Rambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.
应理解，上述存储器为示例性但不是限制性说明，例如，本申请实施例中的存储器还可以是静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synch link DRAM，SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)等等。也就是说，本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。It should be understood that the above-mentioned memory is illustrative but not restrictive. For example, the memory in the embodiment of the present application may also be a static random access memory (static RAM, SRAM), a dynamic random access memory (dynamic RAM, DRAM), Synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection Dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is, the memory in the embodiments of the present application is intended to include, but not be limited to, these and any other suitable types of memory.
本申请实施例还提供了一种计算机可读存储介质，用于存储计算机程序。The embodiment of the present application also provides a computer-readable storage medium for storing computer programs.
在一些实施例中，该计算机可读存储介质可应用于本申请实施例中的发端设备，并且该计算机程序使得计算机执行本申请实施例的各个方法中由发端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer-readable storage medium can be applied to the originating device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the originating device in the methods of the embodiments of the present application. For brevity, I won't repeat them here.
在一些实施例中，该计算机可读存储介质可应用于本申请实施例中的收端设备，并且该计算机程序使得计算机执行本申请实施例的各个方法中由收端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer-readable storage medium can be applied to the terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the terminal device in the methods of the embodiments of the present application, in order It is concise and will not be repeated here.
本申请实施例还提供了一种计算机程序产品，包括计算机程序指令。The embodiment of the present application also provides a computer program product, including computer program instructions.
在一些实施例中，该计算机程序产品可应用于本申请实施例中的发端设备，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由发端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer program product can be applied to the originating device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the originating device in the various methods of the embodiments of the present application. For brevity, the This will not be repeated here.
在一些实施例中，该计算机程序产品可应用于本申请实施例中的收端设备，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由收端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer program product can be applied to the receiving device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the receiving device in the methods of the embodiments of the present application. For the sake of brevity , which will not be repeated here.
本申请实施例还提供了一种计算机程序。The embodiment of the present application also provides a computer program.
在一些实施例中，该计算机程序可应用于本申请实施例中的发端设备，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由发端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer program can be applied to the originating device in the embodiment of the present application. When the computer program is run on the computer, the computer executes the corresponding process implemented by the originating device in each method of the embodiment of the present application, For the sake of brevity, details are not repeated here.
在一些实施例中，该计算机程序可应用于本申请实施例中的收端设备，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由收端设备实现的相应流程，为了简洁，在此不再赘述。In some embodiments, the computer program can be applied to the receiving device in the embodiments of the present application. When the computer program is run on the computer, the computer executes the corresponding functions implemented by the receiving device in the methods of the embodiments of the present application. For the sake of brevity, the process will not be repeated here.
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的***、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
在本申请所提供的几个实施例中，应该理解到，所揭露的***、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。针对这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中， 包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. In view of such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (90)

  1. 一种信道信息的反馈方法，其特征在于，包括：A channel information feedback method, characterized in that, comprising:
    收端设备根据N个信道状态信息CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取所述N个CSI反馈周期的目标信道向量；其中，N为正整数，且N≥2。The receiving end device acquires target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; wherein, N is a positive integer, and N≥2.
  2. 如权利要求1所述的方法，其特征在于，所述CSI相关性包括CSI时域相关性和/或CSI频域相关性。The method according to claim 1, wherein the CSI correlation comprises CSI time domain correlation and/or CSI frequency domain correlation.
  3. 如权利要求1或2所述的方法，其特征在于，所述收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取所述N个CSI反馈周期的目标信道向量，包括：The method according to claim 1 or 2, wherein the receiving end device acquires the target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles ,include:
    所述收端设备接收发端设备发送的K条比特流，所述K条比特流分别是由所述N个CSI反馈周期中的K个CSI反馈周期的信道向量经编码之后得到的，K为正整数，且K＜N；The receiving device receives K bit streams sent by the transmitting device, and the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles, and K is positive Integer, and K<N;
    所述收端设备分别对所述K条比特流进行解码，得到所述K个CSI反馈周期的K个目标信道向量；The receiving device decodes the K bit streams respectively to obtain K target channel vectors of the K CSI feedback cycles;
    所述收端设备通过第一收端神经网络对所述K个目标信道向量进行预测，得到所述N个CSI反馈周期中除所述K个CSI反馈周期之外的CSI反馈周期的N-K个目标信道向量。The receiving end device predicts the K target channel vectors through the first receiving end neural network, and obtains N-K target vectors of CSI feedback cycles other than the K CSI feedback cycles in the N CSI feedback cycles channel vector.
  4. 如权利要求3所述的方法，其特征在于，所述收端设备分别对所述K条比特流进行解码，得到所述K个CSI反馈周期的K个目标信道向量，包括：The method according to claim 3, wherein the receiving device decodes the K bit streams respectively to obtain K target channel vectors for the K CSI feedback cycles, including:
    所述收端设备通过第二收端神经网络分别对所述K条比特流进行解码，得到所述K个目标信道向量。The receiving end device decodes the K bit streams respectively through the second receiving end neural network to obtain the K target channel vectors.
  5. 如权利要求4所述的方法，其特征在于，所述K条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The method according to claim 4, wherein the bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1;
    所述收端设备通过第二收端神经网络分别对所述K条比特流进行解码，得到所述K个目标信道向量，包括：The receiving end device decodes the K bit streams respectively through the second receiving end neural network to obtain the K target channel vectors, including:
    所述收端设备通过所述第二收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第二收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤K，1≤j≤S，L＜i；The receiving end device decodes the bit stream on the jth subband of the i-Lth CSI feedback cycle to the bit stream on the jth subband of the ith CSI feedback cycle through the second receiving end neural network, and decoding the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle through the second receiving-end neural network to obtain the target on the j-th sub-band of the i-th CSI feedback cycle Channel vector, i, j, L are all positive integers, and 1≤i≤K, 1≤j≤S, L<i;
    所述收端设备根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述K个目标信道向量。The receiving end device acquires the K target channel vectors according to the target channel vectors on the j th subband of the i th CSI feedback period.
  6. 如权利要求3至5中任一项所述的方法，其特征在于，所述K个CSI反馈周期为所述N个CSI反馈周期中的前K个连续的CSI反馈周期。The method according to any one of claims 3 to 5, wherein the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  7. 如权利要求3至6中任一项所述的方法，其特征在于，The method according to any one of claims 3 to 6, characterized in that,
    K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。The values of K and N are determined from G group {K, N}, G is a positive integer, and G≥2.
  8. 如权利要求7所述的方法，其特征在于，The method of claim 7, wherein
    K和N的取值是根据信道场景从所述G组{K，N}中确定的。The values of K and N are determined from the G group {K, N} according to the channel scenario.
  9. 如权利要求7或8所述的方法，其特征在于，所述G组{K，N}是网络设备通过无线资源控制RRC信令和/或下行控制信息DCI信令配置的。The method according to claim 7 or 8, wherein the G group {K, N} is configured by a network device through radio resource control RRC signaling and/or downlink control information DCI signaling.
  10. 如权利要求7至9中任一项所述的方法，其特征在于，所述G组{K，N}是网络设备通过RRC信令或DCI信令中的
    Figure PCTCN2021093689-appb-100001
    个比特配置的，其中，
    Figure PCTCN2021093689-appb-100002
    表示向上取整。     The method according to any one of claims 7 to 9, characterized in that, the G group {K, N} is the network equipment through RRC signaling or DCI signaling
    Figure PCTCN2021093689-appb-100001
    bit configuration, where,
    Figure PCTCN2021093689-appb-100002
    Indicates rounding up.
  11. 如权利要求1或2所述的方法，其特征在于，所述收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取所述N个CSI反馈周期的目标信道向量，包括：The method according to claim 1 or 2, wherein the receiving end device acquires the target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles ,include:
    所述收端设备接收发端设备发送的P条比特流和Q条比特流；其中，所述P条比特流分别是由所述N个CSI反馈周期中的P个主CSI反馈周期的信道向量经编码之后得到的，所述Q条比特流分别是由所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量经编码之后得到的，或者，所述Q条比特流分别是由所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量与对应的主CSI反馈周期的信道向量的差值经编码之后得到的，P和Q均为正整数，且P+Q＝N；The receiving end device receives P bit streams and Q bit streams sent by the sending end device; wherein, the P bit streams are respectively channel vectors of P main CSI feedback cycles in the N CSI feedback cycles. After coding, the Q bit streams are respectively obtained by encoding the channel vectors of the Q secondary CSI feedback cycles in the N CSI feedback cycles, or, the Q bit streams are respectively obtained by the The difference between the channel vectors of the Q auxiliary CSI feedback periods in the N CSI feedback periods and the channel vector of the corresponding main CSI feedback period is obtained after encoding, P and Q are both positive integers, and P+Q=N ;
    所述收端设备分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量；The receiving device decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback cycles;
    所述收端设备通过第三收端神经网络分别对所述Q条比特流中的第一比特流和所述P条比特流中的第二比特流进行解码，得到所述Q个辅CSI反馈周期的Q个目标信道向量；其中，所述第一比特流对应的辅CSI反馈周期为所述第二比特流对应的主CSI反馈周期伴随的辅CSI反馈周期。The receiving end device decodes the first bit stream in the Q bit streams and the second bit stream in the P bit streams respectively through the third receiving end neural network to obtain the Q auxiliary CSI feedbacks Periodic Q target channel vectors; wherein, the secondary CSI feedback cycle corresponding to the first bit stream is the secondary CSI feedback cycle accompanying the primary CSI feedback cycle corresponding to the second bit stream.
  12. 如权利要求11所述的方法，其特征在于，所述收端设备分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量，包括：The method according to claim 11, wherein the receiving device decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback cycles, including:
    所述收端设备通过第四收端神经网络分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量。The receiving end device decodes the P bit streams respectively through the fourth receiving end neural network to obtain P target channel vectors of the P main CSI feedback periods.
  13. 如权利要求12所述的方法，其特征在于，所述P条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The method according to claim 12, wherein the bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1;
    所述收端设备通过第四收端神经网络分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量，包括：The receiving end device decodes the P bit streams respectively through the fourth receiving end neural network, and obtains P target channel vectors of the P main CSI feedback cycles, including:
    所述收端设备通过所述第四收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第四收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤P，1≤j≤S，L＜i；The receiving end device decodes the bit stream on the jth subband of the i-Lth CSI feedback cycle to the bit stream on the jth subband of the ith CSI feedback cycle through the fourth receiving end neural network, and decoding the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle through the fourth receiving-end neural network to obtain the target on the j-th sub-band of the i-th CSI feedback cycle Channel vector, i, j, L are all positive integers, and 1≤i≤P, 1≤j≤S, L<i;
    所述收端设备根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述P个主CSI反馈周期的P个目标信道向量。The receiving end device acquires P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the jth subband of the i-th CSI feedback period.
  14. 如权利要求11至13中任一项所述的方法，其特征在于，A method according to any one of claims 11 to 13, wherein
    所述Q条比特流中的一条比特流占用的比特数小于所述P条比特流中的一条比特流占用的比特数。The number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  15. 如权利要求14所述的方法，其特征在于，所述Q条比特流中的不同的比特流占用的比特数不同，或者，所述Q条比特流中的不同的比特流占用的比特数相同。The method according to claim 14, wherein the number of bits occupied by different bit streams in the Q bit streams is different, or the number of bits occupied by different bit streams in the Q bit streams is the same .
  16. 如权利要求11至15中任一项所述的方法，其特征在于，所述N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。The method according to any one of claims 11 to 15, wherein one primary CSI feedback cycle in the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  17. 如权利要求11至16中任一项所述的方法，其特征在于，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。The method according to any one of claims 11 to 16, wherein the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or, the N CSI feedback cycles In the feedback cycle, different primary CSI feedback cycles are accompanied by different numbers of secondary CSI feedback cycles.
  18. 如权利要求11至17中任一项所述的方法，其特征在于，所述N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。The method according to any one of claims 11 to 17, wherein the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are implemented by network equipment through RRC signaling and/or DCI signaling configured.
  19. 如权利要求1或2所述的方法，其特征在于，所述收端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取所述N个CSI反馈周期的目标信道向量，包括：The method according to claim 1 or 2, wherein the receiving end device acquires the target channel vectors of the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles ,include:
    所述收端设备接收发端设备发送的N条比特流；其中，所述N条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The receiving end device receives N bit streams sent by the sending end device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1;
    所述收端设备通过第五收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第五收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤N，1≤j≤S，L＜i；The receiving end device decodes the bit stream from the jth subband of the i-Lth CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and through The fifth receiver neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle , i, j, L are all positive integers, and 1≤i≤N, 1≤j≤S, L<i;
    所述收端设备根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述N个CSI反馈周期的目标信道向量。The receiving end device acquires the target channel vectors of the N CSI feedback periods according to the target channel vectors on the jth subband of the i-th CSI feedback period.
  20. 如权利要求5、13或19所述的方法，其特征在于，The method of claim 5, 13 or 19, wherein,
    所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数。The S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the information of the auxiliary feedback subband in the at least one auxiliary feedback subband occupies less bits than the at least one main feedback subband The number of bits occupied by the information of the main feedback subband in the subband.
  21. 如权利要求20所述的方法，其特征在于，所述S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。The method according to claim 20, wherein the primary feedback subband and the secondary feedback subband among the S subbands are configured by a network device through RRC signaling and/or DCI signaling.
  22. 一种信道信息的反馈方法，其特征在于，包括：A channel information feedback method, characterized in that, comprising:
    发端设备根据N个信道状态信息CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈；其中，N为正整数，且N≥2。The originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; wherein, N is a positive integer, and N≥2.
  23. 如权利要求22所述的方法，其特征在于，所述CSI相关性包括CSI时域相关性和/或CSI频域相关性。The method according to claim 22, wherein the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  24. 如权利要求22或23所述的方法，其特征在于，所述发端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，包括：The method according to claim 22 or 23, wherein the originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles, including:
    所述发端设备通过第一发端神经网络分别对所述N个CSI反馈周期中的K个CSI反馈周期的信道向量进行编码，得到K条比特流；以及所述发端设备不对所述N个CSI反馈周期中除所述K个CSI反馈周期之外的CSI反馈周期的信道向量进行编码；The originating device encodes the channel vectors of the K CSI feedback periods in the N CSI feedback periods respectively through the first originating neural network to obtain K bit streams; and the originating device does not feedback the N CSI feedback The channel vectors of the CSI feedback cycles other than the K CSI feedback cycles in the cycle are encoded;
    所述发端设备分别向收端设备发送所述K条比特流。The originating device sends the K bit streams to the receiving device respectively.
  25. 如权利要求24所述的方法，其特征在于，所述K条比特流中的比特流包括S个子带的信息， 所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The method according to claim 24, wherein the bit streams in the K bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, Wherein, the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is a positive integer , and S>1.
  26. 如权利要求24或25所述的方法，其特征在于，所述K个CSI反馈周期为所述N个CSI反馈周期中的前K个连续的CSI反馈周期。The method according to claim 24 or 25, wherein the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  27. 如权利要求24至26中任一项所述的方法，其特征在于，A method according to any one of claims 24 to 26, wherein,
    K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。The values of K and N are determined from G group {K, N}, G is a positive integer, and G≥2.
  28. 如权利要求27所述的方法，其特征在于，The method of claim 27, wherein,
    K和N的取值是根据信道场景从所述G组{K，N}中确定的。The values of K and N are determined from the G group {K, N} according to the channel scenario.
  29. 如权利要求27或28所述的方法，其特征在于，所述G组{K，N}是网络设备通过无线资源控制RRC信令或下行控制信息DCI信令配置的。The method according to claim 27 or 28, wherein the G group {K, N} is configured by the network device through radio resource control RRC signaling or downlink control information DCI signaling.
  30. 如权利要求27至29中任一项所述的方法，其特征在于，所述G组{K，N}是网络设备通过RRC信令和/或DCI信令中的
    Figure PCTCN2021093689-appb-100003
    个比特配置的，其中，
    Figure PCTCN2021093689-appb-100004
    表示向上取整。     The method according to any one of claims 27 to 29, characterized in that, the G group {K, N} is the network equipment through RRC signaling and/or DCI signaling
    Figure PCTCN2021093689-appb-100003
    bit configuration, where,
    Figure PCTCN2021093689-appb-100004
    Indicates rounding up.
  31. 如权利要求22或23所述的方法，其特征在于，所述发端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，包括：The method according to claim 22 or 23, wherein the originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles, including:
    所述发端设备通过第二发端神经网络分别对所述N个CSI反馈周期中的P个主CSI反馈周期的信道向量进行编码，得到P条比特流；The originating device respectively encodes the channel vectors of the P main CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain P bit streams;
    所述发端设备通过所述第二发端神经网络分别对所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量进行编码，得到Q条比特流；The originating device respectively encodes the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;
    所述发端设备分别向收端设备发送所述P条比特流和所述Q条比特流；其中，P和Q均为正整数，且P+Q＝N。The transmitting device sends the P bit streams and the Q bit streams to the receiving device respectively; wherein, both P and Q are positive integers, and P+Q=N.
  32. 如权利要求31所述的方法，其特征在于，所述P条比特流中的比特流包括S个子带的信息，所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The method according to claim 31, wherein the bit streams in the P bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, Wherein, the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is a positive integer , and S>1.
  33. 如权利要求31或32所述的方法，其特征在于，A method as claimed in claim 31 or 32, characterized in that,
    所述Q条比特流中的一条比特流占用的比特数小于所述P条比特流中的一条比特流占用的比特数。The number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  34. 如权利要求33所述的方法，其特征在于，所述Q条比特流中的不同的比特流占用的比特数不同，或者，所述Q条比特流中的不同的比特流占用的比特数相同。The method according to claim 33, wherein the number of bits occupied by different bit streams in the Q bit streams is different, or the number of bits occupied by different bit streams in the Q bit streams is the same .
  35. 如权利要求31至34中任一项所述的方法，其特征在于，所述N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。The method according to any one of claims 31 to 34, wherein one primary CSI feedback cycle in the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  36. 如权利要求31至35中任一项所述的方法，其特征在于，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。The method according to any one of claims 31 to 35, wherein the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles in the N CSI feedback cycles is the same, or the N CSI feedback cycles In the feedback cycle, different primary CSI feedback cycles are accompanied by different numbers of secondary CSI feedback cycles.
  37. 如权利要求31至36中任一项所述的方法，其特征在于，所述N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。The method according to any one of claims 31 to 36, wherein the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are implemented by network equipment through RRC signaling and/or DCI signaling configured.
  38. 如权利要求22或23所述的方法，其特征在于，所述发端设备根据N个CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈，包括：The method according to claim 22 or 23, wherein the originating device performs CSI feedback according to the CSI correlation between different CSI feedback cycles in the N CSI feedback cycles, including:
    所述发端设备通过第三发端神经网络分别对所述N个CSI反馈周期的信道向量进行编码，得到N条比特流；The originating device respectively encodes the channel vectors of the N CSI feedback cycles through a third originating neural network to obtain N bit streams;
    所述发端设备分别向收端设备发送所述N条比特流。The originating device sends the N bit streams to the receiving device respectively.
  39. 如权利要求38所述的方法，其特征在于，所述N条比特流中的比特流包括S个子带的信息，所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The method according to claim 38, wherein the bit streams in the N bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband, Wherein, the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is a positive integer , and S>1.
  40. 如权利要求25、31或39所述的方法，其特征在于，所述S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。The method according to claim 25, 31 or 39, wherein the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  41. 一种收端设备，其特征在于，包括：A receiving device, characterized in that it includes:
    处理单元，用于根据N个信道状态信息CSI反馈周期中不同CSI反馈周期之间的CSI相关性，获取所述N个CSI反馈周期的目标信道向量；其中，N为正整数，且N≥2。A processing unit, configured to acquire target channel vectors for the N CSI feedback cycles according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; where N is a positive integer, and N≥2 .
  42. 如权利要求41所述的收端设备，其特征在于，所述CSI相关性包括CSI时域相关性和/或 CSI频域相关性。The receiving end device according to claim 41, wherein the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  43. 如权利要求41或42所述的收端设备，其特征在于，The terminal device according to claim 41 or 42, characterized in that,
    所述收端设备包括通信单元，其中，The receiving device includes a communication unit, wherein,
    所述通信单元用于接收发端设备发送的K条比特流，所述K条比特流分别是由所述N个CSI反馈周期中的K个CSI反馈周期的信道向量经编码之后得到的，K为正整数，且K＜N；The communication unit is configured to receive K bit streams sent by the originating device, the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback cycles in the N CSI feedback cycles, and K is Positive integer, and K<N;
    所述处理单元用于分别对所述K条比特流进行解码，得到所述K个CSI反馈周期的K个目标信道向量；The processing unit is configured to respectively decode the K bit streams to obtain K target channel vectors of the K CSI feedback cycles;
    所述处理单元用于通过第一收端神经网络对所述K个目标信道向量进行预测，得到所述N个CSI反馈周期中除所述K个CSI反馈周期之外的CSI反馈周期的N-K个目标信道向量。The processing unit is configured to predict the K target channel vectors through the first receiving-end neural network, and obtain N-K CSI feedback cycles other than the K CSI feedback cycles among the N CSI feedback cycles Target channel vector.
  44. 如权利要求43所述的收端设备，其特征在于，所述处理单元具体用于：The receiving end device according to claim 43, wherein the processing unit is specifically used for:
    通过第二收端神经网络分别对所述K条比特流进行解码，得到所述K个目标信道向量。The K bit streams are respectively decoded by the second receiving-end neural network to obtain the K target channel vectors.
  45. 如权利要求44所述的收端设备，其特征在于，所述K条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The receiving end device according to claim 44, wherein the bit streams in the K bit streams include information of S subbands, S is a positive integer, and S>1;
    所述处理单元具体用于：The processing unit is specifically used for:
    通过所述第二收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第二收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤K，1≤j≤S，L＜i；Decoding from the bit stream on the jth subband of the i-Lth CSI feedback period to the bitstream on the jth subband of the ith CSI feedback period through the second receiving end neural network, and through the said first The neural network at the receiving end decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, Both j and L are positive integers, and 1≤i≤K, 1≤j≤S, L<i;
    根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述K个目标信道向量。Acquire the K target channel vectors according to the target channel vectors on the j th subband of the i th CSI feedback cycle.
  46. 如权利要求43至45中任一项所述的收端设备，其特征在于，所述K个CSI反馈周期为所述N个CSI反馈周期中的前K个连续的CSI反馈周期。The receiving end device according to any one of claims 43 to 45, wherein the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  47. 如权利要求43至46中任一项所述的收端设备，其特征在于，The terminal device according to any one of claims 43 to 46, characterized in that,
    K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。The values of K and N are determined from G group {K, N}, G is a positive integer, and G≥2.
  48. 如权利要求47所述的收端设备，其特征在于，The receiving end device as claimed in claim 47, characterized in that,
    K和N的取值是根据信道场景从所述G组{K，N}中确定的。The values of K and N are determined from the G group {K, N} according to the channel scenario.
  49. 如权利要求47或48所述的收端设备，其特征在于，所述G组{K，N}是网络设备通过无线资源控制RRC信令和/或下行控制信息DCI信令配置的。The receiving end device according to claim 47 or 48, wherein the G group {K, N} is configured by the network device through radio resource control RRC signaling and/or downlink control information DCI signaling.
  50. 如权利要求47至49中任一项所述的收端设备，其特征在于，所述G组{K，N}是网络设备通过RRC信令或DCI信令中的
    Figure PCTCN2021093689-appb-100005
    个比特配置的，其中，
    Figure PCTCN2021093689-appb-100006
    表示向上取整。     The receiving device according to any one of claims 47 to 49, characterized in that, the G group {K, N} is the network device through RRC signaling or DCI signaling
    Figure PCTCN2021093689-appb-100005
    bit configuration, where,
    Figure PCTCN2021093689-appb-100006
    Indicates rounding up.
  51. 如权利要求41或42所述的收端设备，其特征在于，The terminal device according to claim 41 or 42, characterized in that,
    所述收端设备包括通信单元，其中，The receiving device includes a communication unit, wherein,
    所述通信单元用于接收发端设备发送的P条比特流和Q条比特流；其中，所述P条比特流分别是由所述N个CSI反馈周期中的P个主CSI反馈周期的信道向量经编码之后得到的，所述Q条比特流分别是由所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量经编码之后得到的，或者，所述Q条比特流分别是由所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量与对应的主CSI反馈周期的信道向量的差值经编码之后得到的，P和Q均为正整数，且P+Q＝N；The communication unit is configured to receive P bit streams and Q bit streams sent by the originating device; wherein, the P bit streams are respectively channel vectors of P main CSI feedback cycles in the N CSI feedback cycles obtained after encoding, the Q bit streams are respectively obtained by encoding the channel vectors of the Q secondary CSI feedback cycles in the N CSI feedback cycles, or the Q bit streams are respectively obtained by The difference between the channel vectors of the Q auxiliary CSI feedback periods in the N CSI feedback periods and the channel vector of the corresponding main CSI feedback period is obtained after encoding, P and Q are both positive integers, and P+Q= N;
    所述处理单元用于分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量；The processing unit is configured to respectively decode the P bit streams to obtain P target channel vectors of the P main CSI feedback cycles;
    所述处理单元用于通过第三收端神经网络分别对所述Q条比特流中的第一比特流和所述P条比特流中的第二比特流进行解码，得到所述Q个辅CSI反馈周期的Q个目标信道向量；其中，所述第一比特流对应的辅CSI反馈周期为所述第二比特流对应的主CSI反馈周期伴随的辅CSI反馈周期。The processing unit is configured to respectively decode the first bit stream in the Q bit streams and the second bit stream in the P bit streams through a third receiving-end neural network to obtain the Q auxiliary CSI Q target channel vectors for the feedback cycle; wherein, the secondary CSI feedback cycle corresponding to the first bit stream is the secondary CSI feedback cycle accompanying the primary CSI feedback cycle corresponding to the second bit stream.
  52. 如权利要求51所述的收端设备，其特征在于，所述处理单元具体用于：The receiving end device according to claim 51, wherein the processing unit is specifically used for:
    通过第四收端神经网络分别对所述P条比特流进行解码，得到所述P个主CSI反馈周期的P个目标信道向量。The P bit streams are respectively decoded by the fourth receiving-end neural network to obtain P target channel vectors of the P main CSI feedback periods.
  53. 如权利要求52所述的收端设备，其特征在于，所述P条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The receiving end device according to claim 52, wherein the bit streams in the P bit streams include information of S subbands, S is a positive integer, and S>1;
    所述处理单元具体用于：The processing unit is specifically used for:
    通过所述第四收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第四收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤P，1≤j≤S，L＜i；根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述P个主CSI反馈周期的P个目标信道向量。Decoding from the bit stream on the jth subband of the i-Lth CSI feedback period to the bitstream on the jth subband of the ith CSI feedback period through the fourth receiving end neural network, and through the said first The four-receiving-end neural network decodes the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle, and obtains the target channel vector on the j-th sub-band of the i-th CSI feedback cycle, i, Both j and L are positive integers, and 1≤i≤P, 1≤j≤S, L<i; according to the target channel vector on the j-th subband of the i-th CSI feedback cycle, obtain the P P target channel vectors for the main CSI feedback period.
  54. 如权利要求51至53中任一项所述的收端设备，其特征在于，The terminal device according to any one of claims 51 to 53, characterized in that,
    所述Q条比特流中的一条比特流占用的比特数小于所述P条比特流中的一条比特流占用的比特数。The number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  55. 如权利要求54所述的收端设备，其特征在于，所述Q条比特流中的不同的比特流占用的比特数不同，或者，所述Q条比特流中的不同的比特流占用的比特数相同。The receiving end device according to claim 54, wherein the number of bits occupied by different bit streams in the Q bit streams is different, or the bits occupied by different bit streams in the Q bit streams same number.
  56. 如权利要求51至55中任一项所述的收端设备，其特征在于，所述N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。The receiving device according to any one of claims 51 to 55, wherein one primary CSI feedback cycle in the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  57. 如权利要求51至56中任一项所述的收端设备，其特征在于，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。The receiving end device according to any one of claims 51 to 56, wherein the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles among the N CSI feedback cycles is the same, or, the N The number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles in one CSI feedback cycle is different.
  58. 如权利要求51至57中任一项所述的收端设备，其特征在于，所述N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。The receiving end device according to any one of claims 51 to 57, wherein the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are implemented by the network device through RRC signaling and/or DCI signaling configuration.
  59. 如权利要求41或42所述的收端设备，其特征在于，The terminal device according to claim 41 or 42, characterized in that,
    所述收端设备包括通信单元，其中，The receiving device includes a communication unit, wherein,
    所述通信单元用于接收发端设备发送的N条比特流；其中，所述N条比特流中的比特流包括S个子带的信息，S为正整数，S＞1；The communication unit is configured to receive N bit streams sent by the originating device; wherein, the bit streams in the N bit streams include information of S subbands, S is a positive integer, and S>1;
    所述处理单元用于通过第五收端神经网络对从第i-L个CSI反馈周期的第j个子带上的比特流至第i个CSI反馈周期的第j个子带上的比特流进行解码，以及通过所述第五收端神经网络对第i个CSI反馈周期内从第一个子带至第S个子带的比特流进行解码，得到第i个CSI反馈周期的第j个子带上的目标信道向量，i、j、L均为正整数，且1≤i≤N，1≤j≤S，L＜i；The processing unit is configured to decode the bit stream from the jth subband of the i-L CSI feedback period to the jth subband of the ith CSI feedback period through the fifth receiving end neural network, and Decode the bit stream from the first sub-band to the S-th sub-band in the i-th CSI feedback cycle through the fifth receiving-end neural network to obtain the target channel on the j-th sub-band of the i-th CSI feedback cycle Vector, i, j, L are all positive integers, and 1≤i≤N, 1≤j≤S, L<i;
    所述处理单元用于根据所述第i个CSI反馈周期的第j个子带上的目标信道向量，获取所述N个CSI反馈周期的目标信道向量。The processing unit is configured to acquire the target channel vectors of the N CSI feedback periods according to the target channel vectors on the jth subband of the i-th CSI feedback period.
  60. 如权利要求45、53或59所述的收端设备，其特征在于，The terminal device according to claim 45, 53 or 59, characterized in that,
    所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数。The S subbands include at least one main feedback subband and at least one auxiliary feedback subband, wherein the information of the auxiliary feedback subband in the at least one auxiliary feedback subband occupies less bits than the at least one main feedback subband The number of bits occupied by the information of the main feedback subband in the subband.
  61. 如权利要求60所述的收端设备，其特征在于，所述S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。The receiving end device according to claim 60, wherein the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  62. 一种发端设备，其特征在于，包括：An originating device, characterized in that it includes:
    处理单元，用于根据N个信道状态信息CSI反馈周期中不同CSI反馈周期之间的CSI相关性进行CSI反馈；其中，N为正整数，且N≥2。The processing unit is configured to perform CSI feedback according to the CSI correlation between different CSI feedback cycles in the N channel state information CSI feedback cycles; wherein, N is a positive integer, and N≥2.
  63. 如权利要求62所述的发端设备，其特征在于，所述CSI相关性包括CSI时域相关性和/或CSI频域相关性。The originating device according to claim 62, wherein the CSI correlation includes CSI time domain correlation and/or CSI frequency domain correlation.
  64. 如权利要求62或63所述的发端设备，其特征在于，The originating device according to claim 62 or 63, wherein,
    所述发端设备还包括通信单元，其中，The originating device also includes a communication unit, wherein,
    所述处理单元用于通过第一发端神经网络分别对所述N个CSI反馈周期中的K个CSI反馈周期的信道向量进行编码，得到K条比特流；以及所述处理单元不对所述N个CSI反馈周期中除所述K个CSI反馈周期之外的CSI反馈周期的信道向量进行编码；The processing unit is configured to respectively encode the channel vectors of K CSI feedback cycles in the N CSI feedback cycles through the first sending-end neural network to obtain K bit streams; and the processing unit does not encode the N CSI feedback cycles In the CSI feedback cycle, the channel vectors of the CSI feedback cycles other than the K CSI feedback cycles are encoded;
    所述通信单元用于分别向收端设备发送所述K条比特流。The communication unit is configured to respectively send the K bit streams to the receiving device.
  65. 如权利要求64所述的发端设备，其特征在于，所述K条比特流中的比特流包括S个子带的信息，所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The transmitting device according to claim 64, wherein the bit streams in the K bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband , wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is positive Integer, and S>1.
  66. 如权利要求64或65所述的发端设备，其特征在于，所述K个CSI反馈周期为所述N个CSI反馈周期中的前K个连续的CSI反馈周期。The transmitting device according to claim 64 or 65, wherein the K CSI feedback cycles are the first K consecutive CSI feedback cycles in the N CSI feedback cycles.
  67. 如权利要求64至66中任一项所述的发端设备，其特征在于，The originating device according to any one of claims 64 to 66, wherein,
    K和N的取值是从G组{K，N}中确定的，G为正整数，且G≥2。The values of K and N are determined from G group {K, N}, G is a positive integer, and G≥2.
  68. 如权利要求67所述的发端设备，其特征在于，The originating device of claim 67, wherein,
    K和N的取值是根据信道场景从所述G组{K，N}中确定的。The values of K and N are determined from the G group {K, N} according to the channel scenario.
  69. 如权利要求67或68所述的发端设备，其特征在于，所述G组{K，N}是网络设备通过无线资源控制RRC信令或下行控制信息DCI信令配置的。The originating device according to claim 67 or 68, wherein the G group {K, N} is configured by the network device through radio resource control RRC signaling or downlink control information DCI signaling.
  70. 如权利要求67至69中任一项所述的发端设备，其特征在于，所述G组{K，N}是网络设备 通过RRC信令和/或DCI信令中的
    Figure PCTCN2021093689-appb-100007
    个比特配置的，其中，
    Figure PCTCN2021093689-appb-100008
    表示向上取整。     The originating device according to any one of claims 67 to 69, wherein the G group {K, N} is the network device through RRC signaling and/or DCI signaling
    Figure PCTCN2021093689-appb-100007
    bit configuration, where,
    Figure PCTCN2021093689-appb-100008
    Indicates rounding up.
  71. 如权利要求62或63所述的发端设备，其特征在于，The originating device according to claim 62 or 63, wherein,
    所述发端设备还包括通信单元，其中，The originating device also includes a communication unit, wherein,
    所述处理单元用于通过第二发端神经网络分别对所述N个CSI反馈周期中的P个主CSI反馈周期的信道向量进行编码，得到P条比特流；The processing unit is configured to respectively encode the channel vectors of the P main CSI feedback cycles in the N CSI feedback cycles through the second sending-end neural network to obtain P bit streams;
    所述处理单元用于通过所述第二发端神经网络分别对所述N个CSI反馈周期中的Q个辅CSI反馈周期的信道向量进行编码，得到Q条比特流；The processing unit is configured to respectively encode the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods through the second transmitting-end neural network to obtain Q bit streams;
    所述通信单元用于分别向收端设备发送所述P条比特流和所述Q条比特流；其中，P和Q均为正整数，且P+Q＝N。The communication unit is configured to respectively send the P bit streams and the Q bit streams to the receiving device; wherein, both P and Q are positive integers, and P+Q=N.
  72. 如权利要求71所述的发端设备，其特征在于，所述P条比特流中的比特流包括S个子带的信息，所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The transmitting device according to claim 71, wherein the bit streams in the P bit streams include information of S subbands, and the S subbands include at least one primary feedback subband and at least one auxiliary feedback subband , wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is positive Integer, and S>1.
  73. 如权利要求71或72所述的发端设备，其特征在于，The originating device according to claim 71 or 72, wherein,
    所述Q条比特流中的一条比特流占用的比特数小于所述P条比特流中的一条比特流占用的比特数。The number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
  74. 如权利要求73所述的发端设备，其特征在于，所述Q条比特流中的不同的比特流占用的比特数不同，或者，所述Q条比特流中的不同的比特流占用的比特数相同。The transmitting device according to claim 73, wherein the number of bits occupied by different bit streams in the Q bit streams is different, or the number of bits occupied by different bit streams in the Q bit streams same.
  75. 如权利要求71至74中任一项所述的发端设备，其特征在于，所述N个CSI反馈周期中的一个主CSI反馈周期伴随有一个或多个辅CSI反馈周期。The originating device according to any one of claims 71 to 74, wherein one primary CSI feedback cycle in the N CSI feedback cycles is accompanied by one or more secondary CSI feedback cycles.
  76. 如权利要求71至75中任一项所述的发端设备，其特征在于，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量相同，或者，所述N个CSI反馈周期中不同的主CSI反馈周期伴随的辅CSI反馈周期的数量不同。The transmitting device according to any one of claims 71 to 75, wherein the number of secondary CSI feedback cycles accompanied by different primary CSI feedback cycles in the N CSI feedback cycles is the same, or the N CSI feedback cycles In the CSI feedback cycle, different primary CSI feedback cycles are accompanied by different numbers of secondary CSI feedback cycles.
  77. 如权利要求71至76中任一项所述的发端设备，其特征在于，所述N个CSI反馈周期中的主CSI反馈周期和辅CSI反馈周期是网络设备通过RRC信令和/或DCI信令配置的。The originating device according to any one of claims 71 to 76, wherein the primary CSI feedback cycle and the secondary CSI feedback cycle among the N CSI feedback cycles are implemented by the network device through RRC signaling and/or DCI signaling. command configuration.
  78. 如权利要求62或63所述的发端设备，其特征在于，The originating device according to claim 62 or 63, wherein,
    所述发端设备还包括通信单元，其中，The originating device also includes a communication unit, wherein,
    所述处理单元用于通过第三发端神经网络分别对所述N个CSI反馈周期的信道向量进行编码，得到N条比特流；The processing unit is configured to respectively encode the channel vectors of the N CSI feedback cycles through the third sending-end neural network to obtain N bit streams;
    所述通信单元用于分别向收端设备发送所述N条比特流。The communication unit is configured to respectively send the N bit streams to the receiving device.
  79. 如权利要求78所述的发端设备，其特征在于，所述N条比特流中的比特流包括S个子带的信息，所述S个子带包括至少一个主反馈子带和至少一个辅反馈子带，其中，所述至少一个辅反馈子带中的辅反馈子带的信息所占用的比特数小于所述至少一个主反馈子带中的主反馈子带的信息所占用的比特数，S为正整数，且S＞1。The transmitting device according to claim 78, wherein the bit streams in the N bit streams include information of S subbands, and the S subbands include at least one main feedback subband and at least one auxiliary feedback subband , wherein the number of bits occupied by the information of the auxiliary feedback subband in the at least one auxiliary feedback subband is smaller than the number of bits occupied by the information of the main feedback subband in the at least one main feedback subband, and S is positive Integer, and S>1.
  80. 如权利要求65、71或79所述的发端设备，其特征在于，所述S个子带中的主反馈子带和辅反馈子带是网络设备通过RRC信令和/或DCI信令配置的。The originating device according to claim 65, 71 or 79, wherein the primary feedback subband and the secondary feedback subband among the S subbands are configured by the network device through RRC signaling and/or DCI signaling.
  81. 一种收端设备，其特征在于，包括：处理器和存储器，该存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，执行如权利要求1至21中任一项所述的方法。A receiving device, characterized in that it includes: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute the computer program as claimed in claims 1 to 21 any one of the methods described.
  82. 一种发端设备，其特征在于，包括：处理器和存储器，该存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，执行如权利要求22至40中任一项所述的方法。An originating device, characterized by comprising: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute any of claims 22 to 40. one of the methods described.
  83. 一种芯片，其特征在于，包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有所述芯片的设备执行如权利要求1至21中任一项所述的方法。A chip, characterized by comprising: a processor, configured to call and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 1 to 21.
  84. 一种芯片，其特征在于，包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有所述芯片的设备执行如权利要求22至40中任一项所述的方法。A chip, characterized by comprising: a processor, configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 22 to 40.
  85. 一种计算机可读存储介质，其特征在于，用于存储计算机程序，所述计算机程序使得计算机执行如权利要求1至21中任一项所述的方法。A computer-readable storage medium, characterized in that it is used to store a computer program, the computer program causes a computer to execute the method according to any one of claims 1 to 21.
  86. 一种计算机可读存储介质，其特征在于，用于存储计算机程序，所述计算机程序使得计算机执行如权利要求22至40中任一项所述的方法。A computer-readable storage medium, characterized by being used for storing a computer program, the computer program causes a computer to execute the method according to any one of claims 22 to 40.
  87. 一种计算机程序产品，其特征在于，包括计算机程序指令，该计算机程序指令使得计算机执行如权利要求1至21中任一项所述的方法。A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method according to any one of claims 1 to 21.
  88. 一种计算机程序产品，其特征在于，包括计算机程序指令，该计算机程序指令使得计算机执行如权利要求22至40中任一项所述的方法。A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method according to any one of claims 22 to 40.
  89. 一种计算机程序，其特征在于，所述计算机程序使得计算机执行如权利要求1至21中任一项所述的方法。A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 1-21.
  90. 一种计算机程序，其特征在于，所述计算机程序使得计算机执行如权利要求22至40中任一项所述的方法。A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 22-40.
PCT/CN2021/093689 2021-05-13 2021-05-13 Channel information feedback method, receiving end device, and transmitting end device WO2022236785A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2021/093689 WO2022236785A1 (en) 2021-05-13 2021-05-13 Channel information feedback method, receiving end device, and transmitting end device
CN202180094787.0A CN116941198A (en) 2021-05-13 2021-05-13 Feedback method of channel information, receiving end equipment and transmitting end equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/093689 WO2022236785A1 (en) 2021-05-13 2021-05-13 Channel information feedback method, receiving end device, and transmitting end device

Publications (1)

Publication Number Publication Date
WO2022236785A1 true WO2022236785A1 (en) 2022-11-17

Family

ID=84027930

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/093689 WO2022236785A1 (en) 2021-05-13 2021-05-13 Channel information feedback method, receiving end device, and transmitting end device

Country Status (2)

Country Link
CN (1) CN116941198A (en)
WO (1) WO2022236785A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230189030A1 (en) * 2021-12-14 2023-06-15 Lenovo (Singapore) Pte. Ltd. Configuring an artificial intelligence based framework

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018202055A1 (en) * 2017-05-02 2018-11-08 Mediatek Inc. Overhead reduction for linear combination codebook and feedback mechanism in mobile communications
CN111201722A (en) * 2017-10-09 2020-05-26 上海诺基亚贝尔股份有限公司 Method and apparatus for frequency domain omission of sub-band channel state information reporting
CN112470412A (en) * 2018-08-30 2021-03-09 上海诺基亚贝尔股份有限公司 Frequency domain time domain channel hardening and overhead reduction
CN112564757A (en) * 2020-12-03 2021-03-26 西华大学 Deep learning 1-bit compression superposition channel state information feedback method
CN112671505A (en) * 2019-10-16 2021-04-16 维沃移动通信有限公司 Encoding method, decoding method and device
CN112737985A (en) * 2020-12-25 2021-04-30 东南大学 Large-scale MIMO channel joint estimation and feedback method based on deep learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018202055A1 (en) * 2017-05-02 2018-11-08 Mediatek Inc. Overhead reduction for linear combination codebook and feedback mechanism in mobile communications
CN111201722A (en) * 2017-10-09 2020-05-26 上海诺基亚贝尔股份有限公司 Method and apparatus for frequency domain omission of sub-band channel state information reporting
CN112470412A (en) * 2018-08-30 2021-03-09 上海诺基亚贝尔股份有限公司 Frequency domain time domain channel hardening and overhead reduction
CN112671505A (en) * 2019-10-16 2021-04-16 维沃移动通信有限公司 Encoding method, decoding method and device
CN112564757A (en) * 2020-12-03 2021-03-26 西华大学 Deep learning 1-bit compression superposition channel state information feedback method
CN112737985A (en) * 2020-12-25 2021-04-30 东南大学 Large-scale MIMO channel joint estimation and feedback method based on deep learning

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230189030A1 (en) * 2021-12-14 2023-06-15 Lenovo (Singapore) Pte. Ltd. Configuring an artificial intelligence based framework

Also Published As

Publication number Publication date
CN116941198A (en) 2023-10-24

Similar Documents

Publication Publication Date Title
CN114614955A (en) Method and device for transmitting data
WO2022236785A1 (en) Channel information feedback method, receiving end device, and transmitting end device
CN109889247B (en) Low-overhead dynamic feedback safe transmission method and system suitable for narrow-band Internet of things
WO2022217506A1 (en) Channel information feedback method, sending end device, and receiving end device
WO2023004638A1 (en) Channel information feedback methods, transmitting end devices, and receiving end devices
WO2023015499A1 (en) Wireless communication method and device
WO2023028948A1 (en) Model processing method, electronic device, network device, and terminal device
EP4398527A1 (en) Model processing method, electronic device, network device, and terminal device
WO2024020793A1 (en) Channel state information (csi) feedback method, terminal device and network device
WO2023004563A1 (en) Method for obtaining reference signal and communication devices
WO2023133886A1 (en) Channel information feedback method, sending end device, and receiving end device
WO2024046288A1 (en) Communication method and apparatus
WO2022236788A1 (en) Communication method and device, and storage medium
WO2024108356A1 (en) Csi feedback method, transmitter device and receiver device
WO2024077621A1 (en) Channel information feedback method, transmitting end device, and receiving end device
WO2024008004A1 (en) Communication method and apparatus
US20230354096A1 (en) Binary variational (biv) csi coding
US20240072927A1 (en) Signal processing method, communication device, and communication system
WO2024098259A1 (en) Sample set generation method and device
WO2022257042A1 (en) Codebook reporting method, and terminal device and network device
WO2023115254A1 (en) Data processing method and device
WO2022267633A1 (en) Information transmission method and apparatus
WO2023116407A1 (en) Information processing method and apparatus, terminal, and network device
WO2022257121A1 (en) Communication method and device, and storage medium
WO2023283785A1 (en) Method for processing signal, and receiver

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21941356

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202180094787.0

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21941356

Country of ref document: EP

Kind code of ref document: A1