WO2023179473A1 - 信道特征信息上报及恢复方法、终端和网络侧设备 - Google Patents

信道特征信息上报及恢复方法、终端和网络侧设备 Download PDF

Info

Publication number
WO2023179473A1
WO2023179473A1 PCT/CN2023/082127 CN2023082127W WO2023179473A1 WO 2023179473 A1 WO2023179473 A1 WO 2023179473A1 CN 2023082127 W CN2023082127 W CN 2023082127W WO 2023179473 A1 WO2023179473 A1 WO 2023179473A1
Authority
WO
WIPO (PCT)
Prior art keywords
channel
characteristic information
information
channel characteristic
length
Prior art date
Application number
PCT/CN2023/082127
Other languages
English (en)
French (fr)
Inventor
任千尧
孙鹏
Original Assignee
维沃移动通信有限公司
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 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2023179473A1 publication Critical patent/WO2023179473A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • H04L1/0001Systems modifying transmission characteristics according to link quality, e.g. power backoff
    • H04L1/0006Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
    • H04L1/0007Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format by modifying the frame length
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B17/00Monitoring; Testing
    • H04B17/30Monitoring; Testing of propagation channels
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition

Definitions

  • This application belongs to the field of communication technology, and specifically relates to a channel characteristic information reporting and recovery method, terminal and network side equipment.
  • AI network models can be used to encode and decode channel state information (CSI) information.
  • CSI channel state information
  • the degree of compressibility of channel information is different, and the length of information after encoding is also different.
  • simple channel information only requires a short encoding length, but complex channel information requires longer encoding information.
  • the weight parameters and even network structures of the AI network models corresponding to different lengths of coding information are different.
  • Embodiments of the present application provide a channel characteristic information reporting and recovery method, a terminal and a network side device, so that the terminal can adaptively use the same AI network model for encoding according to the length of the channel information, which can reduce the transmission between the terminal and the network side device.
  • the overhead of AI network models are described below.
  • a method for reporting channel characteristic information is provided, which is applied to terminals.
  • the method includes:
  • the terminal uses the target AI network model to process the target channel information into a first channel of the first length. feature information;
  • the terminal sends second channel characteristic information to the network side device, where the second channel characteristic information is part of the first channel characteristic information.
  • a device for reporting channel characteristic information which is applied to a terminal.
  • the device includes:
  • the first processing module is used to process the target channel information into first channel characteristic information of the first length using the target AI network model
  • the first sending module is configured to send second channel characteristic information to the network side device, where the second channel characteristic information is part of the first channel characteristic information.
  • a channel characteristic information recovery method is provided, which is applied to network side equipment.
  • the method includes:
  • the network side device receives the second channel characteristic information from the terminal, wherein the second channel characteristic information includes part of the first channel characteristic information, and the first channel characteristic information is the target channel adopted by the terminal using the target AI network model.
  • the first length of channel characteristic information obtained by processing the information
  • the network side device uses the first AI network model to process the second channel characteristic information to obtain the target channel information.
  • a device for recovering channel characteristic information which is applied to network side equipment.
  • the device includes:
  • the second receiving module is configured to receive second channel characteristic information from the terminal, wherein the second channel characteristic information includes part of the first channel characteristic information, and the first channel characteristic information is the target AI network adopted by the terminal.
  • the first length of channel characteristic information obtained by processing the target channel information by the model;
  • the second processing module is configured to use the first AI network model to process the second channel characteristic information to obtain the target channel information.
  • a terminal in a fifth aspect, includes a processor and a memory.
  • the memory stores programs or instructions that can be run on the processor.
  • the program or instructions are executed by the processor, the following implementations are implemented: The steps of the method described in one aspect.
  • a terminal including a processor and a communication interface, wherein the processing The processor is used to process the target channel information into first channel characteristic information of a first length using the target AI network model, and the communication interface is used to send the second channel characteristic information to the network side device, and the second channel characteristic information is the first channel characteristic information. part of the message.
  • a network side device in a seventh aspect, includes a processor and a memory.
  • the memory stores programs or instructions that can be run on the processor.
  • the program or instructions are executed by the processor.
  • a network side device including a processor and a communication interface, wherein the communication interface is used to receive second channel characteristic information from a terminal, and the second channel characteristic information includes the first channel characteristic information.
  • the first channel characteristic information is the first length of channel characteristic information obtained by the terminal using the target AI network model to process the target channel information; the processor is configured to use the first AI network model to process the third The two channel characteristic information are processed to obtain the target channel information.
  • a ninth aspect provides a communication system, including: a terminal and a network side device.
  • the terminal can be configured to perform the steps of the channel characteristic information reporting method described in the first aspect.
  • the network side device can be configured to perform the steps of the channel characteristic information reporting method as described in the first aspect. The steps of the channel characteristic information recovery method described in the three aspects.
  • a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method are implemented as described in the first aspect. The steps of the method described in the third aspect.
  • a chip in an eleventh aspect, includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement the method described in the first aspect. method, or implement a method as described in the third aspect.
  • a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the first aspect or the second aspect.
  • the terminal uses the target AI network model to process the target channel information into the first channel characteristic information of the first length; the terminal sends the second channel characteristic information to the network side device, and the second channel characteristic information is the first channel characteristic information. Part of the channel characteristic information.
  • the terminal can adaptively use the same AI network model for encoding according to the length of the channel information, and only report part of the channel characteristic information of the corresponding length to the network side device, so that the network side can adopt pre-set
  • the configured AI network model corresponding to the length is used to decode this part of the channel characteristic information, and can reduce the overhead of transmitting the AI network model between the terminal and the network side device.
  • Figure 1 is a schematic structural diagram of a wireless communication system to which embodiments of the present application can be applied;
  • Figure 2 is a flow chart of a method for reporting channel characteristic information provided by an embodiment of the present application
  • Figure 3 is a schematic diagram of the architecture of the neural network model
  • Figure 4 is a schematic diagram of a neuron
  • Figure 5 is a schematic diagram of the power spectrum of the delay path in the embodiment of the present application.
  • Figure 6 is a flow chart of a method for recovering channel characteristic information provided by an embodiment of the present application.
  • Figure 7a is one of the schematic diagrams of the corresponding relationship between the decoder and the channel characteristic information in the embodiment of the present application.
  • Figure 7b is the second schematic diagram of the corresponding relationship between the decoder and the channel characteristic information in the embodiment of the present application.
  • Figure 8 is a schematic structural diagram of a device for reporting channel characteristic information provided by an embodiment of the present application.
  • Figure 9 is a schematic structural diagram of a device for recovering channel characteristic information provided by an embodiment of the present application.
  • Figure 10 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • Figure 11 is a schematic structural diagram of a terminal provided by an embodiment of the present application.
  • Figure 12 is a schematic structural diagram of a network side device provided by an embodiment of the present application.
  • first, second, etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and “second” are distinguished objects It is usually one type, and the number of objects is not limited.
  • the first object can be one or multiple.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the related objects are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced, LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • system and “network” in the embodiments of this application are often used interchangeably, and the described technology can be used not only for the above-mentioned systems and radio technologies, but also for other systems and radio technologies.
  • NR New Radio
  • the following description describes a New Radio (NR) system for example purposes, and NR terminology is used in much of the following description, but these techniques can also be applied to applications other than NR system applications, such as 6th generation Generation, 6G) communication system.
  • 6G 6th generation Generation
  • FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application are applicable.
  • the wireless communication system includes a terminal 11 and a network side device 12.
  • the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, or a super mobile personal computer.
  • Tablet Personal Computer Tablet Personal Computer
  • laptop computer laptop computer
  • PDA Personal Digital Assistant
  • PDA Personal Digital Assistant
  • UMPC ultra-mobile personal computer
  • UMPC mobile Internet device
  • MID mobile Internet device
  • augmented reality augmented reality, AR
  • VR virtual reality
  • robots wearable devices
  • Vehicle user equipment VUE
  • pedestrian terminal pedestrian terminal
  • PUE pedestrian terminal
  • smart home home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.
  • game consoles personal computers (personal computer, PC), teller machine or self-service machine and other terminal-side devices.
  • Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets) bracelets, smart anklets, etc.), smart wristbands, smart clothing, etc.
  • the network side equipment 12 may include access network equipment or core network equipment, where the access network equipment may also be called wireless access network equipment, radio access network (Radio Access Network, RAN), radio access network function or wireless access network unit.
  • Access network equipment can include base stations, Wireless Local Area Network (WLAN) access points or WiFi nodes, etc.
  • WLAN Wireless Local Area Network
  • the base station can be called Node B, Evolved Node B (eNB), access point, base transceiver station ( Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home B-node, home evolved B-node, sending and receiving point ( Transmitting Receiving Point (TRP) or some other suitable term in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiment of this application, only the NR system is used The base station is introduced as an example, and the specific type of base station is not limited.
  • the transmitter can optimize signal transmission based on CSI to better match the channel status.
  • CQI Channel Quality Indicator
  • MCS Modulation and Coding Scheme
  • PMI Precoding Matrix Indicator
  • MIMO Multi-Input Multi-Output
  • the network side device sends CSI reference signals (CSI-Reference Signals, CSI-RS) on certain time-frequency resources of a certain time slot (slot).
  • CSI-RS CSI-Reference Signals
  • the terminal performs channel estimation based on the CSI-RS and calculates the channel on this slot.
  • Information, the PMI is fed back to the base station through the codebook.
  • the network side device combines the channel information based on the codebook information fed back by the terminal. Before the terminal reports the CSI next time, the network side device uses this channel information to perform data precoding and multi-user scheduling. .
  • the terminal can change the PMI reported on each subband to report PMI according to the delay (delay domain, that is, frequency domain). Since the channels in the delay domain are more concentrated, PMI with less delay can be approximated The PMI of all subbands can be regarded as reporting after compressing the delay field information.
  • the network side device can precode the CSI-RS in advance and send the coded CSI-RS to the terminal. What the terminal sees is the channel corresponding to the coded CSI-RS. The terminal only needs to Just select several stronger ports from the ports indicated by the network-side device and report the coefficients corresponding to these ports.
  • AI network models can improve the compression effect of channel feature information.
  • AI network models have many implementation methods, such as: neural networks, decision trees, support vector machines, and Bayesian Classifier etc.
  • the AI network model is a neural network as an example, but the specific type of the AI network model is not limited.
  • the target AI network model with encoding function (that is, the AI network model in the encoder, which can also be called the encoder network model or the encoding AI network model) is used to compress and encode the channel information at the terminal. And report the encoded channel characteristic information to the network side device (for example: base station).
  • the first AI network model with decoding function (that is, the AI network model in the decoder, which can also be called decoding The decoder network model or decoding AI network model) decodes the compressed channel characteristic information to restore the channel information.
  • the first AI network model of the base station and the target AI network model of the terminal need to be jointly trained to achieve a reasonable matching degree.
  • the neural network forms a joint neural network through the encoder network model of the terminal and the decoder network model of the base station, and is jointly trained by the network side device. After the training is completed, the base station sends the encoder network model to the terminal.
  • the terminal estimates the CSI Reference Signal (CSI-RS) and performs calculations based on the estimated channel information to obtain the calculated channel information; then, the calculated channel information or the original estimated channel information is passed through the coding network model Encoding is performed, the encoding result is obtained, and finally the encoding result is sent to the base station.
  • CSI-RS CSI Reference Signal
  • the base station inputs it into the decoding network model and uses the decoding network model to restore the channel information.
  • the degree of compressibility of channel information is different. Therefore, the length of the channel information after encoding is also different. For example, simple channel information only requires a short encoding length, but complex channel information requires a longer length. encoded information. In this way, the weight parameters and even the network structure of the AI network model corresponding to the encoding information of different lengths are different, which requires retraining the AI network model that matches the encoding length. It can be seen that in related technologies, it is necessary to separately train and use the AI network model corresponding to the length of the channel information for each length to encode and decode. This results in the need to transmit multiple data between the terminal and the network side device. An AI network model increases the transmission overhead of the AI network model and the network side device trains and uses it separately for each length of channel information. When encoding and decoding the AI network model corresponding to this length, the calculation amount of the network side device is increased.
  • the terminal can use the target AI network model to process the channel information into fixed-length coded information (i.e., first channel characteristic information), and report part of the first channel characteristic information to the network side device.
  • the terminal may select the second length of the second channel characteristic information to report according to the instructions of the network side device and/or the terminal independently selects the second length of the second channel characteristic information to report to the network side device.
  • the terminal only needs to use one encoding network to encode the channel information, and the network side device only needs to use the decoding network corresponding to the second length to decode part of the channel characteristic information of the second length.
  • the above-mentioned terminal reports the second channel characteristic information to the network side device, and may use the CSI reporting method to carry the second channel characteristic information in the CSI report to report to the network side device, where, The channel characteristic information may specifically be PMI information.
  • the channel characteristic information may specifically be PMI information.
  • the above-mentioned second channel characteristic information can also be reported to the network side device in any other manner.
  • the reporting of the second channel characteristic information in the form of CSI reporting is used as an example for illustration. Does not constitute a specific limitation.
  • first length and the second length in the embodiment of the present application may be the number of bits of the corresponding channel characteristic information after quantization, or the number of coefficients included in the corresponding channel characteristic information before quantization.
  • first length and the second length are respectively the number of bits, as an example, and no specific limitation is constituted here.
  • channel characteristic information reporting method channel characteristic information recovery method, channel characteristic information reporting device, channel characteristic information recovery device and communication equipment provided by the embodiments of the present application will be described in detail through some embodiments and application scenarios. .
  • an embodiment of the present application provides a method for reporting channel characteristic information.
  • the execution subject may be a terminal.
  • the terminal may be various types of terminals 11 listed in Figure 1, or other than those shown in Figure 1. Terminals other than the terminal types listed in the embodiment are not specifically limited here.
  • the channel characteristic information reporting method may include the following steps:
  • Step 201 The terminal uses the target AI network model to process the target channel information into first channel characteristic information of a first length.
  • the above target AI network model may include multiple types of AI algorithm modules, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc., which are not specifically limited here, and for ease of explanation, the following
  • AI algorithm model is a neural network model as an example for illustration, which does not constitute a specific limitation.
  • the neural network model includes an input layer, a hidden layer and an output layer, which can predict possible output results (Y) based on the entry and exit information (X 1 ⁇ X n ) obtained by the input layer.
  • the neural network model consists of a large number of neurons, as shown in Figure 4.
  • K represents the total number of input parameters.
  • the parameters of the neural network are optimized through optimization algorithms.
  • An optimization algorithm is a type of algorithm that can help us minimize or maximize an objective function (sometimes also called a loss function).
  • the objective function is often a mathematical combination of model parameters and data. For example, given the data The difference (f(x)-Y) between it and the true value is the loss function. Our purpose is to find appropriate W and b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the real situation.
  • error back propagation is basically based on error back propagation algorithm.
  • the basic idea of the error back propagation algorithm is that the learning process consists of two processes: forward propagation of signals and back propagation of errors.
  • the input sample is passed in from the input layer, processed layer by layer by each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error backpropagation stage.
  • Error backpropagation is to backpropagate the output error in some form to the input layer layer by layer through the hidden layer, and allocate the error to all units in each layer, thereby obtaining the error signal of each layer unit. This error signal is used as a correction for each unit. The basis for the weight.
  • This process of adjusting the weights of each layer in forward signal propagation and error back propagation is carried out over and over again.
  • the process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until a preset number of learning times.
  • the target AI network model can be used to encode channel information, which can Channel information under different channel environments is encoded into first channel characteristic information of fixed length (ie, first length).
  • first length may be a longer length.
  • any method such as zero padding or redundant coding can be used to supplement the encoding result of the channel information in the channel environment to the first length.
  • the method further includes:
  • the terminal performs channel estimation on the channel state information - reference signal CSI-RS or tracking reference signal (Tracking Reference Signal, TRS) to obtain the target channel information; or,
  • the terminal preprocesses the channel information obtained by channel estimation to obtain the target channel information.
  • the target channel information encoded using the target AI network model may be the channel information obtained by the terminal estimating the CSI-RS channel or the TRS channel, or the terminal performs certain preprocessing on the estimated channel information.
  • the obtained channel information is not specifically limited here.
  • Step 202 The terminal sends second channel characteristic information to the network side device, where the second channel characteristic information is part of the first channel characteristic information.
  • the second channel characteristic information may be a part of the first channel characteristic information: the terminal intercepts part of the first channel characteristic information as the second channel characteristic information.
  • the terminal may send the second bit of the second channel characteristic information to the network side device; or, the terminal may also report the channel characteristic information M times and send M pieces of second channel characteristic information of different lengths or different contents to the network side device.
  • Channel characteristic information that is, in each channel characteristic information reporting process, a piece of second channel characteristic information is reported, but the second channel characteristic information reported through different channel characteristic information reporting processes has different lengths or different contents.
  • the terminal sends second channel characteristic information to the network side device, including:
  • the terminal sends a second length of second channel characteristic information intercepted from the first channel characteristic information to the network side device, and the second length is less than or equal to the first length.
  • the terminal only reports the second channel characteristic information to the network side device, and the length of the second channel characteristic information may be the second length.
  • the second length may be determined according to instructions from the network side device, and/or the terminal determines which second length to adopt.
  • the network side device receives the second channel characteristic information of the second length
  • the first AI network model corresponding to the second length can be used to decode the second channel characteristic information, thereby recovering the channel information.
  • the terminal can report channel characteristic information respectively at different time domain positions, and the second length corresponding to each channel characteristic information report can be the same or different, which is not specifically limited here.
  • the first channel characteristic information of the first length may be divided into K channel characteristic information segments, and the second channel characteristic information of the second length may include 1 to K channel characteristic information segments.
  • the network side device when receiving the second channel characteristic information currently reported by the terminal, can input the second channel characteristic information into the first AI network model, so as to use the first AI network model to The second channel characteristic information is processed to restore the channel information.
  • the network side device can store the historical channel characteristic information reported by the terminal within the historical time, and when receiving the second channel characteristic information currently reported by the terminal, it can update based on the second channel characteristic information. historical channel characteristic information, and then use the first AI network model to process the updated historical channel characteristic information to obtain the target channel information.
  • the terminal reports channel characteristic information cyclically in the order of the second length being N0, N1..., then when the network side device receives the second channel characteristic information of length N0 for the first time, based on the length of N0
  • the second channel characteristic information of length N1 is used to perform channel recovery; then, when the network side device receives the second channel characteristic information of length N1, it performs channel recovery based on the second channel characteristic information of length N0 and the second channel characteristic information of length N1. Channel restored.
  • the network side device receives the second channel characteristic information of length N0, it replaces the second channel characteristic information of length N0 in the historical channel characteristic information based on the second channel characteristic information of length N0.
  • Channel characteristic information and use the updated historical channel characteristic information for channel recovery.
  • the terminal reports the second channel characteristic information with a length of N0 for the first time, then reports the second channel characteristic information with a length of N1-N0 next time, and then reports the second channel characteristic information with a length of N2-N1 next time.
  • the base station uses all the second channel characteristic information for decoding, that is, when there is only the second channel characteristic information of length N0, the second channel characteristic information of length N0 is used; if there are N0 and When the second channel characteristic information of length N1-N0 is provided, The second channel characteristic information of length N1 is combined based on the second channel characteristic information of length N0 and N1-N0, and is decoded based on the second channel characteristic information of length N1, and iterates in sequence until the third channel characteristic information of length L is combined. 1. Channel characteristic information. In the next cycle, the length L is still used for decoding, and the channel characteristic information corresponding to N0 in the historical channel characteristic information is replaced with the new N0, and the iteration is updated accordingly.
  • the target AI network model and the first AI network model can be jointly trained by network-side devices, and one target AI network model can correspond to at least one first AI network model, where each first AI network model have respective corresponding lengths, so that after the second length is determined, the first AI network model corresponding to the second length can be used to decode the second channel characteristic information to achieve channel recovery.
  • the second length of second channel characteristic information includes at least one of the following:
  • N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length
  • N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information are N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information.
  • Option 1 In the case where the second channel characteristic information of the second length includes the first N bits or coefficients in the first channel characteristic information, the terminal directly follows the order of each bit in the first channel characteristic information. To report N bits or coefficients of the second channel characteristic information. For example, assuming that N is equal to 100 bits, the first 100 bits of the first channel characteristic information are reported.
  • Option 2 In the case where the second channel characteristic information of the second length includes N bits or coefficients in the first channel characteristic information whose importance level is greater than a preset level, the N bits or coefficients in the first channel characteristic information may be modified. Each bit or each bit interval or coefficient included is divided into importance levels. In this way, the terminal can preferentially report N bits or coefficients with higher importance levels in the first channel characteristic information to the network side device.
  • Option three In the case where the second channel characteristic information of the second length includes N bits or coefficients in the first channel characteristic information in addition to the reported second channel characteristic information, it is the same as option one. The difference is that when the terminal reports channel characteristic information multiple times, the reporting method of option three can avoid repeated reporting of channel characteristic information. For example: the terminal performs two messages Channel characteristic information is reported. The second length corresponding to the first channel characteristic information report is equal to 100 bits, and the second length corresponding to the second channel characteristic information report is equal to 200 bits.
  • the terminal can report bits 0 to 99 of the first channel characteristic information for the first time, and bits 0 to 199 of the first channel characteristic information for the second time; and when option three is adopted, the terminal can report bits 0 to 99 of the first channel characteristic information for the second time.
  • the 0th to 99th bits in the first channel characteristic information can be reported, and the second time can report the other 200 bits after the 100th bit in the first channel characteristic information.
  • the terminal first The second channel characteristic information reported for the second time may be bits 0 to (N0-1) in the first channel characteristic information
  • the second channel characteristic information reported for the second time may be bits 0 to (N0) in the first channel characteristic information.
  • the second channel characteristic information reported for the second time may include the bit content reported for the first time, and may also include additional N1-N0 length content, and the 0 ⁇ (N0-1) part and N0-(L The length of N1-N0 in -1) may be two segments of channel characteristic information bits that are continuous or discontinuous.
  • the above-mentioned second length may be indicated by the network side device or the second length may be determined by the terminal according to conditions agreed upon in the protocol.
  • the method before the terminal sends the second channel characteristic information of the second length intercepted from the first channel characteristic information to the network side device, the method further includes:
  • the terminal receives first indication information from the network side device, wherein the first indication information indicates the second length and/or a first encoding identifier, and the first encoding identifier and the second length association.
  • the above-mentioned first encoding identifier can be understood as identification information of the encoding length corresponding to the first AI network model. In this way, based on the first coding identifier, it can be determined how much coding length of second channel characteristic information the terminal needs to report.
  • a target AI network model corresponds to K first AI network models
  • the inputs of the K first AI network models are part or all of the channel feature information output by the target AI network model
  • the input length of the K first AI network models are N1, N2 to NK respectively
  • the above-mentioned first encoding identifier may be i or i-1 in Ni.
  • the input length of the K first AI network models may be agreed upon by the protocol, and both the network side device and the terminal know the K first AI network models.
  • the terminal can determine the second length to be reported based on the coding identifier, so that in the first channel characteristic information whose coded length is the first length Intercept a part with length Ni, where i is the first encoding identifier indicated by the network side device.
  • the above-mentioned first indication information is configured by high-level signaling, for example: through Radio Resource Control (Radio Resource Control, RRC) signaling or Media Access Control (Medium Access Control, MAC) Control Element (Control Element, CE), etc.
  • RRC Radio Resource Control
  • MAC Media Access Control
  • CE Control Element
  • the above-mentioned first indication information can also be the indication information in the CSI report configuration (CSI report config), or the network side device can configure each length corresponding to a CSI resource (resource), then the second length indicated by the first indication information can be understood as the length corresponding to the CSI resource used by the terminal, and the first indication information is not specifically limited here.
  • the network side device may indicate the second length to the terminal, so that the terminal intercepts the second channel characteristic information of the corresponding length from the first channel characteristic information according to the instruction of the network side device, and reports it to the network side device.
  • the method before the terminal sends the second channel characteristic information of the second length intercepted from the first channel characteristic information to the network side device, the method further includes:
  • the terminal determines the second length according to at least one of channel characteristics and channel conditions corresponding to the target channel information.
  • the above-mentioned terminal determines the second length according to at least one of channel characteristics and channel conditions corresponding to the target channel information.
  • the terminal may determine the channel characteristics of the target channel according to the target channel information, thereby determining the channel.
  • the second length corresponding to the characteristic; and/or the terminal can determine whether the channel quality of the target channel satisfies the preset channel conditions according to the target channel information, and thereby determine the corresponding second length based on the judgment result.
  • the difference from the embodiment in which the network side device indicates the second length to the terminal is that the terminal can determine the second length according to the target channel information, thereby reporting the second channel characteristics of the second length to the network side device. information.
  • the terminal determines the channel corresponding to the target channel information.
  • Characteristics that determine the second length include:
  • the terminal determines that the length of the value association of the target channel parameter of the target channel corresponding to the target channel information is the second length according to the first association relationship, wherein the first association relationship includes the value of the target channel parameter.
  • the relationship between each value or each value range and length; or,
  • the terminal determines that the length corresponding to the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is the second length according to the second association relationship, wherein the second association relationship includes the The correlation between each value or each value range of the target channel parameter and the coding identifier.
  • the terminal may also determine based on the correlation between the value of the channel parameter and the length or coding identifier. The second length of the target channel parameter association.
  • the target channel parameters of the target channel may include at least one of the following:
  • the target channel is Line of Sight (LOS) propagation or Non-Line of Sight (NLOS) propagation;
  • the number of effective beams of the target channel include beams corresponding to the orthogonal basis of Discrete Fourier Transform (DFT) whose power is greater than the first threshold.
  • DFT Discrete Fourier Transform
  • the channel quality is better than that of non-line-of-sight propagation.
  • Shorter second channel characteristic information can be reported when the target channel is line-of-sight propagation, and when the target channel is line-of-sight propagation, the channel quality is better.
  • the greater the number of effective delay paths of the target channel, the longer the reported second channel characteristic information can be, where the effective delay paths include at least one of the following: the corresponding power or amplitude is greater than the first The delay path of the threshold value, the corresponding delay path of the maximum power or amplitude.
  • the effective delay paths include at least one of the following: the corresponding power or amplitude is greater than the first The delay path of the threshold value, the corresponding delay path of the maximum power or amplitude.
  • the effective delay paths include at least one of the following: the corresponding power or amplitude is greater than the first The delay path of the threshold value, the corresponding delay path of the maximum power or amplitude.
  • the two target paths can be any two paths of the target channel, for example: paths corresponding to two maximum values.
  • the time delay spacing of the two target paths can reflect the path included in the target signal in the frequency domain. Concentrated intensity.
  • Option 4 The greater the number of effective beams of the target channel, the longer the reported second channel characteristic information can be.
  • the terminal can determine the second length according to the value of the detected target channel parameter of the target channel, so that the reported second channel characteristic information of the second length matches the channel state of the target channel.
  • the method further includes:
  • the terminal receives relevant information of K first AI network models from the network side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models The models are respectively used to decode the channel characteristic information of their corresponding lengths;
  • the terminal determines the second length according to channel conditions, including:
  • the terminal intercepts K pieces of second channel characteristic information from the first channel characteristic information, and processes the second channel characteristic information of corresponding lengths into first K pieces of first AI network models respectively.
  • channel information
  • the terminal obtains the degree of matching between the K pieces of the first channel information and the target channel information respectively;
  • the terminal determines that the second length is equal to the first AI network used to process the target first channel information.
  • the relevant information of the first AI network model may be model parameters, model configuration, model identification information, etc.
  • the terminal can determine which first AI network model the network side device will use to decode the second AI network model based on the relevant information. Channel characteristic information. Then, the terminal can use the first AI network model or a simplified network model of the first AI network model to simulate the network-side device corresponding to the long-term degree of decoding of the second channel characteristic information, thereby comparing the simulated decoding result (ie, the first channel information) with the target channel information to determine the degree of matching between the two.
  • the higher the matching degree between the first channel information and the target channel information it means that the first AI network model adopted can restore the target channel information more accurately.
  • the matching degree between the above-mentioned target first channel information and the target channel information satisfies the preset conditions, which can be understood as: obtaining the second channel corresponding to the length of the first AI network model of the target first channel information.
  • the decoding result of the characteristic information can meet business requirements or communication quality requirements.
  • the terminal device may traverse each first AI network model to determine whether the decoding result of each first AI network model for the corresponding length of the second channel characteristic information matches the target channel information to a satisfactory degree.
  • Preset conditions there may be a situation where the degree of matching between the first channel information obtained by at least two first AI network models and the target channel information satisfies the preset conditions. In this case, it is possible to further select from the at least two first AI network models. The smallest one of the corresponding lengths of the two first AI network models is selected as the second length, thereby intercepting the second channel characteristic information of the second length from the first channel characteristic information, and reporting it to the network side device.
  • the terminal device can also sequentially determine the degree of matching between the decoding result of the second channel characteristic information of the corresponding length of the first AI network model pair and the target channel information, and determine the length of the corresponding length of a certain first AI network model pair.
  • the second length is determined to be the length corresponding to the first AI network model pair. In this way, the determination of the second length can be reduced. amount of calculation.
  • the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:
  • the correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation
  • the channel capacity of the target first channel information is greater than or equal to a first preset value times the channel capacity of the target channel information, and the first preset value is greater than 0 and less than or equal to 1;
  • the target first channel information is the one in which a channel quality indicator (Channel quality indicator, CQI) among the K pieces of first channel information is the same as or closest to the CQI of the target channel information;
  • CQI Channel quality indicator
  • the target first channel information is modulated and coded among the K pieces of first channel information.
  • the scheme (Modulation and coding scheme, MCS) is the same as or the closest one to the MCS of the target channel information.
  • the correlation between the above-mentioned target first channel information and the target channel information may be the similarity between the information content of the target first channel information and the target channel information, for example: the target first channel information and the above-mentioned target channel information.
  • Mutual information between target channel information may be the similarity between the information content of the target first channel information and the target channel information, for example: the target first channel information and the above-mentioned target channel information.
  • the second channel characteristic information may only include part of the first channel characteristic information, and the above-mentioned first channel information may only include part of the information in the target channel information, then the second channel characteristics based on different lengths and/or different positions
  • the channel information decoded by the information may contain different channel capacities, CQIs, MCSs, etc. In this case, it may be preferable to select the channel capacity of the first channel information to be greater than the first preset value times the channel capacity of the target channel information.
  • the length of the first AI network model is used as the second length, where the first preset value may be a value indicated by the network side device or agreed upon by the protocol.
  • the second length can decode channel information that meets business requirements and/or channel quality requirements.
  • the first channel information that is closest to the CQI and/or MCS in the target channel information may also be used as the target first channel information.
  • the channel characteristic information reporting method further includes:
  • the terminal sends second indication information to the network side device, and the second indication information indicates the second length.
  • the terminal when determining the second length, the terminal also reports the second length to the network side device, so that the network side device directly uses the first AI network model corresponding to the second length to decode the second channel characteristic information. .
  • the terminal may not report the second length to the network side device.
  • the network side device may detect the length of the second channel characteristic information reported by the terminal. Therefore, the first AI network model corresponding to the length is used to decode the second channel characteristic information, which is not specifically limited here.
  • the CSI report may include a fixed-length CSI part (eg, CSI Part1) and a variable-length CSI part (eg, CSI Part2).
  • CSI Part1 a fixed-length CSI part
  • variable-length CSI part eg, CSI Part2
  • the above-mentioned second indication information may be carried in a fixed-length CSI part or a variable-length CSI part in the CSI report.
  • the second channel characteristic information of the second length may also be located in the variable length CSI part, Alternatively, one part is in the fixed-length CSI part and the other part is in the variable-length CSI part.
  • the value range of the second length may include multiple values between the minimum length and the first length, and the fixed-length CSI part in the CSI report often only accommodates smaller lengths, at this time, the The minimum length part of the second channel characteristic information of the second length is placed in the fixed-length CSI part of the CSI report, and the other parts of the second channel characteristic information are placed in the variable-length CSI part of the CSI report.
  • the above-mentioned minimum length may be less than or equal to the second length, that is, the minimum length may be equal to the minimum value that the second length may take. For example, assume that the input lengths of the K first AI network models are from short to For long arrays N1 ⁇ NK, the minimum length can be equal to N1.
  • N2 to NK all contain the channel characteristic information corresponding to N1, so that the fixed-length CSI part in the CSI report can fixedly carry the content of the 0th to (N1-1) bits in the first channel characteristic information. And when the second length is greater than N1, the content located after the (N1-1)th bit in the second channel characteristic information may be placed in the variable-length CSI part of the CSI report.
  • the position of the minimum length part of the second channel characteristic information of the second length in the second channel characteristic information can be agreed by the protocol, for example: the second channel characteristic information
  • the minimum length portion of may include at least one of the following:
  • the first X bits in the second channel characteristic information, X is equal to the minimum length
  • the second indication information is carried in a fixed-length CSI part in the CSI report, and the second channel characteristic information of the second length is carried in a variable-length CSI part in the CSI report.
  • Example 2 The minimum length part of the second channel characteristic information of the second length and the second indication information are carried in the fixed length CSI part of the CSI report, and the second channel characteristic information of the second length The variable length part in , except the minimum length part, is carried in the variable length CSI part in the CSI report.
  • the second indication information and the second channel characteristic information of the second length are both carried in a variable-length CSI part in the CSI report.
  • the terminal sends second channel characteristic information to the network side device, including:
  • the terminal sends the second channel feature information intercepted from the first channel feature information to the network side device respectively, where M is an integer greater than 1, and the M times channel feature information
  • M is an integer greater than 1
  • M times channel feature information The lengths of the second channel characteristic information reported by the information are different from each other, or the contents of the second channel characteristic information reported by the M times of channel characteristic information are different from each other.
  • the above-mentioned M pieces of second channel characteristic information can be divided into M times of reporting, that is, the terminal reports M times of channel characteristic information, each time reporting a piece of second channel characteristic information.
  • the terminal may also report at least two second channel characteristic information at one time, which is not specifically limited here.
  • the terminal may send the second channel characteristic information intercepted from the first channel characteristic information to the network side device in turn in order of length from small to large in M times of channel characteristic information reporting.
  • the network side device can gradually improve the accuracy of channel recovery during the process of channel recovery based on the received second channel characteristic information.
  • the terminal can determine the corresponding second lengths of the M times of channel characteristic information reporting according to the current channel environment.
  • the second length of the M pieces of second channel characteristic information is It can be the same or different.
  • the network side device may obtain M pieces of second channel characteristic information with different lengths (that is, the historical channel characteristic information includes M pieces of mutually different lengths reported by the terminal in the historical time period).
  • Different second channel characteristic information in this way, during the subsequent channel recovery process, the network side device can update the historical channel characteristic information based on the second channel characteristic information currently reported by the terminal, and use all updated historical channel characteristics information to perform channel recovery. That is to say, the length of all the historical channel characteristic information can be the same as the length of the first channel characteristic information.
  • part of the historical channel characteristic information is the current channel characteristic information, and the other part is the channel once reported by the terminal. Feature information.
  • the time-frequency resource location for the M times of channel characteristic information reporting is configured by a piece of CSI report configuration information
  • the time-frequency resource locations for the M channel characteristic information reports are configured by M pieces of CSI report configuration information.
  • the time-frequency resource locations for the M times of channel characteristic information reporting can be configured in the same CSI report configuration information (CSI report config), that is, one CSI report config configures M time-frequency resource locations for reporting channel characteristic information, and the terminal reports second channel characteristic information at each time-frequency resource location.
  • CSI report config CSI report configuration information
  • the time-frequency resource locations for the M times of channel characteristic information reporting can be configured in M CSI report configuration information (CSI report config), that is, M CSI report configs are configured, and each CSI report config can be used to configure the time-frequency resource location for reporting channel characteristic information.
  • M CSI report configuration information CSI report config
  • the time-frequency resource location for each channel characteristic information report can be more flexibly configured.
  • the lengths of the second channel characteristic information reported M times are sequentially increased from the minimum length to the first length
  • the second channel characteristic information reported by the M times of channel characteristic information respectively includes non-overlapping parts of the first channel characteristic information, and the sum of the lengths of the second channel characteristic information reported by the M times of channel characteristic information is equal to the first length.
  • the lengths of the second channel characteristic information reported in the M times of channel characteristic information increase sequentially from the minimum length to the first length.
  • the terminal sends the second channel characteristic information intercepted from the first channel characteristic information to the network side device respectively in M times of channel characteristic information reporting, including:
  • the terminal sends the second channel characteristic information to the network side device respectively according to the order of the length of the second channel characteristic information from short to long.
  • the network side device can use the second channel characteristic information reported in order from short to long to gradually improve the accuracy of the restored channel information.
  • the second channel characteristic information reported for the M times of channel characteristic information respectively includes non-overlapping portions of the first channel characteristic information, and the M times of channel characteristic information reported are The sum of the lengths of the second channel characteristic information is equal to the first length.
  • the terminal sends the second channel characteristic information intercepted from the first channel characteristic information to the network side device respectively in M times of channel characteristic information reporting, including:
  • the terminal sends the second channel characteristic information to the network side device according to the order in which the second channel characteristic information is arranged in the first channel characteristic information. interest.
  • the terminal can report non-overlapping channel characteristic information contents respectively during multiple channel characteristic information reporting processes.
  • the network side device can store the historical channel characteristic information that the terminal has reported, and report the second channel on the terminal. feature information, use the second channel feature information to update the reported historical channel feature information, and use the updated historical channel feature information as a whole to restore the channel information, which can reduce the second channel feature reported by the terminal.
  • the amount of information can also be increased, and the amount of historical channel characteristic information used by network-side equipment for channel recovery can also be increased.
  • the terminal uses the target AI network model to process the target channel information into the first channel characteristic information of the first length; the terminal sends the second channel characteristic information to the network side device, and the second channel characteristic information is the first channel characteristic information. Part of the channel characteristic information.
  • the terminal can adaptively use the same AI network model for encoding according to the length of the channel information, and only report part of the channel characteristic information of the corresponding length to the network side device, so that the network side uses the preconfigured
  • the AI network model corresponding to the length is used to decode this part of the channel characteristic information, and can reduce the cost of transmitting the AI network model between the terminal and the network side device.
  • an embodiment of the present application provides a channel characteristic information recovery method.
  • the execution subject may be a network side device.
  • the terminal may be various types of network side devices 12 listed in Figure 1, or other than Network-side devices other than the network-side device types listed in the embodiment shown in FIG. 1 are not specifically limited here.
  • the channel characteristic information recovery method may include the following steps:
  • Step 601 The network side device receives second channel characteristic information from the terminal, where the second channel characteristic information includes part of the first channel characteristic information, and the first channel characteristic information is the target AI network model adopted by the terminal. Channel characteristic information of the first length obtained by processing the target channel information.
  • first channel characteristic information, second channel characteristic information and target channel information respectively have the same characteristics as the first channel characteristic information, second channel characteristic information and target channel information in the method embodiment as shown in Figure 2. The meaning will not be elaborated here.
  • Step 602 The network side device uses the first AI network model to process the second channel characteristic information to obtain the target channel information.
  • the network side device uses the first AI network model to process the second channel characteristic information to obtain the target channel information, which may be: the network side device uses a length corresponding to the second channel characteristic information.
  • the first AI network model processes the second channel characteristic information to obtain the target channel information; or, the network side device uses at least two first AI network models corresponding to the second channel characteristic information to obtain the second channel characteristic information. The information is processed to obtain the target channel information.
  • the network side device receives the second channel characteristic information from the terminal, including:
  • the network side device receives second channel characteristic information of a second length intercepted from the first channel characteristic information from the terminal, and the second length is less than or equal to the first length.
  • the above-mentioned second length of second channel characteristic information has the same meaning as the second length of second channel characteristic information in the method embodiment shown in Figure 2, and also means that the terminal can determine the second length according to the instructions of the network side device. , or determine the second length according to the conditions agreed in the protocol, and report the second channel characteristic information of the second length to the network side device, which is not specifically limited here.
  • the network side device uses a first AI network model to process the second channel characteristic information to obtain the target channel information, which includes:
  • the network side device uses a first AI network model corresponding to the second channel characteristic information of the second length to process the second channel characteristic information of the second length to obtain the target channel information.
  • each decoder has its own first AI network model.
  • Each first AI The network models have corresponding second lengths: N0 to N4. In this way, each decoder can obtain the target channel information by decoding the corresponding second channel characteristic information of the second length.
  • the network side device uses a first AI network model corresponding to the second length each time to perform channel recovery.
  • the network side device uses a first AI network model to process the second channel characteristic information to obtain the target channel information, including:
  • the The network side device updates the historical channel characteristic information according to the second channel characteristic information of the second length;
  • the network side device uses the first AI network model to process the updated historical channel characteristic information to obtain the target channel information.
  • the above-mentioned network side device uses the first AI network model to process the updated historical channel characteristic information to obtain the target channel information, which may be: using an algorithm with the updated historical channel characteristic information.
  • the first AI network model corresponding to the length processes the updated historical channel characteristic information to obtain the target channel information. For example: as shown in Figure 7a, assuming that the bit length of the updated historical channel characteristic information is the same as the decoded Corresponding to the decoder 5, the first AI network model in the decoder 5 is used to decode the updated historical channel characteristic information.
  • the above-mentioned network side device uses the first AI network model to process the updated historical channel characteristic information to obtain the target channel information, or it can also use the sum of the length and the updated historical channel characteristic information.
  • at least one first AI network model corresponding to the position in the first channel characteristic information processes the updated historical channel characteristic information to obtain the target channel information, for example: as shown in Figure 7b, assuming 1 encoder corresponds to 4 decoders (decoder 1 to decoder 4 respectively), and each decoder has its own first AI network model, and the second length corresponding to each first AI network model is the same (assuming the second length is N bits) but do not overlap each other.
  • the network side device can use the decoder
  • the first AI network model in 1 decodes the corresponding second channel feature information, and uses the first AI network model in decoder 2 to decode the corresponding second channel feature information, and finally combines decoder 1 and decoding
  • the decoding result of processor 2 is used to obtain the target channel information. That is, each decoder corresponds to the incremental part of the channel characteristic information, and the results of multiple decoders are combined to restore the channel information.
  • the second length of second channel characteristic information includes at least one of the following:
  • N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length
  • N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information are N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information.
  • the method before the network side device receives the second channel characteristic information of the second length intercepted from the first channel characteristic information from the terminal, the method further includes:
  • the network side device sends first indication information to the terminal, wherein the first indication information indicates the second length and/or a first encoding identifier, and the first encoding identifier is associated with the second length. .
  • the first indication information is configured by high-level signaling; or,
  • the second channel characteristic information is carried in the channel state information CSI report, and the first indication information is indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.
  • the channel characteristic information recovery method further includes:
  • the network side device receives second indication information from the terminal, and the second indication information indicates the second length.
  • the second indication information is carried in a fixed-length CSI part in the CSI report, and the second channel characteristic information of the second length is carried in a variable-length CSI part in the CSI report;
  • the minimum length part of the second channel characteristic information of the second length and the second indication information are carried in the fixed length CSI part of the CSI report, and the second channel characteristic information of the second length except for the The variable length part other than the minimum length part is carried in the variable length CSI part in the CSI report; or,
  • the second indication information and the second channel characteristic information of the second length are both carried in the variable-length CSI part of the CSI report.
  • the minimum length is less than or equal to the second length.
  • the network side device receives second channel characteristic information from the terminal, including:
  • the network side device receives the second channel characteristic information respectively in the M times of channel characteristic information reporting by the terminal, where M is an integer greater than 1, and the second channel characteristic information reported by the M times of channel characteristic information is The lengths are different from each other, or the contents of the second channel characteristic information reported by the M times of channel characteristic information are different from each other.
  • the network side device uses the first AI network model to process the second channel characteristic information to obtain the target channel information, including:
  • the network side device respectively uses M first AI network models to process the second channel characteristic information of corresponding lengths to obtain the target channel information.
  • the corresponding lengths of the M first AI network models include the corresponding lengths.
  • the network side device uses a first AI network model to process the second channel characteristic information reported by the M times of channel characteristic information to obtain the target channel information.
  • the above-mentioned network side device respectively uses M first AI network models to process the second channel characteristic information of corresponding lengths to obtain the target channel information, which is the same as the implementation shown in Figure 7b
  • M first AI network models to process the second channel characteristic information of corresponding lengths to obtain the target channel information
  • the above network side device uses a first AI network model to process the second channel characteristic information reported by the M times of channel characteristic information to obtain the target channel information, as shown in Figure
  • the embodiment shown in 7a is similar and has the same beneficial effects, and will not be described again here.
  • the time-frequency resource location for the M times of channel characteristic information reporting is configured by a piece of CSI report configuration information
  • the time-frequency resource locations for the M channel characteristic information reports are configured by M pieces of CSI report configuration information.
  • the lengths of the second channel characteristic information reported in the M times of channel characteristic information increase sequentially from the minimum length to the first length
  • the second channel characteristic information reported by the M times of channel characteristic information respectively includes non-overlapping parts of the channel characteristic information, and the sum of the lengths of the second channel characteristic information reported by the M times of channel characteristic information is equal to the First length.
  • the network side device receives the second channel characteristic information reported from the terminal M times of channel characteristic information, including:
  • the network side device receives the second channel feature information from the terminal in a preset order, and the preset order includes:
  • the length of the second channel characteristic information is arranged in order from short to long;
  • the order in which the second channel characteristic information is arranged in the first channel characteristic information is arranged in the first channel characteristic information.
  • the network side device can use the first AI network model corresponding to the length of part of the first channel characteristic information reported by the terminal (that is, the second channel characteristic information) to perform channel recovery on the second channel characteristic information. , which can reduce the cost of transmitting AI network models between terminals and network-side devices.
  • the embodiment of the present application uses the following interaction process of channel characteristic information as an example to illustrate the channel characteristic information reporting method and channel characteristic information provided by the embodiments of the present application.
  • Feature information recovery method In this embodiment, the interaction process of channel feature information includes the following steps:
  • Step 1 The terminal detects CSI-RS or TRS at the time-frequency domain location specified by the network, and performs channel estimation to obtain target channel information;
  • Step 2 The terminal encodes the target channel information into the first channel characteristic information through the target AI network model (i.e., AI encoding network model);
  • the target AI network model i.e., AI encoding network model
  • Step 3 The terminal selects part of the first channel characteristic information as the second channel characteristic information to be reported;
  • Step 4 The terminal combines the second channel characteristic information to be reported and other control information into uplink control information (UCI), or uses the second channel characteristic information to be reported as UCI;
  • UCI uplink control information
  • Step 5 The terminal divides the UCI according to the length of the UCI and adds cyclic redundancy check (CRC) bits;
  • CRC cyclic redundancy check
  • Step 6 The terminal performs channel coding on the UCI with CRC bits added
  • Step 7 The terminal performs rate matching on UCI
  • Step 8 The terminal performs code block association on UCI
  • Step 9 The terminal maps the UCI to the Physical Uplink Control Channel (PUCCH) or Physical Uplink Shared Channel (PUSCH) for reporting.
  • PUCCH Physical Uplink Control Channel
  • PUSCH Physical Uplink Shared Channel
  • the execution subject may be the channel characteristic information Information reporting device.
  • the method for reporting channel characteristic information performed by the channel characteristic information reporting device is used as an example to illustrate the channel characteristic information reporting device provided by the embodiment of the present application.
  • a device for reporting channel characteristic information provided by an embodiment of the present application can be a device in a terminal.
  • the device 800 for reporting channel characteristic information can include the following modules:
  • the first processing module 801 is configured to use the target AI network model to process the target channel information into first channel characteristic information of a first length;
  • the first sending module 802 is configured to send second channel characteristic information to the network side device, where the second channel characteristic information is part of the first channel characteristic information.
  • the first sending module 802 is specifically used for:
  • the first length is the number of bits of the first channel characteristic information, or the first length is the number of coefficients included in the first channel characteristic information; and/or,
  • the second length is the number of bits of the second channel characteristic information, or the second length is the number of coefficients included in the second channel characteristic information.
  • the second length of second channel characteristic information includes at least one of the following:
  • N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length
  • N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information are N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information.
  • the channel characteristic information reporting device 800 also includes:
  • a first receiving module configured to receive first indication information from the network side device, wherein the first indication information indicates the second length and/or a first encoding identifier, and the first encoding identifier is identical to the first encoding identifier. Describe the second length association.
  • the first indication information is configured by high-level signaling; or,
  • the second channel characteristic information is carried in the channel state information CSI report, and the first indication information is the indication information in the CSI report configuration, or the first indication information is used by the terminal. Corresponds to the CSI resources used.
  • the channel characteristic information reporting device 800 also includes:
  • a determining module configured to determine the second length according to at least one of channel characteristics and channel conditions corresponding to the target channel information.
  • the channel characteristic information reporting device 800 also includes:
  • a third sending module is configured to send second indication information to the network side device, where the second indication information indicates the second length.
  • the second indication information is carried in a fixed-length CSI part in the CSI report, and the second length of the second channel characteristic information is carried in a variable-length CSI part in the CSI report;
  • the minimum length part of the second channel characteristic information of the second length and the fixed length CSI part of the second indication information are carried in the CSI report, and the second length of the second channel characteristic information except The variable-length part other than the minimum-length part is carried in the variable-length CSI part in the CSI report; or,
  • the second indication information and the second channel characteristic information of the second length are both carried in the variable-length CSI part of the CSI report.
  • the minimum length is less than or equal to the second length.
  • the determination module is specifically used to perform any of the following:
  • the length of the value association of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the first association relationship includes each value of the target channel parameter. Or the relationship between each value range and length;
  • the second association relationship it is determined that the length corresponding to the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the second association relationship includes the target channel parameter The association between each value or each value range and the coding identifier.
  • the target channel parameters of the target channel include at least one of the following:
  • the target channel is line-of-sight propagation or non-line-of-sight propagation
  • the number of effective beams of the target channel include beams corresponding to the discrete Fourier transform DFT orthogonal basis with power greater than the first threshold.
  • the effective delay path includes at least one of the following:
  • the corresponding delay path whose power or amplitude is greater than the first threshold
  • the delay path corresponding to the maximum power or amplitude.
  • the channel characteristic information reporting device 800 also includes:
  • the fourth receiving module is configured to receive relevant information of K first AI network models from the network side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models correspond to the target AI network models.
  • the first AI network model is used to decode the channel characteristic information of the respective corresponding lengths;
  • the determination module includes:
  • the second processing unit is configured to intercept K second channel characteristic information from the first channel characteristic information, and convert the second channel characteristic information of corresponding lengths through the K first AI network models. Processed into first channel information;
  • An acquisition unit configured to acquire the degree of matching between K pieces of the first channel information and the target channel information respectively;
  • Determining unit configured to determine that the second length is equal to the first length for processing to obtain the target first channel information when it is determined that the matching degree between the target first channel information and the target channel information satisfies a preset condition.
  • the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:
  • the correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation
  • the channel capacity of the target first channel information is greater than or equal to a first preset value times the channel capacity of the target channel information, and the first preset value is greater than 0 and less than or equal to 1;
  • the target first channel information is the one in which the channel quality indicator CQI of the K pieces of first channel information is the same as or the closest to the CQI of the target channel information;
  • the target first channel information is one of the K pieces of first channel information in which the modulation and coding scheme MCS is the same as or closest to the MCS of the target channel information.
  • the first sending module 802 is specifically used for:
  • the second channel characteristic information intercepted from the first channel characteristic information is sent to the network side device respectively, where M is an integer greater than 1, and the M times of channel characteristic information reporting are The lengths of the second channel characteristic information are different from each other, or the contents of the second channel characteristic information reported by the M times of channel characteristic information are different from each other.
  • the time-frequency resource location for the M times of channel characteristic information reporting is configured by a piece of CSI report configuration information
  • the time-frequency resource locations for the M channel characteristic information reports are configured by M pieces of CSI report configuration information.
  • the lengths of the second channel characteristic information reported for the M times of channel characteristic information increase sequentially from the minimum length to the first length
  • the second channel characteristic information reported by the M times of channel characteristic information respectively includes non-overlapping parts of the first channel characteristic information, and the sum of the lengths of the second channel characteristic information reported by the M times of channel characteristic information is equal to the first length.
  • the first sending module 802 is specifically used for:
  • the second channel characteristic information is sent to the network side device respectively in a preset order, and the preset order includes:
  • the length of the second channel characteristic information is arranged in order from short to long;
  • the order in which the second channel characteristic information is arranged in the first channel characteristic information is arranged in the first channel characteristic information.
  • the channel characteristic information reporting device 800 also includes:
  • a channel estimation module configured to perform channel estimation on the channel state information-reference signal CSI-RS or tracking reference signal TRS to obtain the target channel information
  • a preprocessing module is used to preprocess the channel information obtained by channel estimation to obtain the target channel information.
  • the channel characteristic information reporting device 800 in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.
  • the electronic device may be a terminal or other devices other than the terminal.
  • Example, terminal It may include but is not limited to the types of terminals 11 listed above.
  • Other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiments of this application.
  • the channel characteristic information reporting device 800 provided by the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 2 and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • the execution subject may be a channel characteristic information recovery device.
  • the channel characteristic information restoration method performed by the channel characteristic information restoration apparatus is used as an example to illustrate the channel characteristic information restoration apparatus provided by the embodiments of the present application.
  • a channel characteristic information recovery device provided by an embodiment of the present application can be a device in a network side device.
  • the channel characteristic information recovery device 900 can include the following modules:
  • the second receiving module 901 is configured to receive second channel characteristic information from the terminal, where the second channel characteristic information includes part of the first channel characteristic information, and the first channel characteristic information is the target AI adopted by the terminal.
  • the first length of channel characteristic information obtained by processing the target channel information by the network model;
  • the second processing module 902 is configured to use the first AI network model to process the second channel characteristic information to obtain the target channel information.
  • the second receiving module 901 is specifically used for:
  • the first length is the number of bits of the first channel characteristic information, or the first length is the number of coefficients included in the first channel characteristic information; and/or,
  • the second length is the number of bits of the second channel characteristic information, or the second length is the number of coefficients included in the second channel characteristic information.
  • the second processing module 902 is specifically used to:
  • the first AI network model corresponding to the second channel characteristic information of the second length is used to process the second channel characteristic information of the second length to obtain the target channel information.
  • the second processing module 902 includes:
  • An update unit configured to update the historical channel characteristic information according to the second channel characteristic information of the second length when the network side device stores the historical channel characteristic information of the terminal;
  • the first processing unit is configured to use a first AI network model to process the updated historical channel characteristic information to obtain the target channel information.
  • the second length of second channel characteristic information includes at least one of the following:
  • N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length
  • N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information are N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information.
  • the channel characteristic information recovery device 900 also includes:
  • the fourth sending module is configured to send first indication information to the terminal, wherein the first indication information indicates the second length and/or a first encoding identifier, and the first encoding identifier is the same as the second encoding identifier. Length correlation.
  • the first indication information is configured by high-level signaling; or,
  • the second channel characteristic information is carried in the channel state information CSI report, and the first indication information is indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.
  • the channel characteristic information recovery device 900 also includes:
  • a third receiving module is configured to receive second indication information from the terminal, where the second indication information indicates the second length.
  • the second indication information is carried in a fixed-length CSI part of the CSI report, and the second length of the second channel characteristic information is carried in a variable-length CSI part of the CSI report;
  • the minimum length part of the second channel characteristic information of the second length and the second indication information are carried in the fixed length CSI part of the CSI report, and the second channel characteristic information of the second length except for the The variable length part other than the minimum length part is carried in the variable length CSI part in the CSI report; or,
  • the second indication information and the second channel characteristic information of the second length are both carried in the variable-length CSI part in the CSI report.
  • the minimum length is less than or equal to the second length.
  • the second receiving module 901 is specifically used for:
  • the second channel feature information is received respectively, where M is an integer greater than 1, and the lengths of the second channel feature information reported by the M times of channel feature information are different from each other, Or the contents of the second channel characteristic information reported in the M times of channel characteristic information are different from each other.
  • the second processing module 902 is specifically used to perform any of the following:
  • M first AI network models are respectively used to process the second channel characteristic information of corresponding lengths to obtain the target channel information, and the corresponding lengths of the M first AI network models include the M channel characteristics.
  • a first AI network model is used to process the second channel characteristic information reported M times to obtain the target channel information.
  • the time-frequency resource location for the M times of channel characteristic information reporting is configured by a piece of CSI report configuration information
  • the time-frequency resource locations for the M channel characteristic information reports are configured by M pieces of CSI report configuration information.
  • the lengths of the second channel characteristic information reported for the M times of channel characteristic information increase sequentially from the minimum length to the first length
  • the second channel characteristic information reported by the M times of channel characteristic information respectively includes non-overlapping parts of the channel characteristic information, and the sum of the lengths of the second channel characteristic information reported by the M times of channel characteristic information is equal to the First length.
  • the second receiving module 901 is specifically used for:
  • the second channel feature information from the terminal is received respectively in a preset order, and the preset order includes:
  • the length of the second channel characteristic information is arranged in order from short to long;
  • the order in which the second channel characteristic information is arranged in the first channel characteristic information is arranged in the first channel characteristic information.
  • the channel characteristic information recovery device 900 in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in an electronic device, such as an integrated circuit or chip.
  • the electronic device may be a network-side device, or may be other devices besides the network-side device.
  • the terminal may include but is not limited to the types of network side devices 12 listed above.
  • Other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiment of this application.
  • the channel characteristic information recovery device 900 provided by the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 6 and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • this embodiment of the present application also provides a communication device 1000, which includes a processor 1001 and a memory 1002.
  • the memory 1002 stores programs or instructions that can be run on the processor 1001, such as , when the communication device 1000 is a terminal, when the program or instruction is executed by the processor 1001, each step of the above channel characteristic information reporting method embodiment is implemented, and the same technical effect can be achieved.
  • the communication device 1000 is a network-side device, when the program or instruction is executed by the processor 1001, each step of the above channel characteristic information recovery method embodiment is implemented, and the same technical effect can be achieved. To avoid duplication, the details are not repeated here.
  • An embodiment of the present application also provides a terminal, including a processor and a communication interface.
  • the processor is used to use the target AI network model to process the target channel information into first channel characteristic information of a first length;
  • the communication interface is used to provide The network side device sends second channel characteristic information, and the second channel characteristic information is part of the first channel characteristic information.
  • This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment.
  • Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this terminal embodiment, and can achieve the same technical effect.
  • FIG. 11 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application.
  • the terminal 1100 includes but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109, a processor 1110, etc. At least some parts.
  • the terminal 1100 may also include a power supply (such as a battery) that supplies power to various components.
  • the power supply may be logically connected to the processor 1110 through a power management system.
  • the power management system is used to manage functions such as charging, discharging, and power consumption management.
  • the terminal structure shown in FIG. 11 does not constitute a limitation on the terminal.
  • the terminal may include more or fewer components than shown in the figure, or some components may be combined or arranged differently, which will not be described again here.
  • the input unit 1104 may include a graphics processing unit (Graphics Processing Unit, GPU) 11041 and a microphone 11042.
  • the graphics processor 11041 is responsible for the image capture device (GPU) in the video capture mode or the image capture mode. Process the image data of still pictures or videos obtained by cameras (such as cameras).
  • the display unit 1106 may include a display panel 11061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like.
  • the user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072 .
  • Touch panel 11071 also called touch screen.
  • the touch panel 11071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 11072 may include but are not limited to physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be described again here.
  • the radio frequency unit 1101 after receiving downlink data from the network side device, the radio frequency unit 1101 can transmit it to the processor 1110 for processing; in addition, the radio frequency unit 1101 can send uplink data to the network side device.
  • the radio frequency unit 1101 includes, but is not limited to, an antenna, amplifier, transceiver, coupler, low noise amplifier, duplexer, etc.
  • Memory 1109 may be used to store software programs or instructions as well as various data.
  • the memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, Image playback function, etc.) etc.
  • memory 1109 may include volatile memory or nonvolatile memory, or memory 1109 may include both volatile and nonvolatile memory.
  • 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), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • Volatile memory can be random access memory (Random Access Memory, RAM), 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, DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (Synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM Double Data Rate SDRAM
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM, SLDRAM synchronous link dynamic random access memory
  • the processor 1110 may include one or more processing units; optionally, the processor 1110 integrates an application processor and a modem processor, where the application processor mainly handles operations related to the operating system, user interface, application programs, etc., Modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the above modem processor may not be integrated into the processor 1110.
  • the processor 1110 is configured to use the target AI network model to process the target channel information into first channel characteristic information of a first length;
  • the radio frequency unit 1101 is configured to send second channel characteristic information to the network side device, where the second channel characteristic information is part of the first channel characteristic information.
  • the sending of the second channel characteristic information to the network side device performed by the radio frequency unit 1101 includes:
  • the first length is the number of bits of the first channel characteristic information, or the first length is the number of coefficients included in the first channel characteristic information; and/or,
  • the second length is the number of bits of the second channel characteristic information, or the second length is the number of coefficients included in the second channel characteristic information.
  • the second length of second channel characteristic information includes at least one of the following:
  • N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length
  • N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information are N bits or coefficients in the first channel characteristic information other than the reported channel characteristic information.
  • the radio frequency unit 1101 before performing the sending of the second channel characteristic information of the second length intercepted from the first channel characteristic information to the network side device, is also configured to receive a third channel characteristic information from the network side device. an indication information, wherein the first indication information indicates the second length and/or A first encoding identifier, the first encoding identifier is associated with the second length.
  • the first indication information is configured by high-level signaling; or,
  • the second channel characteristic information is carried in the channel state information CSI report, and the first indication information is indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.
  • the processor 1110 is further configured to: At least one of channel characteristics and channel conditions corresponding to the information determines the second length.
  • the radio frequency unit 1101 is also configured to send second indication information to the network side device, where the second indication information indicates the second length.
  • the second indication information is carried in a fixed-length CSI part in the CSI report, and the second length of the second channel characteristic information is carried in a variable-length CSI part in the CSI report;
  • the minimum length part of the second channel characteristic information of the second length and the fixed length CSI part of the second indication information are carried in the CSI report, and the second length of the second channel characteristic information except The variable-length part other than the minimum-length part is carried in the variable-length CSI part in the CSI report; or,
  • the second indication information and the second channel characteristic information of the second length are both carried in the variable-length CSI part of the CSI report.
  • the minimum length is less than or equal to the second length.
  • the step performed by the processor 1110 to determine the second length according to the channel characteristics corresponding to the target channel information includes:
  • the length of the value association of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the first association relationship includes each value of the target channel parameter. Or the relationship between each value range and length; or,
  • the second association relationship it is determined that the length corresponding to the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the second association relationship includes the target channel parameter The relationship between each value or each value range and the encoding identifier relationship.
  • the target channel parameters of the target channel include at least one of the following:
  • the target channel is line-of-sight propagation or non-line-of-sight propagation
  • the number of effective beams of the target channel include beams corresponding to the discrete Fourier transform DFT orthogonal basis with power greater than the first threshold.
  • the effective delay path includes at least one of the following:
  • the corresponding delay path whose power or amplitude is greater than the first threshold
  • the delay path corresponding to the maximum power or amplitude.
  • the radio frequency unit 1101 is also configured to receive relevant information of K first AI network models from the network side device, where the K first AI network models correspond to the target AI network model, The K first AI network models are respectively used to decode channel characteristic information of corresponding lengths;
  • Determining the second length according to channel conditions performed by the processor 1110 includes:
  • the processor 1110 intercepts K pieces of second channel characteristic information from the first channel characteristic information, and processes the corresponding lengths of the second channel characteristic information into first K pieces of first AI network models.
  • channel information
  • the processor 1110 obtains the matching degree of each of the K first channel information and the target channel information
  • the processor 1110 determines that the second length is equal to the first AI network used to process the target first channel information.
  • the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:
  • the correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation
  • the channel capacity of the target first channel information is greater than or equal to the channel capacity of the target channel information.
  • the first preset value times the channel capacity, the first preset value is greater than 0 and less than or equal to 1;
  • the target first channel information is the one in which the channel quality indicator CQI of the K pieces of first channel information is the same as or the closest to the CQI of the target channel information;
  • the target first channel information is one of the K pieces of first channel information in which the modulation and coding scheme MCS is the same as or closest to the MCS of the target channel information.
  • the sending of the second channel characteristic information to the network side device performed by the radio frequency unit 1101 includes:
  • the second channel feature information intercepted from the first channel feature information is sent to the network side device respectively, where M is an integer greater than 1, and the M times channel
  • M is an integer greater than 1
  • M times channel The lengths of the second channel characteristic information reported by the characteristic information are different from each other, or the contents of the second channel characteristic information reported by the M times of channel characteristic information are different from each other.
  • the time-frequency resource location for the M times of channel characteristic information reporting is configured by a piece of CSI report configuration information
  • the time-frequency resource locations for the M channel characteristic information reports are configured by M pieces of CSI report configuration information.
  • the lengths of the second channel characteristic information reported in the M times of channel characteristic information increase sequentially from the minimum length to the first length
  • the second channel characteristic information reported by the M times of channel characteristic information respectively includes non-overlapping parts of the first channel characteristic information, and the sum of the lengths of the second channel characteristic information reported by the M times of channel characteristic information is equal to the first length.
  • the second channel characteristic information intercepted from the first channel characteristic information is sent to the network side device respectively, including:
  • the second channel characteristic information is sent to the network side device respectively in a preset order, and the preset order includes:
  • the length of the second channel characteristic information is arranged in order from short to long;
  • the order in which the second channel characteristic information is arranged in the first channel characteristic information is arranged in the first channel characteristic information.
  • processor 1110 performs the process of using the target AI network model to process the target channel information into the first channel characteristic information of the first length:
  • the radio frequency unit 1101 is also used to perform channel estimation on the channel state information-reference signal CSI-RS or tracking reference signal TRS to obtain the target channel information; or,
  • the processor 1110 is also configured to preprocess the channel information obtained by channel estimation to obtain the target channel information.
  • the terminal 1100 provided by the embodiment of the present application can perform each process performed by each module in the channel characteristic information reporting device as shown in Figure 8, and can achieve the same beneficial effects. To avoid duplication, details will not be described here.
  • An embodiment of the present application also provides a network side device, including a processor and a communication interface.
  • the communication interface is used to receive second channel characteristic information from a terminal, where the second channel characteristic information includes part of the first channel characteristic information.
  • the first channel characteristic information is the channel characteristic information of the first length obtained by the terminal using the target AI network model to process the target channel information;
  • the processor is configured to use the first AI network model to process the second channel The characteristic information is processed to obtain the target channel information.
  • This network-side device embodiment corresponds to the above-mentioned network-side device method embodiment.
  • Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this network-side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 1200 includes: an antenna 1201, a radio frequency device 1202, a baseband device 1203, a processor 1204 and a memory 1205.
  • Antenna 1201 is connected to radio frequency device 1202.
  • the radio frequency device 1202 receives information through the antenna 1201 and sends the received information to the baseband device 1203 for processing.
  • the baseband device 1203 processes the information to be sent and sends it to the radio frequency device 1202.
  • the radio frequency device 1202 processes the received information and then sends it out through the antenna 1201.
  • the method performed by the network side device in the above embodiment can be implemented in the baseband device 1203, which includes a baseband processor.
  • the baseband device 1203 may include, for example, at least one baseband board on which multiple chips are disposed, as shown in FIG. program to execute the network shown in the above method embodiment. network device operation.
  • the network side device may also include a network interface 1206, which is, for example, a common public radio interface (CPRI).
  • a network interface 1206, which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 1200 in this embodiment of the present invention also includes: instructions or programs stored in the memory 1205 and executable on the processor 1204.
  • the processor 1204 calls the instructions or programs in the memory 1205 to execute the various operations shown in Figure 9. The method of module execution and achieving the same technical effect will not be described in detail here to avoid duplication.
  • Embodiments of the present application also provide a readable storage medium.
  • Programs or instructions are stored on the readable storage medium.
  • the program or instructions are executed by a processor, each process of the method embodiment shown in Figure 2 or Figure 6 is implemented. , and can achieve the same technical effect, so to avoid repetition, they will not be described again here.
  • the processor is the processor in the terminal described in the above embodiment.
  • the readable storage medium includes computer readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disk, etc.
  • An embodiment of the present application further provides a chip.
  • the chip includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions.
  • the implementation is as shown in Figure 2 or Figure 6. Each process of the method embodiment is shown, and the same technical effect can be achieved. To avoid repetition, the details will not be described here.
  • chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
  • the embodiment of the present application further provides a computer program/program product, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement Figure 2 or Figure 6
  • a computer program/program product is stored in a storage medium
  • the computer program/program product is executed by at least one processor to implement Figure 2 or Figure 6
  • Embodiments of the present application also provide a communication system, including: a terminal and a network side device.
  • the terminal can be used to perform the steps of the channel characteristic information reporting method as described above.
  • the network side device can be used to perform the above steps. Steps of the channel characteristic information recovery method.
  • the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation.
  • the technical solution of the present application can be embodied in the form of a computer software product that is essentially or contributes to the existing technology.
  • the computer software product is stored in a storage medium (such as ROM/RAM, disk , CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of this application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Quality & Reliability (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种信道特征信息上报及恢复方法、终端和网络侧设备,属于通信技术领域,本申请实施例的信道特征信息上报方法包括:终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。

Description

信道特征信息上报及恢复方法、终端和网络侧设备
相关申请的交叉引用
本申请主张在2022年3月21日在中国提交的中国专利申请No.202210283893.X的优先权,其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域,具体涉及一种信道特征信息上报及恢复方法、终端和网络侧设备。
背景技术
随着人工智能(Artificial Intelligence,AI)在通信领域的应用,可以使用AI网络模型对信道状态信息(Channel State Information,CSI)信息进行编码和解码。
但是,在不同的信道环境下,信道信息的可压缩程度不同,编码之后的信息长度也不同,例如:简单的信道信息只需要很短的编码长度,但是复杂的信道信息需要较长的编码信息。而不同长度的编码信息对应的AI网络模型的权重参数甚至网络结构都有所不同,在相关技术中,需要针对每一种长度的信道信息,分别训练和使用与该长度对应的AI网络模型进行编码和解码,这就造成在终端和网络侧设备之间需要传递多个AI网络模型,增大了AI网络模型的传递开销。
发明内容
本申请实施例提供一种信道特征信息上报及恢复方法、终端和网络侧设备,使终端能够根据信道信息的长度自适应的采用同一AI网络模型进行编码,可以降低终端和网络侧设备之间传递AI网络模型的开销。
第一方面,提供了一种信道特征信息上报方法,应用于终端,该方法包括:
终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道 特征信息;
所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
第二方面,提供了一种信道特征信息上报装置,应用于终端,该装置包括.:
第一处理模块,用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;
第一发送模块,用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
第三方面,提供了一种信道特征信息恢复方法,应用于网络侧设备,该方法包括:
网络侧设备接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;
所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
第四方面,提供了一种信道特征信息恢复装置,应用于网络侧设备,该装置包括:
第二接收模块,用于接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;
第二处理模块,用于采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
第五方面,提供了一种终端,该终端包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第六方面,提供了一种终端,包括处理器及通信接口,其中,所述处理 器用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息,所述通信接口用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
第七方面,提供了一种网络侧设备,该网络侧设备包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第八方面,提供了一种网络侧设备,包括处理器及通信接口,其中,所述通信接口用于接收来自终端的第二信道特征信息,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;所述处理器用于采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
第九方面,提供了一种通信***,包括:终端及网络侧设备,所述终端可用于执行如第一方面所述的信道特征信息上报方法的步骤,所述网络侧设备可用于执行如第三方面所述的信道特征信息恢复方法的步骤。
第十方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤,或者实现如第三方面所述的方法的步骤。
第十一方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面所述的方法,或实现如第三方面所述的方法。
第十二方面,提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面或第三方面所述的方法的步骤。
在本申请实施例中,终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。这样,在不同的信道环境下,终端能够根据信道信息的长度自适应的采用同一AI网络模型进行编码,且仅向网络侧设备上报相应长度的部分信道特征信息,以使网络侧采用预先 配置的与该长度相对应的AI网络模型来解码该部分信道特征信息,且可以降低终端和网络侧设备之间传递AI网络模型的开销。
附图说明
图1是本申请实施例能够应用的一种无线通信***的结构示意图;
图2是本申请实施例提供的一种信道特征信息上报方法的流程图;
图3是神经网络模型的架构示意图;
图4是神经元的示意图;
图5是本申请实施例中的时延径的功率谱示意图;
图6是本申请实施例提供的一种信道特征信息恢复方法的流程图;
图7a是本申请实施例中解码器与信道特征信息的对应关系示意图之一;
图7b是本申请实施例中解码器与信道特征信息的对应关系示意图之二;
图8是本申请实施例提供的一种信道特征信息上报装置的结构示意图;
图9是本申请实施例提供的一种信道特征信息恢复装置的结构示意图;
图10是本申请实施例提供的一种通信设备的结构示意图;
图11是本申请实施例提供的一种终端的结构示意图;
图12是本申请实施例提供的一种网络侧设备的结构示意图。
具体实施方式
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清楚描述,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。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)***,还可用于其他无线通信***,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access, TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access,SC-FDMA)和其他***。本申请实施例中的术语“***”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的***和无线电技术,也可用于其他***和无线电技术。以下描述出于示例目的描述了新空口(New Radio,NR)***,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR***应用以外的应用,如第6代(6th Generation,6G)通信***。
图1示出本申请实施例可应用的一种无线通信***的框图。无线通信***包括终端11和网络侧设备12。其中,终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、增强现实(augmented reality,AR)/虚拟现实(virtual reality,VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(Vehicle User Equipment,VUE)、行人终端(Pedestrian User Equipment,PUE)、智能家居(具有无线通信功能的家居设备,如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer,PC)、柜员机或者自助机等终端侧设备,可穿戴式设备包括:智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是,在本申请实施例并不限定终端11的具体类型。网络侧设备12可以包括接入网设备或核心网设备,其中,接入网设备也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备可以包括基站、无线局域网(Wireless Local Area Network,WLAN)接入点或WiFi节点等,基站可被称为节点B、演进节点B(eNB)、接入点、基收发机站(Base Transceiver Station,BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set,BSS)、扩展服务集(Extended Service Set,ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point,TRP)或所述领域中其他某个合适的术语,只要达到相同的技术效果,所述基站不限于特定技术词汇,需要说明的是,在本申请实施例中仅以NR***中的基站为例进行介绍,并不限定基站的具体类型。
在无线通信技术中,准确的CSI反馈对信道容量至关重要。尤其是对于多天线***来讲,发送端可以根据CSI优化信号的发送,使其更加匹配信道的状态。如:信道质量指示(Channel Quality Indicator,CQI)可以用来选择合适的调制编码方案(Modulation and Coding Scheme,MCS),以实现链路自适应;预编码矩阵指示(Precoding Matrix Indicator,PMI)可以用来实现特征波束成形(eigen beamforming),从而最大化接收信号的强度,或者用来抑制干扰(如小区间干扰、多用户之间干扰等)。因此,自从多天线技术(如:多输入多输出(Multi-Input Multi-Output,MIMO))被提出以来,CSI的获取一直都是研究热点。
通常,网络侧设备在某个时隙(slot)的某些时频资源上发送CSI参考信号(CSI-Reference Signals,CSI-RS),终端根据CSI-RS进行信道估计,计算这个slot上的信道信息,通过码本将PMI反馈给基站,网络侧设备根据终端反馈的码本信息组合出信道信息,并在终端下一次上报CSI之前,网络侧设备以此信道信息进行数据预编码及多用户调度。
为了进一步减少CSI反馈开销,终端可以将每个子带上报PMI改成按照时延(delay域,即频域)上报PMI,由于delay域的信道更集中,用更少的delay的PMI就可以近似表示全部子带的PMI,其可以视作是将delay域信息压缩之后再上报。
同样,为了减少开销,网络侧设备可以事先对CSI-RS进行预编码,将编码后的CSI-RS发送给终端,终端看到的是经过编码之后的CSI-RS对应的信道,终端只需要在网络侧设备指示的端口中选择若干个强度较大的端口,并上报这些端口对应的系数即可。
在相关技术中,利用AI网络模型对信道信息进行压缩,能够提升信道特征信息的压缩效果,其中,AI网络模型有多种实现方式,例如:神经网络、决策树、支持向量机、贝叶斯分类器等。为了便于说明,本申请实施例中以AI网络模型为神经网络为例进行说明,但是并不限定AI网络模型的具体类型。
本申请实施例中,在终端利用具有编码功能的目标AI网络模型(即编码器中的AI网络模型,其又可以称之为编码器网络模型或编码AI网络模型)对信道信息进行压缩编码,并将编码后的信道特征信息上报给网络侧设备(例如:基站),在基站侧则利用具有解码功能的第一AI网络模型(即解码器中的AI网络模型,其又可以称之为解码器网络模型或解码AI网络模型)对压缩后的信道特征信息进行解码,从而恢复信道信息。此时基站的第一AI网络模型和终端的目标AI网络模型需要联合训练,达到合理的匹配度。神经网络通过终端的编码器网络模型和基站的解码器网络模型组成联合的神经网络,由网络侧设备进行联合训练,训练完成之后,基站将编码器网络模型发送给终端。
终端估计CSI参考信号(CSI Reference Signal,CSI-RS),根据该估计到的信道信息进行计算,得到计算的信道信息;然后,将计算的信道信息或者原始的估计到的信道信息通过编码网络模型进行编码,得到编码结果,最后将编码结果发送给基站。在基站侧,基站在接收编码后的结果后,将其输入到解码网络模型中,利用该解码网络模型恢复信道信息。
但是,不同的信道环境下,信道信息的可压缩程度不同,因此,编码之后的信道信息的长度也不同,例如:简单的信道信息只需要很短的编码长度,但是复杂的信道信息需要较长的编码信息。这样,不同长度的编码信息对应的AI网络模型的权重参数甚至网络结构都有所不同,这就需要重新训练与该编码长度匹配的AI网络模型。由此可见,在相关技术中,需要针对每一种长度的信道信息,分别训练和使用与该长度对应的AI网络模型进行编码和解码,这就造成在终端和网络侧设备之间需要传递多个AI网络模型,增大了AI网络模型的传递开销以及网络侧设备在针对每一种长度的信道信息,分别训练和使用 与该长度对应的AI网络模型进行编码和解码时,增大了网络侧设备的计算量的问题。
本申请实施例中,终端可以利用目标AI网络模型将信道信息处理成固定长度的编码信息(即第一信道特征信息),并向网络侧设备上报第一信道特征信息中的部分内容,这样,终端可以根据网络侧设备的指示和/或终端自主选择上报的第二信道特征信息的第二长度,并从该第一信道特征信息中截取第二长度的部分来上报给网络侧设备,这样,终端仅需使用一个编码网络进行信道信息的编码,网络侧设备也仅需使用与第二长度对应的解码网络对该第二长度的部分信道特征信息进行解码。
需要说明的是,在实施中,上述终端将第二信道特征信息上报给网络侧设备,可以是采用CSI上报的方式在CSI报告中携带该第二信道特征信息,以上报网络侧设备,其中,信道特征信息具体可以是PMI信息。当然,上述第二信道特征信息还可以采用其他任意方式上报给网络侧设备,为了便于说明,本申请实施例中,以采用CSI上报的方式上报第二信道特征信息为例进行举例说明,在此不构成具体限定。
此外,本申请实施例中的第一长度和第二长度可以是对应的信道特征信息在量化后的比特数,或者,是对应的信道特征信息在量化前所包含的系数的个数。为了便于说明,本申请实施例中以第一长度和第二长度分别为比特数为例进行举例说明,在此也不构成具体限定。
下面结合附图,通过一些实施例及其应用场景对本申请实施例提供的信道特征信息上报方法、信道特征信息恢复方法、信道特征信息上报装置、信道特征信息恢复装置及通信设备等进行详细地说明。
请参阅图2,本申请实施例提供的一种信道特征信息上报方法,其执行主体可以是终端,该终端可以是如图1中列举的各种类型的终端11,或者是除了如图1所示实施例中列举的终端类型之外的其他终端,在此不作具体限定。如图2所示,该信道特征信息上报方法可以包括以下步骤:
步骤201、终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息。
在实施中,上述目标AI网络模型可以包括多种类型的AI算法模块,例如:神经网络、决策树、支持向量机、贝叶斯分类器等,在此不作具体限定,且为了便于说明,以下实施例中以所述AI算法模型为神经网络模型为例进行举例说明,在此不构成具体限定。
如图3所示,神经网络模型包括输入层、隐层和输出层,其可以根据输入层获取的出入信息(X1~Xn)预测可能的输出结果(Y)。神经网络模型由大量的神经元组成,如图4所示,神经元的参数包括:输入参数a1~aK、权值w、偏置b以及激活函数σ(z),以及与这些参数获取输出值a,其中,常见的激活函数包括S型生长曲线(Sigmoid)函数、双曲正切(tanh)函数、线性整流函数(Rectified Linear Unit,ReLU,其也称之为修正线性单元)函数等等,且上述函数σ(z)中的z可以通过以下公式计算得到:
z=a1w1+…+akwk+aKwK+b
其中,K表示输入参数的总数。
神经网络的参数通过优化算法进行优化。优化算法就是一种能够帮我们最小化或者最大化目标函数(有时候也叫损失函数)的一类算法。而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y,我们构建一个神经网络模型f(.),有了模神经网络型后,根据输入x就可以得到预测输出f(x),并且可以计算出预测值和真实值之间的差距(f(x)-Y),这个就是损失函数。我们的目的是找到合适的W和b,使上述的损失函数的值达到最小,损失值越小,则说明我们的模型越接近于真实情况。
目前常见的优化算法,基本都是基于误差反向传播算法。误差反向传播算法的基本思想是,学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时,输入样本从输入层传入,经各隐层逐层处理后,传向输出层。若输出层的实际输出与期望的输出不符,则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传,并将误差分摊给各层的所有单元,从而获得各层单元的误差信号,此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程,是周而复始地进行的。权值不断调整的过程,也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度,或进行到预先设定的学习次数为止。
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent,SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、Nesterov(其表示带动量的随机梯度下降)、自适应梯度下降(Adaptive gradient descent,Adagrad)、自适应学习率调整(Adadelta)、均方根误差降速(root mean square prop,RMSprop)、自适应动量估计(Adaptive Moment Estimation,Adam)等。
这些优化算法在误差反向传播时,都是根据损失函数得到的误差/损失,对当前神经元求导数/偏导,加上学习速率、之前的梯度/导数/偏导等影响,得到梯度,将梯度传给上一层。
在实施中,目标AI网络模型可以用于对信道信息进行编码,其能够将各 种不同信道环境下的信道信息编码成固定长度(即第一长度)的第一信道特征信息。在实施中,上述第一长度可以是较长的一个长度。在某一信道环境下的信道信息的编码结果比第一长度短时,可以采用补零、冗余编码等任意方式将该信道环境下的信道信息的编码结果补充至第一长度。
可选地,在所述终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息之前,所述方法还包括:
所述终端对信道状态信息-参考信号CSI-RS或跟踪参考信号(Tracking Reference Signal,TRS)进行信道估计得到所述目标信道信息;或者,
所述终端对信道估计得到的信道信息进行预处理,得到所述目标信道信息。
本实施方式中,利用目标AI网络模型进行编码处理的目标信道信息可以是终端对CSI-RS信道或TRS信道进行估计所得到的信道信息,或者是终端对估计到的信道信息进行一定的预处理所得到的信道信息,在此不作具体限定。
步骤202、所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
在实施中,上述第二信道特征信息是第一信道特征信息的部分内容可以是:终端从第一信道特征信息中截取部分作为第二信道特征信息。
在实施中,终端可以向网路侧设备发送第二比特的第二信道特征信息;或者,终端也可以分M次信道特征信息上报向网路侧设备发送不同长度或不同内容的M条第二信道特征信息,即每一次信道特征信息上报过程中,上报一条第二信道特征信息,但是通过不同信道特征信息上报过程所上报的第二信道特征信息的长度不同或内容不同。
<作为一种可选的实施方式一>
所述终端向网络侧设备发送第二信道特征信息,包括:
所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
本实施方式中,终端仅向网络侧设备上报第二信道特征信息,且该第二信道特征信息的长度可以是第二长度。
在实施中,该第二长度可以根据网络侧设备的指示来确定,和/或由终端判断采用哪第二长度。相对应的,在网络侧设备接收到该第二长度的第二信道特征信息时,可以采用与该第二长度对应的第一AI网络模型来解码该第二信道特征信息,从而恢复信道信息。
需要说明的是,在无线通信过程中,终端可以在不同的时域位置分别进行信道特征信息上报,且每次信道特征信息上报对应的第二长度可以相同或者不同,在此不作具体限定。例如:可以将第一长度的第一信道特征信息划分为K个信道特征信息段,则第二长度的第二信道特征信息可以包括1~K个信道特征信息段。
在一种可能的实现方式中,网络侧设备在接收终端当前上报的第二信道特征信息时,可以将该第二信道特征信息输入至第一AI网络模型中,以利用第一AI网络模型对该第二信道特征信息进行处理,实现恢复信道信息。
在另一种可能的实现方式中,网络侧设备可以存储终端在历史时间内上报的历史信道特征信息,且在接收终端当前上报的第二信道特征信息时,可以基于该第二信道特征信息更新历史信道特征信息,然后采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息。例如:假设终端以第二长度分别为N0、N1……的顺序循环地上报信道特征信息,则网络侧设备在第一次接收到长度为N0的第二信道特征信息时,基于该长度为N0的第二信道特征信息进行信道恢复;然后,网络侧设备在接收到长度为N1的第二信道特征信息时,基于长度为N0的第二信道特征信息和长度为N1的第二信道特征信息进行信道恢复。此外,在下一次循环过程中,网络侧设备在接收到长度为N0的第二信道特征信息时,基于该长度为N0的第二信道特征信息替换掉历史信道特征信息中的长度为N0的第二信道特征信息,且使用更新后的历史信道特征信息进行信道恢复。
再例如:终端第一次上报长度为N0的第二信道特征信息,然后下次上报长度为N1-N0的第二信道特征信息,再下次上报长度为N2-N1的第二信道特征信息,并依次循环;基站接收到第二信道特征信息之后,使用全部的第二信道特征信息进行解码,即只有N0长度的第二信道特征信息时候用该N0长度的第二信道特征信息;有N0和N1-N0长度的第二信道特征信息时候, 基于该N0和N1-N0长度的第二信道特征信息组合出N1长度的第二信道特征信息,并基于该N1长度的第二信道特征信息进行解码,并依次迭代直到组合出长度为L的第一信道特征信息。在下一次循环的时候,还是用长度L进行解码,且用新的N0替换历史信道特征信息中的对应N0的信道特征信息,并依此更新迭代。
在实际应用中,目标AI网络模型与第一AI网络模型可以由网络侧设备联合训练得到,且一个目标AI网络模型可以与至少一个第一AI网络模型对应,其中,每一个第一AI网络模型具有各自对应的长度,这样,在确定第二长度之后,可以采用与该第二长度对应的第一AI网络模型对第二信道特征信息进行解码,以实现信道恢复。
可选地,所述第二长度的第二信道特征信息包括以下至少一项:
所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
选项一,在所述第二长度的第二信道特征信息包括所述第一信道特征信息中的前N个比特或系数的情况下,终端直接按照第一信道特征信息中的各个比特的排列顺序来上报N个比特或系数的第二信道特征信息,例如:假设N等于100bit,则上报所述第一信道特征信息中的前100bit。
选项二,在所述第二长度的第二信道特征信息包括所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数的情况下,可以对第一信道特征信息中的每一比特或每一个比特区间或包含的系数进行重要性等级划分,这样,终端可以优先向网络侧设备上报第一信道特征信息中重要性等级较高的N个比特或系数。
选项三,在所述第二长度的第二信道特征信息包括所述第一信道特征信息中除了已上报的第二信道特征信息之外的N个比特或系数的情况下,其与选项一的区别在于,在终端在进行多次信道特征信息上报的过程中,采用选项三的上报方式可以避免信道特征信息的重复上报。例如:终端进行两次信 道特征信息上报,第一次信道特征信息上报对应的第二长度等于100bit,第二次信道特征信息上报对应的第二长度等于200bit。则采用选项一时,终端第一次可以上报第一信道特征信息中的第0~99bit,第二次可以上报第一信道特征信息中的第0~199bit;而采用选项三时,终端第一次可以上报第一信道特征信息中的第0~99bit,第二次可以上报第一信道特征信息中的第100bit之后的另一个200bit。
需要说明的是,在实施中,上述选项一至选项三中的至少两项可以组合,例如:在所述第二长度的第二信道特征信息包括选项一和选定三时,所述终端第一次上报的第二信道特征信息可以是第一信道特征信息中的第0~(N0-1)比特,第二次上报的第二信道特征信息可以是第一信道特征信息中的0~(N0-1)部分和N0-(L-1)中的N1-N0长度,其中,L表示第一长度,N0表示第一次上报使用的第二长度,N1表示第二次上报使用的第二长度。在实施中第二次上报的第二信道特征信息既可以包含第一次上报的比特内容,还可以包含额外的N1-N0长度的内容,且0~(N0-1)部分和N0-(L-1)中的N1-N0长度可以是连续或者互不连续的两段信道特征信息比特。
在实施中,上述第二长度可以由网络侧设备指示或者由终端根据协议约定的条件来确定第二长度。
作为一种可选的实施方式,在所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
所述终端接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
在实施中,上述第一编码标识可以理解为第一AI网络模型对应的编码长度的标识信息。这样,基于该第一编码标识可以确定终端需要上报多少编码长度的第二信道特征信息。例如:一个目标AI网络模型对应K个第一AI网络模型,K个第一AI网络模型的输入分别是目标AI网络模型输出的部分或全部信道特征信息,K个第一AI网络模型的输入长度分别为N1,N2到NK,则上述第一编码标识可以是Ni中的i或i-1。在实施中,K个第一AI网络模型的输入长度可以是协议约定的,网络侧设备和终端都已知K个第一AI网 络模型的输入长度,这样,网络侧设备向终端指示一个编码标识时,终端能够根据该编码标识确定需要上报的第二长度,从而在编码后的长度为第一长度的第一信道特征信息中截取长度为Ni的部分,其中i是网络侧设备指示的第一编码标识。
其中,上述第一指示信息由高层信令配置,例如:通过无线资源控制(Radio Resource Control,RRC)信令或媒体接入控制(Medium Access Control,MAC)控制单元(Control Element,CE)等提前配置第二长度,这样,终端可以在每次信道特征信息上报中都上报相同长度的第二信道特征信息。
当然,在所述第二信道特征信息携带于信道状态信息CSI报告中的情况下,上述第一指示信息也可以是CSI报告配置(CSI report config)中的指示信息,或者网络侧设备可以配置每个CSI资源(resource)对应的长度,则所述第一指示信息所指示的第二长度可以理解为所述终端使用的CSI资源对应的长度,在此对第一指示信息不作具体限定。
本实施方式中,可以由网络侧设备向终端指示第二长度,以使终端按照网络侧设备的指示来从第一信道特征信息中截取对应长度的第二长度的第二信道特征信息,并上报给网络侧设备。
作为另一种可选的实施方式,在所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
所述终端根据所述目标信道信息对应的信道特性和信道条件中的至少一项,确定所述第二长度。
在实施中,上述终端根据所述目标信道信息对应的信道特性和信道条件中的至少一项,确定所述第二长度,可以是终端根据目标信道信息确定目标信道的信道特性,从而确定该信道特性对应的第二长度;和/或,终端可以根据目标信道信息判断目标信道的信道质量等是否满足预设的信道条件,从而根据判断结果确定对应的第二长度。
本实施方式中,与网络侧设备向终端指示第二长度的实施方式的不同之处在于,终端能够根据目标信道信息确定第二长度,从而向网络侧设备上报该第二长度的第二信道特征信息。
在一种可选的实施方式中,所述终端根据所述目标信道信息对应的信道 特性,确定所述第二长度,包括:
所述终端根据第一关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的长度为所述第二长度,其中,所述第一关联关系包括所述目标信道参数的各个取值或各个取值范围与长度之间的关联关系;或者,
所述终端根据第二关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的编码标识对应的长度为所述第二长度,其中,所述第二关联关系包括所述目标信道参数的各个取值或各个取值范围与编码标识之间的关联关系。
在实施中,与上述第一指示信息可以指示第二长度或者该第二长度对应的第一编码标识相对应的,终端也可以根据信道参数的值与长度或编码标识之间的关联关系来确定目标信道参数关联的第二长度。
其中,所述目标信道的目标信道参数可以包括以下至少一项:
所述目标信道是视距(Line of Sight,LOS)传播或非视距传播(Non-Line of Sight,NLOS);
所述目标信道的有效时延径的个数;
所述目标信道的两个目标径的时延间距;
所述目标信道的有效波束的数量,所述有效波束包括功率大于第一阈值的离散傅里叶变换(Discrete Fourier Transform,DFT)正交基对应的波束。
选项一,上述目标信道是视距传播时,其信道质量相较非视距传播时的信道质量更好,可以在目标信道是视距传播时上报较短的第二信道特征信息,而在目标信道是非视距传播时,上报较长的第二信道特征信息,例如:假设K=2,LOS使用N0,NLOS使用N1,N0<N1,特别的,N1=L,其中,K表示第二长度的取值个数,L表示第一长度;
选项二,所述目标信道的有效时延径的个数越多,则上报的第二信道特征信息可以越长,其中,有效时延径包括以下至少一项:对应的功率或幅度大于第一阈值的时延径、对应的功率或幅度为极大值的时延径。例如:如图5所示功率图谱中,假设有效时延径包括功率或幅度大于第一阈值的时延径,则有效时延径为分别位于时延域位置:-2,0,1,4处的四条径;假设有效时延径 包括功率或幅度为极大值的时延径,则有效时延径为分别位于时延域位置:-2,0,4处的三条径。
选项三,所述目标信道的两个目标径的时延间距越大,则上报的第二信道特征信息可以越长。其中,两个目标径可以是目标信道的任一两个径,例如:两个极大值对应的径,该两个目标径的时延间距能够反映目标信达包含的径在频域上的集中强度。
选项四,所述目标信道的有效波束的数量越多,则上报的第二信道特征信息可以越长。
本实施方式中,终端能够根据检测到的目标信道的目标信道参数的取值,来确定第二长度,以使上报的第二长度的第二信道特征信息与目标信道的信道状态相匹配。
在另一种可选的实施方式中,所述方法还包括:
所述终端接收来自所述网络侧设备的K个第一AI网络模型的相关信息,其中,所述K个第一AI网络模型与所述目标AI网络模型对应,所述K个第一AI网络模型分别用于解码各自对应的长度的信道特征信息;
所述终端根据信道条件,确定所述第二长度,包括:
所述终端从所述第一信道特征信息中截取K个第二信道特征信息,并分别通过K个所述第一AI网络模型将各自对应的长度的所述第二信道特征信息处理成第一信道信息;
所述终端获取K个所述第一信道信息分别与所述目标信道信息的匹配程度;
所述终端在确定目标第一信道信息与所述目标信道信息的匹配程度满足预设条件的情况下,确定所述第二长度等于用于处理得到所述目标第一信道信息的第一AI网络模型对应的长度,其中,K个所述第一AI网络模型处理得到的K个第一信道信息包括所述目标第一信道信息。
在实施中,上述第一AI网络模型的相关信息可以是模型参数、模型配置、模型的标识信息等,终端能够根据该相关信息确定网络侧设备会采用哪一个第一AI网络模型去解码第二信道特征信息。然后,终端可以采用该第一AI网络模型或该第一AI网络模型的简化网络模型去模拟网络侧设备对对应长 度的第二信道特征信息的解码过程,从而将模拟的解码结果(即第一信道信息)与目标信道信息进行比对,以确定两者之间的匹配程度。
其中,第一信道信息与目标信道信息的匹配程度越高,则表示采用的第一AI网络模型能够更加准确的恢复目标信道信息。在实际应用中,上述目标第一信道信息与所述目标信道信息的匹配程度满足预设条件,可以理解为:得出目标第一信道信息的第一AI网络模型对对应的长度的第二信道特征信息的解码结果能够满足业务需求或通信质量需求等。
可选地,终端设备可以遍历每一个第一AI网络模型,以确定每一个第一AI网络模型对各自对应的长度的第二信道特征信息的解码结果与所述目标信道信息的匹配程度是否满足预设条件,在实施中,可能存在有至少两个第一AI网络模型得出的第一信道信息与所述目标信道信息的匹配程度满足预设条件的情况,此时,可以进一步从该至少两个第一AI网络模型各自对应的长度中选择最小的一个作为第二长度,从而从第一信道特征信息中截取该第二长度的第二信道特征信息,并上报网络侧设备。
当然,终端设备也可以依次确定第一AI网络模型对对应的长度的第二信道特征信息的解码结果与所述目标信道信息的匹配程度,并在确定某一个第一AI网络模型对对应的长度的第二信道特征信息的解码结果与所述目标信道信息的匹配程度满足预设条件的情况下,确定第二长度为该第一AI网络模型对对应的长度,这样,可以减少确定第二长度的计算量。
可选地,所述目标第一信道信息与所述目标信道信息的匹配程度满足预设条件包括以下至少一项:
所述目标第一信道信息与所述目标信道信息的相关性大于或者等于预设相关性;
所述目标第一信道信息的信道容量大于或者等于所述目标信道信息的信道容量的第一预设值倍,所述第一预设值大于0且小于或者等于1;
所述目标第一信道信息为所述K个所述第一信道信息中的信道质量指示(Channel quality indicator,CQI)与所述目标信道信息的CQI相同或者最接近的一个;
所述目标第一信道信息为所述K个所述第一信道信息中的且调制和编码 方案(Modulation and coding scheme,MCS)与所述目标信道信息的MCS相同或者最接近的一个。
在实施中,上述目标第一信道信息与所述目标信道信息的相关性,可以是目标第一信道信息与所述目标信道信息的信息内容的相似性,例如:目标第一信道信息与所述目标信道信息之间的互信息。
另外,第二信道特征信息可以仅包含第一信道特征信息中的部分内容,上述第一信道信息可以仅包含目标信道信息中的部分信息,则基于不同长度和/或不同位置的第二信道特征信息所解码出的信道信息所包含的信道容量、CQI、MCS等可以不同,此时,可以优选选择得出的第一信道信息的信道容量大于目标信道信息的信道容量的第一预设值倍的第一AI网络模型的长度作为第二长度,其中,第一预设值可以是网络侧设备指示或协议约定的取值,在信道容量满足第一预设值的情况下,该第二长度的第二信道特征信息能够解码出满足业务需求和/或信道质量需求的信道信息。此外,还可以根据与所述目标信道信息中的CQI和/或MCS最接近的一个第一信道信息作为目标第一信道信息。
可选地,所述信道特征信息上报方法还包括:
所述终端向所述网络侧设备发送第二指示信息,所述第二指示信息指示所述第二长度。
本实施方式中,终端在确定第二长度时,还向网络侧设备上报该第二长度,以使网络侧设备直接采用与该第二长度对应的第一AI网络模型来解码第二信道特征信息。
需要说明的是,在实施中,在终端确定第二长度后,终端也可以不向网络侧设备上报该第二长度,此时,网络侧设备可以检测终端上报的第二信道特征信息的长度,从而采用与该长度对应的第一AI网络模型来解码第二信道特征信息,在此不作具体限定。
在实施中,CSI报告可以包括固定长度的CSI部分(例如:CSI Part1)和可变长度的CSI部分(例如:CSI Part2)。此时,上述第二指示信息可以携带于CSI报告中的固定长度的CSI部分或者可变长度的CSI部分。
此外,第二长度的第二信道特征信息也可以位于可变长度的CSI部分, 或者,一部分位于固定长度的CSI部分,另一部分位于可变长度的CSI部分。
具体的,鉴于第二长度的取值范围可以包括最小长度至第一长度之间的多个取值,而CSI报告中的固定长度的CSI部分往往仅容纳较少的长度,此时,可以将第二长度的第二信道特征信息中的最小长度的部分放置在CSI报告中的固定长度的CSI部分,该第二信道特征信息的其他部分则放置在CSI报告中的可变长度的CSI部分。在实施中,上述最小长度可以小于或者等于所述第二长度,即最小长度可以等于第二长度可以取的最小取值,例如:假设K个第一AI网络模型的输入长度分别为由短至长排列的N1~NK,则最小长度可以等于N1。在实施中,N2~NK均包含N1对应的信道特征信息,从而可以使CSI报告中的固定长度的CSI部分固定携带第一信道特征信息中的第0~(N1-1)个比特的内容,且第二长度大于N1时,可以将第二信道特征信息中的位于第(N1-1)个比特之后的内容放置在CSI报告中的可变长度的CSI部分。
当然,以上举例仅作为示例,在实际应用中第二长度的第二信道特征信息中的最小长度的部分在第二信道特征信息中的位置可以由协议约定,例如:所述第二信道特征信息中的最小长度的部分可以包括以下至少一项:
所述第二信道特征信息中的前X比特,X等于所述最小长度;
所述第二信道特征信息中重要性等级大于预设等级的X比特。
举例一,所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中的可变长度的CSI部分。
举例二,所述第二长度的第二信道特征信息中的最小长度的部分和所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度的部分携带于所述CSI报告中的可变长度的CSI部分。
举例三,所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
<作为一种可选的实施方式二>
所述终端向网络侧设备发送第二信道特征信息,包括:
所述终端在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
在实施中,上述M条第二信道特征信息可以分为M次上报,即终端进行M次信道特征信息上报,每一次上报一条第二信道特征信息。当然,在实际应用中终端也可以一次上报至少两个第二信道特征信息,在此不作具体限定。
例如:终端可以在M次信道特征信息上报中,以长度由小到大的顺序,轮流向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息。这样,网络侧设备在根据接收的第二信道特征信息进行信道恢复的过程中,可以逐渐的提升信道恢复的精度。
再例如:终端可以在M次信道特征信息上报中,分别根据当前的信道环境来确定该M次信道特征信息上报各自对应的第二长度,此时,M条第二信道特征信息的第二长度可以相同也可以不同,这样,在经历一段时间后,网络侧设备可能获取M条长度互不相同的第二信道特征信息(即历史信道特征信息包括终端在历史时间段内上报的M条长度互不相同的第二信道特征信息),这样,后续的信道恢复过程中,网络侧设备可以根据终端当前上报的第二信道特征信息来更新历史信道特征信息,并根据更新后的全部的历史信道特征信息来进行信道恢复。也就是说,全部的历史信道特征信息的长度可以与第一信道特征信息的长度相同,但是,历史信道特征信息中的一部分内容为当前的信道特征信息,另一部分内容为终端曾经上报过的信道特征信息。
可选地,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
或者,
所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
在一种可选的实施方式中,上述M次信道特征信息上报的时频资源位置可以在同一个CSI报告配置信息(CSI report config)来配置,即一个CSI report  config配置M个信道特征信息上报的时频资源位置,终端在每个时频资源位置上报第二信道特征信息。
这样,可以简化M次信道特征信息上报的时频资源位置的配置过程。
在另一种可选的实施方式中,上述M次信道特征信息上报的时频资源位置可以在M个CSI报告配置信息(CSI report config)来配置,即配置M个CSI report config,每个CSI report config可以用于配置一个信道特征信息上报的时频资源位置。
这样,可以更加灵活的配置每一次信道特征信息上报的时频资源位置。
作为一种可选的实施方式,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
或者,
所述M次信道特征信息上报的第二信道特征信息分别包括所述第一信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
在一种可选的实施方式中,上述所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增。此时,所述终端在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,包括:
所述终端在M次信道特征信息上报中,按照所述第二信道特征信息的长度由短至长的排列顺序,分别向网络侧设备发送第二信道特征信息。
在网络侧,网络侧设备可以利用该由短至长的顺序依次上报的第二信道特征信息逐步的提升恢复的信道信息的准确度。
在另一种可选的实施方式中,上述M次信道特征信息上报的第二信道特征信息分别包括所述第一信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。此时,所述终端在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,包括:
所述终端在M次信道特征信息上报中,按照所述第二信道特征信息在所述第一信道特征信息中的排列顺序,分别向网络侧设备发送第二信道特征信 息。
这样,终端可以在多次信道特征信息上报过程中,分别上报互不重叠的信道特征信息内容,在网络侧,网络侧设备可以存储终端已经上报的历史信道特征信息,并在终端上报第二信道特征信息时,利用该第二信道特征信息对已经上报的历史信道特征信息进行更新,并利用更新后的历史信道特征信息作为一个整体来恢复的信道信息,其可以降低终端上报的第二信道特征信息的信息量,且还可以提升网络侧设备进行信道恢复时所采用的历史信道特征信息的信息量。
在本申请实施例中,终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。这样,在不同的信道环境下,终端能够根据信道信息的长度自适应的采用同一AI网络模型进行编码,且仅向网络侧设备上报相应长度的部分信道特征信息,以使网络侧采用预先配置的与该长度相对应的AI网络模型来解码该部分信道特征信息,且可以降低终端和网络侧设备之间传递AI网络模型的开销。
请参阅图6,本申请实施例提供的一种信道特征信息恢复方法,其执行主体可以是网络侧设备,该终端可以是如图1中列举的各种类型的网络侧设备12,或者是除了如图1所示实施例中列举的网络侧设备类型之外的其他网络侧设备,在此不作具体限定。如图6所示,该信道特征信息恢复方法可以包括以下步骤:
步骤601、网络侧设备接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息。
在实施中,上述第一信道特征信息、第二信道特征信息和目标信道信息分别与如图2所示方法实施例中的第一信道特征信息、第二信道特征信息和目标信道信息具有相同的含义,在此不再赘述。
步骤602、所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
在实施中,上述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,可以是:网络侧设备采用一个与第二信道特征信息的长度对应的第一AI网络模型对该第二信道特征信息进行处理,得到所述目标信道信息;或者,网络侧设备采用至少两个与第二信道特征信息对应的第一AI网络模型对该第二信道特征信息进行处理,得到所述目标信道信息。
作为一种可选的实施方式,所述网络侧设备接收来自终端的第二信道特征信息,包括:
所述网络侧设备接收来自终端的从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
上述第二长度的第二信道特征信息与如图2所示方法实施例中的第二长度的第二信道特征信息具有相同含义,且同样表示,终端可以根据网络侧设备的指示确定第二长度,或者根据协议约定的条件确定第二长度,并向网络侧设备上报该第二长度的第二信道特征信息,在此不作具体限定。
在一种可能的实现方式中,所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,包括:
所述网络侧设备采用与所述第二长度的第二信道特征信息对应的第一AI网络模型对所述第二长度的第二信道特征信息进行处理,得到所述目标信道信息。
例如:如图7a所示,假设1个编码器与5个解码器(分别为解码器1至解码器5)对应,且每一个解码器具有各自的第一AI网络模型,每一个第一AI网络模型具有各自对应的第二长度:N0~N4,这样,每一个解码器通过对各自对应的第二长度的第二信道特征信息进行解码,便可以得出目标信道信息。
本实施方式中,网络侧设备每次采用与第二长度对应的一个第一AI网络模型进行信道恢复。
在另一种可能的实现方式中,所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,包括:
在所述网络侧设备存储有所述终端的历史信道特征信息的情况下,所述 网络侧设备根据所述第二长度的第二信道特征信息更新所述历史信道特征信息;
所述网络侧设备采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息。
在实施中,上述网络侧设备采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息,可以是:采用一个与更新后的所述历史信道特征信息的长度对应的第一AI网络模型对该更新后的所述历史信道特征信息进行处理,得到所述目标信道信息,例如:如图7a所示,假设更新后的历史信道特征信息的比特长度与解码器5对应,则采用解码器5中的第一AI网络模型对更新后的所述历史信道特征信息进行解码。
当然,上述网络侧设备采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息,也可以是:采用与更新后的所述历史信道特征信息的长度和/或在第一信道特征信息中的位置对应的至少一个第一AI网络模型对该更新后的所述历史信道特征信息进行处理,得到所述目标信道信息,例如:如图7b所示,假设1个编码器与4个解码器(分别为解码器1至解码器4)对应,且每一个解码器具有各自的第一AI网络模型,而每一个第一AI网络模型对应的第二长度相同(假设第二长度为N比特)但是互不重叠,这样,若更新后的历史信道特征信息包括与解码器1和解码器2分别对应的第二信道特征信息,则网络侧设备可以采用解码器1中的第一AI网络模型对对应的第二信道特征信息进行解码,并采用解码器2中的第一AI网络模型对对应的另第二信道特征信息进行解码,最终结合解码器1和解码器2的解码结果来得到目标信道信息。即每个解码器对应信道特征信息的增量部分,多个解码器的结果相组合来恢复信道信息。
可选地,所述第二长度的第二信道特征信息包括以下至少一项:
所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
可选地,在所述网络侧设备接收来自终端的从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
所述网络侧设备向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
可选地,所述第一指示信息由高层信令配置;或者,
所述第二信道特征信息携带于信道状态信息CSI报告中,且所述第一指示信息是CSI报告配置中的指示信息,或者所述第一指示信息与所述终端使用的CSI资源对应。
可选地,所述信道特征信息恢复方法还包括:
所述网络侧设备接收来自所述终端的第二指示信息,所述第二指示信息指示所述第二长度。
可选地,所述第二指示信息携带于CSI报告中固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中可变长度的CSI部分;或者,
所述第二长度的第二信道特征信息中的最小长度部分和所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度部分携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
可选地,所述最小长度小于或者等于所述第二长度。
可选地,所述网络侧设备接收来自终端的第二信道特征信息,包括:
所述网络侧设备在所述终端的M次信道特征信息上报中,分别接收第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
可选地,所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,包括:
所述网络侧设备分别采用M个第一AI网络模型对各自对应的长度的第二信道特征信息进行处理,得到所述目标信道信息,所述M个第一AI网络模型各自对应的长度包括所述M次信道特征信息上报的第二信道特征信息的长度;或者,
所述网络侧设备采用一个第一AI网络模型对所述M次信道特征信息上报的第二信道特征信息进行处理,得到所述目标信道信息。
在一种可选的实施方式中,上述网络侧设备分别采用M个第一AI网络模型对各自对应的长度的第二信道特征信息进行处理,得到所述目标信道信息,与图7b所示实施例相似,且具有相同的有益效果,在此不再赘述。
在另一种可选的实施方式中,上述网络侧设备采用一个第一AI网络模型对所述M次信道特征信息上报的第二信道特征信息进行处理,得到所述目标信道信息,与如图7a所示实施例相似,且具有相同的有益效果,在此不再赘述。
可选地,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
或者,
所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
可选地,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
或者,
所述M次信道特征信息上报的第二信道特征信息分别包括所述信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
可选地,所述网络侧设备接收来自终端的M次信道特征信息上报的第二信道特征信息,包括:
所述网络侧设备在所述终端的M次信道特征信息上报中,按照预设顺序分别接收来自终端的第二信道特征信息,所述预设顺序包括:
所述第二信道特征信息的长度由短至长的排列顺序;
所述第二信道特征信息在所述第一信道特征信息中的排列顺序。
本申请实施例中,网络侧设备能够采用终端上报的第一信道特征信息的部分内容(即第二信道特征信息)的长度对应的第一AI网络模型来对该第二信道特征信息进行信道恢复,可以降低终端和网络侧设备之间传递AI网络模型的开销。
为了便于说明本申请实施例提供的信道特征信息上报方法和信道特征信息恢复方法,本申请实施例通过以下信道特征信息的交互流程作为举例来说明本申请实施例提供的信道特征信息上报方法和信道特征信息恢复方法,本实施例中,信道特征信息的交互流程包括以下步骤:
步骤1、终端在网络指定的时频域位置检测CSI-RS或TRS,并进行信道估计,得到目标信道信息;
步骤2、终端通过目标AI网络模型(即AI编码网络模型)将目标信道信息编码为第一信道特征信息;
步骤3、终端选择第一信道特征信息的部分内容作为待上报的第二信道特征信息;
步骤4、终端将待上报的第二信道特征信息和其他控制信息组合为上行控制信息(Uplink Control Information,UCI),或者将待上报的第二信道特征信息作为UCI;
步骤5、终端根据UCI的长度对UCI进行分割,并添加循环冗余校验(Cyclic redundancy check,CRC)比特;
步骤6、终端对添加CRC比特的UCI进行信道编码;
步骤7、终端对UCI进行速率匹配;
步骤8、终端对UCI进行码块关联;
步骤9、终端将UCI映射到物理上行控制信道(Physical Uplink Control Channel,PUCCH)或物理上行共享信道(Physical Uplink Shared Channel,PUSCH)进行上报。
需要说明的是,上述信道特征信息的交互流程中,部分步骤的顺序可以调整或者省略,在此不构成具体限定。
本申请实施例提供的信道特征信息上报方法,执行主体可以为信道特征 信息上报装置。本申请实施例中以信道特征信息上报装置执行信道特征信息上报方法为例,说明本申请实施例提供的信道特征信息上报装置。
请参阅图8,本申请实施例提供的一种信道特征信息上报装置,可以是终端内的装置,如图8所示,该信道特征信息上报装置800可以包括以下模块:
第一处理模块801,用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;
第一发送模块802,用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
可选的,第一发送模块802,具体用于:
向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
可选的,所述第一长度为所述第一信道特征信息的比特数,或者,所述第一长度为所述第一信道特征信息的包含的系数的个数;和/或,
所述第二长度为所述第二信道特征信息的比特数,或者,所述第二长度为所述第二信道特征信息的包含的系数的个数。
可选的,所述第二长度的第二信道特征信息包括以下至少一项:
所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
可选的,信道特征信息上报装置800还包括:
第一接收模块,用于接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
可选的,所述第一指示信息由高层信令配置;或者,
所述第二信道特征信息携带于信道状态信息CSI报告中,且所述第一指示信息是CSI报告配置中的指示信息,或者所述第一指示信息与所述终端使 用的CSI资源对应。
可选的,信道特征信息上报装置800还包括:
确定模块,用于根据所述目标信道信息对应的信道特性和信道条件中的至少一项,确定所述第二长度。
可选的,信道特征信息上报装置800还包括:
第三发送模块,用于向所述网络侧设备发送第二指示信息,所述第二指示信息指示所述第二长度。
可选的,所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二长度的第二信道特征信息中的最小长度的部分和所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度的部分携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
可选的,所述最小长度小于或者等于所述第二长度。
可选的,所述确定模块,具体用于执行以下任一项:
根据第一关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的长度为所述第二长度,其中,所述第一关联关系包括所述目标信道参数的各个取值或各个取值范围与长度之间的关联关系;
根据第二关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的编码标识对应的长度为所述第二长度,其中,所述第二关联关系包括所述目标信道参数的各个取值或各个取值范围与编码标识之间的关联关系。
可选的,所述目标信道的目标信道参数包括以下至少一项:
所述目标信道是视距传播或非视距传播;
所述目标信道的有效时延径的个数;
所述目标信道的两个目标径的时延间距;
所述目标信道的有效波束的数量,所述有效波束包括功率大于第一阈值的离散傅里叶变换DFT正交基对应的波束。
可选的,所述有效时延径包括以下至少一项:
对应的功率或幅度大于第一阈值的时延径;
对应的功率或幅度为极大值的时延径。
可选的,信道特征信息上报装置800还包括:
第四接收模块,用于接收来自所述网络侧设备的K个第一AI网络模型的相关信息,其中,所述K个第一AI网络模型与所述目标AI网络模型对应,所述K个第一AI网络模型分别用于解码各自对应的长度的信道特征信息;
所述确定模块,包括:
第二处理单元,用于从所述第一信道特征信息中截取K个第二信道特征信息,并分别通过K个所述第一AI网络模型将各自对应的长度的所述第二信道特征信息处理成第一信道信息;
获取单元,用于获取K个所述第一信道信息分别与所述目标信道信息的匹配程度;
确定单元,用于在确定目标第一信道信息与所述目标信道信息的匹配程度满足预设条件的情况下,确定所述第二长度等于用于处理得到所述目标第一信道信息的第一AI网络模型对应的长度,其中,K个所述第一AI网络模型处理得到的K个第一信道信息包括所述目标第一信道信息。
可选的,所述目标第一信道信息与所述目标信道信息的匹配程度满足预设条件包括以下至少一项:
所述目标第一信道信息与所述目标信道信息的相关性大于或者等于预设相关性;
所述目标第一信道信息的信道容量大于或者等于所述目标信道信息的信道容量的第一预设值倍,所述第一预设值大于0且小于或者等于1;
所述目标第一信道信息为所述K个所述第一信道信息中的信道质量指示CQI与所述目标信道信息的CQI相同或者最接近的一个;
所述目标第一信道信息为所述K个所述第一信道信息中的且调制和编码方案MCS与所述目标信道信息的MCS相同或者最接近的一个。
可选的,第一发送模块802,具体用于:
在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
可选的,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
或者,
所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
可选的,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
或者,
所述M次信道特征信息上报的第二信道特征信息分别包括所述第一信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
可选的,第一发送模块802,具体用于:
在M次信道特征信息上报中,按照预设顺序分别向网络侧设备发送第二信道特征信息,所述预设顺序包括:
所述第二信道特征信息的长度由短至长的排列顺序;
所述第二信道特征信息在所述第一信道特征信息中的排列顺序。
可选的,信道特征信息上报装置800还包括:
信道估计模块,用于对信道状态信息-参考信号CSI-RS或跟踪参考信号TRS进行信道估计得到所述目标信道信息;或者,
预处理模块,用于对信道估计得到的信道信息进行预处理,得到所述目标信道信息。
本申请实施例中的信道特征信息上报装置800可以是电子设备,例如具有操作***的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是终端,也可以为除终端之外的其他设备。示例性的,终端 可以包括但不限于上述所列举的终端11的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例不作具体限定。
本申请实施例提供的信道特征信息上报装置800能够实现图2所示方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例提供的信道特征信息恢复方法,执行主体可以为信道特征信息恢复装置。本申请实施例中以信道特征信息恢复装置执行信道特征信息恢复方法为例,说明本申请实施例提供的信道特征信息恢复装置。
请参阅图9,本申请实施例提供的一种信道特征信息恢复装置,可以是网络侧设备内的装置,如图9所示,该信道特征信息恢复装置900可以包括以下模块:
第二接收模块901,用于接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;
第二处理模块902,用于采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
可选的,第二接收模块901具体用于:
接收来自终端的从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
可选的,所述第一长度为所述第一信道特征信息的比特数,或者,所述第一长度为所述第一信道特征信息的包含的系数的个数;和/或,
所述第二长度为所述第二信道特征信息的比特数,或者,所述第二长度为所述第二信道特征信息的包含的系数的个数。
可选的,第二处理模块902具体用于:
采用与所述第二长度的第二信道特征信息对应的第一AI网络模型对所述第二长度的第二信道特征信息进行处理,得到所述目标信道信息。
可选的,第二处理模块902,包括:
更新单元,用于在所述网络侧设备存储有所述终端的历史信道特征信息的情况下,根据所述第二长度的第二信道特征信息更新所述历史信道特征信息;
第一处理单元,用于采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息。
可选的,所述第二长度的第二信道特征信息包括以下至少一项:
所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
可选的,信道特征信息恢复装置900还包括:
第四发送模块,用于向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
可选的,所述第一指示信息由高层信令配置;或者,
所述第二信道特征信息携带于信道状态信息CSI报告中,且所述第一指示信息是CSI报告配置中的指示信息,或者所述第一指示信息与所述终端使用的CSI资源对应。
可选的,信道特征信息恢复装置900还包括:
第三接收模块,用于接收来自所述终端的第二指示信息,所述第二指示信息指示所述第二长度。
可选的,所述第二指示信息携带于CSI报告中固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中可变长度的CSI部分;或者,
所述第二长度的第二信道特征信息中的最小长度部分和所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度部分携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
可选的,所述最小长度小于或者等于所述第二长度。
可选的,第二接收模块901,具体用于:
在所述终端的M次信道特征信息上报中,分别接收第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
可选的,第二处理模块902,具体用于执行以下任一项:
分别采用M个第一AI网络模型对各自对应的长度的第二信道特征信息进行处理,得到所述目标信道信息,所述M个第一AI网络模型各自对应的长度包括所述M次信道特征信息上报的第二信道特征信息的长度;
采用一个第一AI网络模型对所述M次信道特征信息上报的第二信道特征信息进行处理,得到所述目标信道信息。
可选的,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
或者,
所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
可选的,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
或者,
所述M次信道特征信息上报的第二信道特征信息分别包括所述信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
可选的,第二接收模块901,具体用于:
在所述终端的M次信道特征信息上报中,按照预设顺序分别接收来自终端的第二信道特征信息,所述预设顺序包括:
所述第二信道特征信息的长度由短至长的排列顺序;
所述第二信道特征信息在所述第一信道特征信息中的排列顺序。
本申请实施例中的信道特征信息恢复装置900可以是电子设备,例如具有操作***的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是网络侧设备,也可以为除网络侧设备之外的其他设备。示例性的,终端可以包括但不限于上述所列举的网络侧设备12的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例不作具体限定。
本申请实施例提供的信道特征信息恢复装置900能够实现图6所示方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
可选的,如图10所示,本申请实施例还提供一种通信设备1000,包括处理器1001和存储器1002,存储器1002上存储有可在所述处理器1001上运行的程序或指令,例如,该通信设备1000为终端时,该程序或指令被处理器1001执行时实现上述信道特征信息上报方法实施例的各个步骤,且能达到相同的技术效果。该通信设备1000为网络侧设备时,该程序或指令被处理器1001执行时实现上述信道特征信息恢复方法实施例的各个步骤,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供一种终端,包括处理器和通信接口,所述处理器用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;所述通信接口用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
该终端实施例与上述终端侧方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该终端实施例中,且能达到相同的技术效果。
具体地,图11为实现本申请实施例的一种终端的硬件结构示意图。
该终端1100包括但不限于:射频单元1101、网络模块1102、音频输出单元1103、输入单元1104、传感器1105、显示单元1106、用户输入单元1107、接口单元1108、存储器1109以及处理器1110等中的至少部分部件。
本领域技术人员可以理解,终端1100还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理***与处理器1110逻辑相连,从而通 过电源管理***实现管理充电、放电、以及功耗管理等功能。图11中示出的终端结构并不构成对终端的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。
应理解的是,本申请实施例中,输入单元1104可以包括图形处理单元(Graphics Processing Unit,GPU)11041和麦克风11042,图形处理器11041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1106可包括显示面板11 061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板11061。用户输入单元1107包括触控面板11071以及其他输入设备11072中的至少一种。触控面板11071,也称为触摸屏。触控面板11071可包括触摸检测装置和触摸控制器两个部分。其他输入设备11072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。
本申请实施例中,射频单元1101接收来自网络侧设备的下行数据后,可以传输给处理器1110进行处理;另外,射频单元1101可以向网络侧设备发送上行数据。通常,射频单元1101包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器1109可用于存储软件程序或指令以及各种数据。存储器1109可主要包括存储程序或指令的第一存储区和存储数据的第二存储区,其中,第一存储区可存储操作***、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外,存储器1109可以包括易失性存储器或非易失性存储器,或者,存储器1109可以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),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,DDRSDRAM)、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)和直接内存总线随机存取存储器(Direct Rambus RAM,DRRAM)。本申请实施例中的存储器1109包括但不限于这些和任意其它适合类型的存储器。
处理器1110可包括一个或多个处理单元;可选的,处理器1110集成应用处理器和调制解调处理器,其中,应用处理器主要处理涉及操作***、用户界面和应用程序等的操作,调制解调处理器主要处理无线通信信号,如基带处理器。可以理解的是,上述调制解调处理器也可以不集成到处理器1110中。
其中,处理器1110,用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;
射频单元1101,用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
可选地,射频单元1101执行的所述向网络侧设备发送第二信道特征信息,包括:
向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
可选地,所述第一长度为所述第一信道特征信息的比特数,或者,所述第一长度为所述第一信道特征信息的包含的系数的个数;和/或,
所述第二长度为所述第二信道特征信息的比特数,或者,所述第二长度为所述第二信道特征信息的包含的系数的个数。
可选地,所述第二长度的第二信道特征信息包括以下至少一项:
所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
可选地,射频单元1101在执行所述向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,还用于接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第二长度和/或 第一编码标识,所述第一编码标识与所述第二长度关联。
可选地,所述第一指示信息由高层信令配置;或者,
所述第二信道特征信息携带于信道状态信息CSI报告中,且所述第一指示信息是CSI报告配置中的指示信息,或者所述第一指示信息与所述终端使用的CSI资源对应。
可选地,在射频单元1101执行所述向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,处理器1110,还用于根据所述目标信道信息对应的信道特性和信道条件中的至少一项,确定所述第二长度。
可选地,射频单元1101,还用于向所述网络侧设备发送第二指示信息,所述第二指示信息指示所述第二长度。
可选地,所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二长度的第二信道特征信息中的最小长度的部分和所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度的部分携带于所述CSI报告中的可变长度的CSI部分;或者,
所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
可选地,所述最小长度小于或者等于所述第二长度。
可选地,处理器1110执行的所述根据所述目标信道信息对应的信道特性,确定所述第二长度,包括:
根据第一关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的长度为所述第二长度,其中,所述第一关联关系包括所述目标信道参数的各个取值或各个取值范围与长度之间的关联关系;或者,
根据第二关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的编码标识对应的长度为所述第二长度,其中,所述第二关联关系包括所述目标信道参数的各个取值或各个取值范围与编码标识之间的关 联关系。
可选地,所述目标信道的目标信道参数包括以下至少一项:
所述目标信道是视距传播或非视距传播;
所述目标信道的有效时延径的个数;
所述目标信道的两个目标径的时延间距;
所述目标信道的有效波束的数量,所述有效波束包括功率大于第一阈值的离散傅里叶变换DFT正交基对应的波束。
可选地,所述有效时延径包括以下至少一项:
对应的功率或幅度大于第一阈值的时延径;
对应的功率或幅度为极大值的时延径。
可选地,射频单元1101,还用于接收来自所述网络侧设备的K个第一AI网络模型的相关信息,其中,所述K个第一AI网络模型与所述目标AI网络模型对应,所述K个第一AI网络模型分别用于解码各自对应的长度的信道特征信息;
处理器1110执行的所述根据信道条件,确定所述第二长度,包括:
处理器1110从所述第一信道特征信息中截取K个第二信道特征信息,并分别通过K个所述第一AI网络模型将各自对应的长度的所述第二信道特征信息处理成第一信道信息;
处理器1110获取K个所述第一信道信息分别与所述目标信道信息的匹配程度;
处理器1110在确定目标第一信道信息与所述目标信道信息的匹配程度满足预设条件的情况下,确定所述第二长度等于用于处理得到所述目标第一信道信息的第一AI网络模型对应的长度,其中,K个所述第一AI网络模型处理得到的K个第一信道信息包括所述目标第一信道信息。
可选地,所述目标第一信道信息与所述目标信道信息的匹配程度满足预设条件包括以下至少一项:
所述目标第一信道信息与所述目标信道信息的相关性大于或者等于预设相关性;
所述目标第一信道信息的信道容量大于或者等于所述目标信道信息的信 道容量的第一预设值倍,所述第一预设值大于0且小于或者等于1;
所述目标第一信道信息为所述K个所述第一信道信息中的信道质量指示CQI与所述目标信道信息的CQI相同或者最接近的一个;
所述目标第一信道信息为所述K个所述第一信道信息中的且调制和编码方案MCS与所述目标信道信息的MCS相同或者最接近的一个。
可选地,射频单元1101执行的所述向网络侧设备发送第二信道特征信息,包括:
在所述终端的M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
可选地,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
或者,
所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
可选地,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
或者,
所述M次信道特征信息上报的第二信道特征信息分别包括所述第一信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
可选地,射频单元1101执行的所述在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,包括:
在M次信道特征信息上报中,按照预设顺序分别向网络侧设备发送第二信道特征信息,所述预设顺序包括:
所述第二信道特征信息的长度由短至长的排列顺序;
所述第二信道特征信息在所述第一信道特征信息中的排列顺序。
可选地,在处理器1110执行所述采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息之前:
射频单元1101,还用于对信道状态信息-参考信号CSI-RS或跟踪参考信号TRS进行信道估计得到所述目标信道信息;或者,
处理器1110,还用于对信道估计得到的信道信息进行预处理,得到所述目标信道信息。
本申请实施例提供的终端1100,能够执行如图8所示信道特征信息上报装置中的各模块执行的各个过程,且能够取得相同的有益效果,为避免重复,在此不再赘述。
本申请实施例还提供一种网络侧设备,包括处理器和通信接口,所述通信接口用于接收来自终端的第二信道特征信息,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;所述处理器用于采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
该网络侧设备实施例与上述网络侧设备方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中,且能达到相同的技术效果。
具体地,本申请实施例还提供了一种网络侧设备。如图12所示,该网络侧设备1200包括:天线1201、射频装置1202、基带装置1203、处理器1204和存储器1205。天线1201与射频装置1202连接。在上行方向上,射频装置1202通过天线1201接收信息,将接收的信息发送给基带装置1203进行处理。在下行方向上,基带装置1203对要发送的信息进行处理,并发送给射频装置1202,射频装置1202对收到的信息进行处理后经过天线1201发送出去。
以上实施例中网络侧设备执行的方法可以在基带装置1203中实现,该基带装置1203包括基带处理器。
基带装置1203例如可以包括至少一个基带板,该基带板上设置有多个芯片,如图12所示,其中一个芯片例如为基带处理器,通过总线接口与存储器1205连接,以调用存储器1205中的程序,执行以上方法实施例中所示的网 络设备操作。
该网络侧设备还可以包括网络接口1206,该接口例如为通用公共无线接口(common public radio interface,CPRI)。
具体地,本发明实施例的网络侧设备1200还包括:存储在存储器1205上并可在处理器1204上运行的指令或程序,处理器1204调用存储器1205中的指令或程序执行图9所示各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
本申请实施例还提供一种可读存储介质,所述可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现如图2或图6所示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
其中,所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质,包括计算机可读存储介质,如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如图2或图6所示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为***级芯片,***芯片,芯片***或片上***芯片等。
本申请实施例另提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如图2或图6所示方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供了一种通信***,包括:终端及网络侧设备,所述终端可用于执行如上所述的信道特征信息上报方法的步骤,所述网络侧设备可用于执行如上所述的信道特征信息恢复方法的步骤。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还 包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,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可以以计算机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(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。

Claims (33)

  1. 一种信道特征信息上报方法,包括:
    终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;
    所述终端向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
  2. 根据权利要求1所述的方法,其中,所述终端向网络侧设备发送第二CSI信息,包括:
    所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
  3. 根据权利要求2所述的方法,其中,所述第一长度为所述第一信道特征信息的比特数,或者,所述第一长度为所述第一信道特征信息的包含的系数的个数;和/或,
    所述第二长度为所述第二信道特征信息的比特数,或者,所述第二长度为所述第二信道特征信息的包含的系数的个数。
  4. 根据权利要求2所述的方法,其中,所述第二长度的第二信道特征信息包括以下至少一项:
    所述第一信道特征信息中的前N个比特或系数,N等于所述第二长度对应的比特数或所述第二长度对应的系数的个数;
    所述第一信道特征信息中重要性等级大于预设等级的N个比特或系数;
    所述第一信道特征信息中除了已上报的信道特征信息之外的N个比特或系数。
  5. 根据权利要求2或4所述的方法,其中,在所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
    所述终端接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
  6. 根据权利要求5所述的方法,其中,所述第一指示信息由高层信令配置;或者,
    所述第二信道特征信息携带于信道状态信息CSI报告中,且所述第一指示信息是CSI报告配置中的指示信息,或者所述第一指示信息与所述终端使用的CSI资源对应。
  7. 根据权利要求2或4所述的方法,其中,在所述终端向网络侧设备发送从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
    所述终端根据所述目标信道信息对应的信道特性和信道条件中的至少一项,确定所述第二长度。
  8. 根据权利要求7所述的方法,其中,所述方法还包括:
    所述终端向所述网络侧设备发送第二指示信息,所述第二指示信息指示所述第二长度。
  9. 根据权利要求8所述的方法,其中,所述第二指示信息携带于CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息携带于所述CSI报告中的可变长度的CSI部分;或者,
    所述第二长度的第二信道特征信息中的最小长度的部分和所述第二指示信息携带于所述CSI报告中的固定长度的CSI部分,所述第二长度的第二信道特征信息中的除了所述最小长度的部分之外的可变长度的部分携带于所述CSI报告中的可变长度的CSI部分;或者,
    所述第二指示信息和所述第二长度的第二信道特征信息均携带于CSI报告中的可变长度的CSI部分。
  10. 根据权利要求9所述的方法,其中,所述最小长度小于或者等于所述第二长度。
  11. 根据权利要求7所述的方法,其中,所述终端根据所述目标信道信息对应的信道特性,确定所述第二长度,包括:
    所述终端根据第一关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的长度为所述第二长度,其中,所述第一关联关系包括所述目标信道参数的各个取值或各个取值范围与长度之间的关联关系;或 者,
    所述终端根据第二关联关系,确定所述目标信道信息对应的目标信道的目标信道参数的值关联的编码标识对应的长度为所述第二长度,其中,所述第二关联关系包括所述目标信道参数的各个取值或各个取值范围与编码标识之间的关联关系。
  12. 根据权利要求11所述的方法,其中,所述目标信道的目标信道参数包括以下至少一项:
    所述目标信道是视距传播或非视距传播;
    所述目标信道的有效时延径的个数;
    所述目标信道的两个目标径的时延间距;
    所述目标信道的有效波束的数量,所述有效波束包括功率大于第一阈值的离散傅里叶变换DFT正交基对应的波束。
  13. 根据权利要求12所述的方法,其中,所述有效时延径包括以下至少一项:
    对应的功率或幅度大于第一阈值的时延径;
    对应的功率或幅度为极大值的时延径。
  14. 根据权利要求7所述的方法,其中,所述方法还包括:
    所述终端接收来自所述网络侧设备的K个第一AI网络模型的相关信息,其中,所述K个第一AI网络模型与所述目标AI网络模型对应,所述K个第一AI网络模型分别用于解码各自对应的长度的信道特征信息;
    所述终端根据信道条件,确定所述第二长度,包括:
    所述终端从所述第一信道特征信息中截取K个第二信道特征信息,并分别通过K个所述第一AI网络模型将各自对应的长度的所述第二信道特征信息处理成第一信道信息;
    所述终端获取K个所述第一信道信息分别与所述目标信道信息的匹配程度;
    所述终端在确定目标第一信道信息与所述目标信道信息的匹配程度满足预设条件的情况下,确定所述第二长度等于用于处理得到所述目标第一信道信息的第一AI网络模型对应的长度,其中,K个所述第一AI网络模型处理 得到的K个第一信道信息包括所述目标第一信道信息。
  15. 根据权利要求14所述的方法,其中,所述目标第一信道信息与所述目标信道信息的匹配程度满足预设条件包括以下至少一项:
    所述目标第一信道信息与所述目标信道信息的相关性大于或者等于预设相关性;
    所述目标第一信道信息的信道容量大于或者等于所述目标信道信息的信道容量的第一预设值倍,所述第一预设值大于0且小于或者等于1;
    所述目标第一信道信息为所述K个所述第一信道信息中的信道质量指示CQI与所述目标信道信息的CQI相同或者最接近的一个;
    所述目标第一信道信息为所述K个所述第一信道信息中的且调制和编码方案MCS与所述目标信道信息的MCS相同或者最接近的一个。
  16. 根据权利要求1所述的方法,其中,所述终端向网络侧设备发送第二信道特征信息,包括:
    所述终端在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
  17. 根据权利要求16所述的方法,其中,在所述第二信道特征携带于CSI报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
    或者,
    所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
  18. 根据权利要求16所述的方法,其中,所述M次信道特征信息上报的第二信道特征信息的长度分别为由最小长度至所述第一长度之间依次递增;
    或者,
    所述M次信道特征信息上报的第二信道特征信息分别包括所述第一信道特征信息中互不重叠的部分,且所述M次信道特征信息上报的第二信道特征信息的长度之和等于所述第一长度。
  19. 根据权利要求16至18中任一项所述的方法,其中,所述终端在M次信道特征信息上报中,分别向网络侧设备发送从所述第一信道特征信息中截取的第二信道特征信息,包括:
    所述终端在M次信道特征信息上报中,按照预设顺序分别向网络侧设备发送第二信道特征信息,所述预设顺序包括:
    所述第二信道特征信息的长度由短至长的排列顺序;
    所述第二信道特征信息在所述第一信道特征信息中的排列顺序。
  20. 根据权利要求1所述的方法,其中,在所述终端采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息之前,所述方法还包括:
    所述终端对信道状态信息-参考信号CSI-RS或跟踪参考信号TRS进行信道估计得到所述目标信道信息;或者,
    所述终端对信道估计得到的信道信息进行预处理,得到所述目标信道信息。
  21. 一种信道特征信息上报装置,应用于终端,所述装置包括:
    第一处理模块,用于采用目标AI网络模型将目标信道信息处理成第一长度的第一信道特征信息;
    第一发送模块,用于向网络侧设备发送第二信道特征信息,第二信道特征信息是第一信道特征信息的部分内容。
  22. 一种信道特征信息恢复方法,包括:
    网络侧设备接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;
    所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
  23. 根据权利要求22所述的方法,其中,所述网络侧设备接收来自终端的第二信道特征信息,包括:
    所述网络侧设备接收来自终端的从所述第一信道特征信息中截取的第二 长度的第二信道特征信息,所述第二长度小于或者等于所述第一长度。
  24. 根据权利要求23所述的方法,其中,所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,包括:
    所述网络侧设备采用与所述第二长度的第二信道特征信息对应的第一AI网络模型对所述第二长度的第二信道特征信息进行处理,得到所述目标信道信息。
  25. 根据权利要求23所述的方法,其中,所述网络侧设备采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息,包括:
    在所述网络侧设备存储有所述终端的历史信道特征信息的情况下,所述网络侧设备根据所述第二长度的第二信道特征信息更新所述历史信道特征信息;
    所述网络侧设备采用第一AI网络模型对更新后的所述历史信道特征信息进行处理,得到所述目标信道信息。
  26. 根据权利要求23至25中任一项所述的方法,其中,在所述网络侧设备接收来自终端的从所述第一信道特征信息中截取的第二长度的第二信道特征信息之前,所述方法还包括:
    所述网络侧设备向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第二长度和/或第一编码标识,所述第一编码标识与所述第二长度关联。
  27. 根据权利要求23至25中任一项所述的方法,其中,所述方法还包括:
    所述网络侧设备接收来自所述终端的第二指示信息,所述第二指示信息指示所述第二长度。
  28. 根据权利要求22所述的方法,其中,所述网络侧设备接收来自终端的第二信道特征信息,包括:
    所述网络侧设备在所述终端的M次信道特征信息上报中,分别接收第二信道特征信息,其中,M为大于1的整数,所述M次信道特征信息上报的第二信道特征信息的长度互不相同,或者所述M次信道特征信息上报的第二信道特征信息的内容互不相同。
  29. 根据权利要求28所述的方法,其中,在所述第二信道特征携带于CSI 报告中的情况下,所述M次信道特征信息上报的时频资源位置由一个CSI报告配置信息配置;
    或者,
    所述M次信道特征信息上报的时频资源位置由M个CSI报告配置信息配置。
  30. 一种信道特征信息恢复装置,应用于网络侧设备,所述装置包括:
    第二接收模块,用于接收来自终端的第二信道特征信息,其中,所述第二信道特征信息包括第一信道特征信息的部分,所述第一信道特征信息为所述终端采用目标AI网络模型对目标信道信息进行处理得到的第一长度的信道特征信息;
    第二处理模块,用于采用第一AI网络模型对所述第二信道特征信息进行处理,得到所述目标信道信息。
  31. 一种终端,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至20中任一项所述的信道状态信息信道特征信息上报方法的步骤。
  32. 一种网络侧设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求22至29中任一项所述的信道状态信息信道特征信息恢复方法的步骤。
  33. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1至20中任一项所述的信道状态信息信道特征信息上报方法的步骤,或者实现如权利要求22至29中任一项所述的信道特征信息恢复方法的步骤。
PCT/CN2023/082127 2022-03-21 2023-03-17 信道特征信息上报及恢复方法、终端和网络侧设备 WO2023179473A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210283893.X 2022-03-21
CN202210283893.XA CN116827481A (zh) 2022-03-21 2022-03-21 信道特征信息上报及恢复方法、终端和网络侧设备

Publications (1)

Publication Number Publication Date
WO2023179473A1 true WO2023179473A1 (zh) 2023-09-28

Family

ID=88099893

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/082127 WO2023179473A1 (zh) 2022-03-21 2023-03-17 信道特征信息上报及恢复方法、终端和网络侧设备

Country Status (2)

Country Link
CN (1) CN116827481A (zh)
WO (1) WO2023179473A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210160149A1 (en) * 2019-11-22 2021-05-27 Huawei Technologies Co., Ltd. Personalized tailored air interface
CN114070675A (zh) * 2020-08-05 2022-02-18 展讯半导体(南京)有限公司 Ai网络模型匹配方法及装置、存储介质、用户设备
CN114070676A (zh) * 2020-08-05 2022-02-18 展讯半导体(南京)有限公司 Ai网络模型支持能力上报、接收方法及装置、存储介质、用户设备、基站
CN114079493A (zh) * 2020-08-13 2022-02-22 华为技术有限公司 一种信道状态信息测量反馈方法及相关装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210160149A1 (en) * 2019-11-22 2021-05-27 Huawei Technologies Co., Ltd. Personalized tailored air interface
CN114070675A (zh) * 2020-08-05 2022-02-18 展讯半导体(南京)有限公司 Ai网络模型匹配方法及装置、存储介质、用户设备
CN114070676A (zh) * 2020-08-05 2022-02-18 展讯半导体(南京)有限公司 Ai网络模型支持能力上报、接收方法及装置、存储介质、用户设备、基站
CN114079493A (zh) * 2020-08-13 2022-02-22 华为技术有限公司 一种信道状态信息测量反馈方法及相关装置

Also Published As

Publication number Publication date
CN116827481A (zh) 2023-09-29

Similar Documents

Publication Publication Date Title
US20230412430A1 (en) Inforamtion reporting method and apparatus, first device, and second device
WO2023246618A1 (zh) 信道矩阵处理方法、装置、终端及网络侧设备
WO2023179473A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023179474A1 (zh) 信道特征信息辅助上报及恢复方法、终端和网络侧设备
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023282804A1 (en) Classification of csi compression quality
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
WO2024032606A1 (zh) 信息传输方法、装置、设备、***及存储介质
WO2023179570A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2023185995A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
CN117411527A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024055974A1 (zh) Cqi传输方法、装置、终端及网络侧设备
WO2023179460A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024104126A1 (zh) 更新ai网络模型的方法、装置和通信设备
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
CN117335849A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023185980A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024007949A1 (zh) Ai模型处理方法、装置、终端及网络侧设备
US20240129004A1 (en) Method and apparatus for transmitting channel state information
WO2024055993A1 (zh) Cqi传输方法、装置、终端及网络侧设备
CN116939647A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
CN117978218A (zh) 信息传输方法、信息处理方法、装置和通信设备
CN116996898A (zh) Ai网络模型确定方法、装置、参考节点和网络侧设备

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: 23773721

Country of ref document: EP

Kind code of ref document: A1