WO2024037380A1 - 信道信息处理方法、装置、通信设备及存储介质 - Google Patents

信道信息处理方法、装置、通信设备及存储介质 Download PDF

Info

Publication number
WO2024037380A1
WO2024037380A1 PCT/CN2023/111731 CN2023111731W WO2024037380A1 WO 2024037380 A1 WO2024037380 A1 WO 2024037380A1 CN 2023111731 W CN2023111731 W CN 2023111731W WO 2024037380 A1 WO2024037380 A1 WO 2024037380A1
Authority
WO
WIPO (PCT)
Prior art keywords
channel information
compressed
compression
channel
compression method
Prior art date
Application number
PCT/CN2023/111731
Other languages
English (en)
French (fr)
Inventor
杨昂
谢天
吴昊
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 WO2024037380A1 publication Critical patent/WO2024037380A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W28/00Network traffic management; Network resource management
    • H04W28/02Traffic management, e.g. flow control or congestion control
    • H04W28/06Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to a channel information processing method, device, communication equipment and storage medium.
  • a network node (hereinafter referred to as node A) can input the acquired channel information into the encoder of node A, obtain the output compressed channel information, and combine the channel information with the compressed channel
  • the information is sent to another network node (hereinafter referred to as Node B), so that Node B corrects the encoder of Node B according to the channel information and the compressed channel information, so that the encoder of Node A can be compared with the encoder of Node B Matching to achieve joint work between different network nodes.
  • Embodiments of the present application provide a channel information processing method, device, communication equipment and storage medium, which can solve the problem of high overhead in transmitting channel information.
  • a channel information processing method includes: a first device obtains target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is: using a first compression method. Compressed channel information after compressing the first channel information; the first device uses the second compression method to compress the third channel information, and the third channel information is: at least one of the first channel information and the second channel information, and the second
  • the compression method is different from the first compression method; the first device sends fourth channel information to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and compression the compressed second channel information; the compressed first channel information, and the second channel information; the compressed first channel information, and the compressed second channel information.
  • a channel information processing device in a second aspect, includes an acquisition module, a compression module and a sending module; the acquisition module is used to acquire target channel information, and the target channel information includes first channel information and second channel information.
  • the second channel information is: compressed channel information after using the first compression method to compress the first channel information; the compression module is used to use the second compression method to compress the third channel information, and the third channel information is: the first channel information and At least one of the second channel information, the second compression method is different from the first compression method; the sending module is configured to send the fourth channel information to the second device according to the compression result of compressing the third channel information; wherein, the fourth The channel information includes any of the following: first channel information and compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information information.
  • a channel information processing method includes: a second device receiving The fourth channel information sent includes any of the following: first channel information and compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and the compressed second channel information; the second device uses the target decompression method to decompress the fourth channel information; wherein the second channel information is: the first channel information is compressed using the first compression method compressed channel information.
  • a channel information processing device which device includes a receiving module and a decompression module; a receiving module configured to receive fourth channel information sent by the first device, where the fourth channel information includes any of the following: first Channel information and compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information; decompression module, used to adopt the target
  • the decompression method is to decompress the fourth channel information; wherein the second channel information is: the compressed channel information obtained by using the first compression method to compress the first channel information.
  • a communication device in a fifth aspect, includes a processor and a memory.
  • the memory stores a program or instructions that can be run on the processor.
  • the program or instructions are implemented when executed by the processor. The steps of the method as described in the first aspect, or the steps of implementing the method as described in the third aspect.
  • a communication device including a processor and a communication interface, wherein the communication interface is used to obtain target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is : Compressed channel information after using the first compression method to compress the first channel information;
  • the processor is configured to use the second compression method to compress the third channel information, and the third channel information is: the first channel information and the second channel information At least one of them, the second compression method is different from the first compression method;
  • the communication interface is also used to send fourth channel information to the second device according to the compression result of compressing the third channel information; wherein, the fourth channel information Including any of the following: first channel information and compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information; or,
  • the communication interface is used to receive fourth channel information sent by the first device.
  • the fourth channel information includes any of the following: first channel information and compressed second channel information; compressed first channel information, and third channel information. Two channel information; compressed first channel information, and compressed second channel information; the processor is configured to use a target decompression method to decompress the fourth channel information; wherein the second channel information is: using Compressed channel information obtained by compressing the first channel information by the first compression method.
  • a communication system including: a first device as described in the first aspect and a second device as described in the third aspect, where the first device can be used to perform the method as described in the first aspect.
  • the steps of the channel information processing method, the second device may be configured to perform the steps of the channel information processing method described in the third aspect.
  • 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 a ninth 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. , or implement the 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 method as described in the first aspect
  • the target channel information includes first channel information and second channel information.
  • the second channel information is: using the first compression method to compress the first channel information. compressed channel information; and the second compression method can be used to compress the third channel information, the third channel information is: at least one of the first channel information and the second channel information, the second compression method is different from the first compression method; And can send fourth channel information to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and compressed second channel information; compressed First channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the first device can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then send the first channel information to the second device according to the compression result.
  • information and the compressed second channel information or send the compressed first channel information, and the second channel information, or send the compressed first channel information, and the compressed second channel information, so the target channel can be avoided
  • Information redundancy can reduce the overhead of transmitting channel information.
  • Figure 1 is a block diagram of a wireless communication system applicable to the embodiment of the present application.
  • Figure 2 is a schematic diagram of a neural network
  • Figure 3 is a schematic diagram of neurons in a neural network
  • Figure 4 is one of the flow charts of a channel information processing method provided by an embodiment of the present application.
  • Figure 5 is the second flow chart of a channel information processing method provided by an embodiment of the present application.
  • Figure 6 is one of the structural schematic diagrams of a channel information processing device provided by an embodiment of the present application.
  • Figure 7 is a second structural schematic diagram of a channel information processing device provided by an embodiment of the present application.
  • Figure 8 is a schematic diagram of a communication device provided by an embodiment of the present application.
  • Figure 9 is a schematic diagram of the hardware structure when the communication device provided by the embodiment of the present application is a terminal;
  • Figure 10 is a schematic diagram of the hardware structure when the communication device provided by the embodiment of the present application is a network-side device.
  • 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
  • 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
  • NR New Radio
  • 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
  • Mobile Internet Device MID
  • augmented reality augmented reality, AR
  • VR virtual reality
  • robots wearable devices
  • VUE vehicle-mounted equipment
  • 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 computers, PC), teller machines or self-service Terminal devices
  • wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, 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 12 may also be called wireless access network equipment, radio access network (Radio Access Network, RAN), radio access network function or Wireless access network unit.
  • the access network device 12 may include a base station, a WLAN access point or a WiFi node, etc.
  • the base station may be called a Node B, an evolved Node B (eNB), an access point, a Base Transceiver Station (BTS), a radio Base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home B-Node, Home Evolved B-Node, Transmitting Receiving Point (TRP) or all
  • eNB evolved Node B
  • BTS Base Transceiver Station
  • BSS Basic Service Set
  • ESS Extended Service Set
  • Home B-Node Home Evolved B-Node
  • TRP Transmitting Receiving Point
  • Core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, mobility management entities (Mobility Management Entity, MME), access mobility management functions (Access and Mobility Management Function, AMF), session management functions (Session Management Function, SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Services Discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data warehousing (Unified Data Repository, UDR), home subscriber server (Home Subscriber Server, HSS), centralized network configuration ( Centralized network configuration, CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (Local NEF, or L-NEF), Binding Support Function (Binding Support Function, BSF), application function (Application Function, AF), etc.
  • MME mobility management entities
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • FIG. 2 shows a schematic diagram of a neural network, as shown in Figure 2, the neural network is composed of neurons;
  • Figure 3 shows a schematic diagram of the neurons in the neural network, as shown in Figure 3, a is the input , w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and ⁇ (.) is the activation function.
  • Common activation functions can include Sigmoid (i.e. S-shaped growth curve), tanh (i.e. hyperbolic tangent function), linear rectification function (Rectified Linear Unit, ReLU), etc.
  • the parameters of neural networks can be optimized through gradient optimization algorithms.
  • Gradient optimization algorithms are a type of algorithm that minimize or maximize an objective function (also called a loss function), which is often a mathematical combination of model parameters and data.
  • an objective function also called a loss function
  • BP error Back Propagation
  • the basic idea of BP 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.
  • GD Gradient Descent
  • SGD stochastic gradient descent
  • mini-batch gradient descent i.e., small batch gradient descent
  • momentum method i.e., Momentum
  • Nesterov specifically, drive Quantitative stochastic gradient descent
  • adaptive gradient descent ADAptive GRADient descent, Adagrad
  • Adadelta root mean square error reduction (root mean square prop, RMSprop), adaptive momentum estimation (Adaptive Moment Estimation, Adam), etc.
  • the transmitter can optimize the signal based on CSI to better match the channel status.
  • the channel quality indicator CQI
  • MCS modulation and coding scheme
  • PMI precoding matrix indicator
  • the base station sends CSI reference signals on certain time-frequency resources in a certain time unit, and the terminal can The CSI reference signal performs channel estimation, calculates the channel information in this time unit, and feeds back the PMI to the base station through the codebook, so that the base station can combine the channel information based on the codebook information fed back by the terminal, and use this before the next CSI report.
  • the terminal can change the PMI reported on each subband to report PMI according to delay. Since the channels in the delay domain are more concentrated, PMI with fewer delays can approximately represent the PMI of all subbands, that is, delay Domain information is compressed before being reported.
  • the base station can first precode the CSI reference signal, and then send the encoded CSI reference signal to the terminal. What the terminal obtains is the channel corresponding to the encoded CSI reference signal, so the terminal only needs to Just select several ports with greater strength among the indicated ports and report the coefficients corresponding to these ports.
  • each node trains its own module separately, and then uses some means to ensure that each module can be paired with each other.
  • the most common method to ensure that various modules can work together is that after a node completes training of its own module, it will send the input and output data of the module to other nodes, and the other nodes will then train their own modules based on the received data, thus This enables the modules to work jointly without leaking the details of the respective models of the nodes.
  • the input and output data of a certain module usually includes a large amount of channel information, the cost of sending the input and output data of the module is often large (much greater than the cost of the transmission model, even hundreds of times). Therefore, the input and output data need to be further compressed to reduce the data transmission overhead to an acceptable level.
  • the secondary compression problem of input and output data there is currently no clear solution in the industry for the secondary compression problem of input and output data.
  • the target channel information includes the first channel information and the second channel information.
  • the second channel information is: using the first Compressed channel information after a compression method compresses the first channel information; and a second compression method can be used to compress the third channel information, and the third channel information is: at least one of the first channel information and the second channel information, The second compression method is different from the first compression method; and the fourth channel information can be sent to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and Compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the first device can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then send the first channel information to the second device according to the compression result.
  • information and the compressed second channel information or send the compressed first channel information, and the second channel information, or send the compressed first channel information, and the compressed second channel information, so the target channel can be avoided
  • Information redundancy can reduce the overhead of transmitting channel information.
  • the embodiment of the present application provides a channel information processing method.
  • Figure 4 shows the channel provided by the embodiment of the present application.
  • the channel information processing method provided by the embodiment of the present application may include the following steps 401 to 403.
  • Step 401 The first device obtains target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is compressed channel information obtained by compressing the first channel information using the first compression method.
  • the number of first channel information may be one or more, and each second channel information corresponds to one first channel information.
  • the first channel information may include at least one of the following: reference signal information, transmission channel information, and control channel information.
  • the above-mentioned reference signal may be: synchronization signal block (Synchronization Signal Block, SSB), CSI reference signal (i.e. CSI-RS), tracking reference signal (Tracking Reference Signal, TRS), phase tracking Reference signal (Phase-tracking Reference Signal, PTRS) or channel detection reference signal (Sounding Reference Signal, SRS), etc.
  • SSB Synchronization Signal Block
  • CSI-RS CSI reference signal
  • TRS Track Reference Signal
  • Phase tracking Reference signal Phase-tracking Reference Signal
  • PTRS Phase-tracking Reference Signal
  • SRS Sounding Reference Signal
  • the above-mentioned transmission channel may be: a physical downlink shared channel (PDSCH) or a physical uplink shared channel (Physical Uplink Shared Channel, PUSCH), etc.
  • PDSCH physical downlink shared channel
  • PUSCH Physical Uplink Shared Channel
  • the above control channel may be: a physical downlink control channel (PDCCH) or a physical uplink control channel (Physical Uplink Control Channel, PUCCH), etc.
  • PDCCH physical downlink control channel
  • PUCCH Physical Uplink Control Channel
  • the first compression method may be: a compression method based on an encoder composed of a 3rd Generation Partnership Project (3GPP) codebook; wherein the 3GPP codebook includes a variety of Type, for example, Type 1 (Type I) codebook, Type 2 (Type II) codebook, etc.
  • 3GPP 3rd Generation Partnership Project
  • the first compression method may be used to compress the channel information into PMI.
  • the first compression method may include a layer shared compression (ie, layer common) method, or a layer/rank specific compression (ie, layer/rank specific) method, etc.
  • the layer-sharing compression method the data is shared and compressed by each layer, that is, no matter how many layers or ranks, the channel information of each layer is compressed in parallel and separately (for example, each layer of 2 layers
  • the compression method is the same as the compression method for each layer of the 4 layers), and there is no need to interact with information such as rank; in the layer/rank separate special compression method, different compression methods are used for different layers or different ranks (such as , the 2-layer compression method is different from the 4-layer compression method), and it also needs to exchange information such as rank, layer index, or map the compressed channel information in a certain order (for example, map in the order of layer strength from high to low) Compressed channel information of each layer).
  • Step 402 The first device uses the second compression method to compress the third channel information.
  • the third channel information is: at least one of the first channel information and the second channel information, and the second compression method is different from the first compression method.
  • the second compression method may include at least one of the following: an encoder compression method, a channel information screening method, a quantization method, a principal component analysis method, and a text compression algorithm.
  • the second compression method may include at least one of an encoder compression method, a channel information screening method, a quantization method, a principal component analysis method, and a text compression algorithm
  • the first device may adopt different compression methods.
  • the third channel information is compressed, thereby improving the flexibility of compressing the channel information.
  • the above quantization method may include at least one of the following: uniform quantization method, non-uniform quantization method, weight sharing quantization method, group quantization method, parameter coding method, transform domain quantization method, product quantization method method.
  • floating point numbers can be divided into multiple sets, and the elements in each set share a value.
  • floating point numbers can be encoded (including lossy encoding or lossless encoding, etc.), for example, Huffman encoding is performed on floating point numbers.
  • the floating point number in the above transform domain quantization method, can be transformed to another domain (for example, frequency domain, S domain, Z domain, etc.) first, and then the quantization operation is performed, and then the reverse operation is performed. Transform back.
  • another domain for example, frequency domain, S domain, Z domain, etc.
  • the floating point number in the embodiment of the present application, can be divided into multiple subspaces, and a quantization operation is performed on each subspace.
  • the above quantization method may include at least one of a uniform quantization method, a non-uniform quantization method, a weight sharing quantization method, a grouping quantization method, a parameter coding method, a transform domain quantization method, and a product quantization method, therefore
  • the compression method used by the first device when compressing the third channel information can be enriched, thereby further improving the flexibility of compressing the channel information.
  • the third channel information is the first channel information and the second channel information; then, the compression method of the first device for compressing the first channel information is the same as the compression method of the first device for compressing the second channel information.
  • the methods are the same or different.
  • the second compression method when the compression method used by the first device to compress the first channel information is different from the compression method used by the first device to compress the second channel information, the second compression method includes the above-mentioned encoder compression method, channel information screening At least two of methods, quantification methods, principal component analysis methods and text compression algorithms.
  • the compression method used by the first device to compress the first channel information is the same as or different from the compression method used by the first device to compress the second channel information, the flexibility of compressing the channel information can be further improved.
  • step 402 can be specifically implemented through the following step 402a.
  • Step 402a The first device uses the second compression method to compress the third channel information according to the compression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the above-mentioned core network node may include: Network Data Analysis Function (NWDAF, Network Data Analytics Function, NWDAF), Location Management Function (Location Management Function, LMF) or neural network processing section, etc.
  • NWDAF Network Data Analysis Function
  • LMF Location Management Function
  • neural network processing section etc.
  • the above-mentioned access network node may include: a base station or a newly defined neural network processing node, etc.
  • the above-mentioned third-party node may be an over-the-top (OTT) server, usually a node or device that does not belong to the 3GPP entity.
  • OTT over-the-top
  • both the first device and the second device may be terminals or network-side devices, and the first device and the second device may be the same or different.
  • the above compression parameters may include at least one of the following: compression rate, codebook parameters, etc.
  • the first device can use the second compression method to compress the third channel information according to the compression parameters configured by at least one of the core network node, the access network node and the third-party node, the compression channel can be improved. Accuracy of information.
  • the second compression method is the above-mentioned encoder compression method; then the above-mentioned step 402 can be specifically implemented through the following steps 402b and 402c.
  • Step 402b The first device uses the encoder compression method to compress the third channel information through the first encoder to obtain the first compressed channel information, and decompress the first compressed channel information through the first decoder to obtain the fifth channel information.
  • the first compressed channel information may be: after the first device inputs the third channel information into the first encoder, the PMI and coded bits corresponding to the third channel information output by the first encoder Or compress information, etc.
  • the first encoder may be: an encoder based on the 3GPP codebook; the first encoder may be used to compress channel information into PMI.
  • the first decoder may be: a decoder based on the 3GPP codebook; the first decoder may be used to restore the PMI to any of the following: channel information, precoding Matrix, precoding vector.
  • 3GPP codebooks include multiple types, such as Type 1 (Type I) codebooks, Type 2 (Type II) codebooks, etc.
  • the first encoder may be an encoder based on the first codebook, or may be an encoder based on the second codebook.
  • the first decoder may be a decoder based on the first codebook, or may be a decoder based on the second codebook.
  • the second codebook is: a codebook in which the value range of some parameters in the first codebook is expanded.
  • the value range of the L parameter (the parameter used to select the number of beams) in the first codebook is [1, 2, 3, 4, 6]
  • the value range of the L parameter in the second codebook can be is smaller than the CSI reference signal antenna port interface at the network side; and/or, the value of the ⁇ parameter in the first codebook (the Feiling coefficient accounts for the proportion of all coefficients) is [1/4 1/2 3/4], then the value of the first codebook is [1/4 1/2 3/4].
  • the value of the ⁇ parameter in the second codebook can also be 1/8, 3/8, 1/16, etc.; and/or the value of the M parameter (used to select the delay number) in the first codebook is [ 1 2 4 8], then the value of the M parameter in the second codebook can also be 16, 32, etc.; and/or, the pv parameter in the first codebook (used to calculate a coefficient used in the M parameter parameter) is [1/8 1/4 1/2], then the value of the pv parameter in the second codebook can also be 1/16, 1/32, 1/64, etc.
  • the first codebook may be a 3GPP-based codebook, such as a Type I codebook, a Type II codebook, etc.
  • the second codebook may be an enhanced codebook based on the 3GPP codebook.
  • both the first encoder and the first decoder can be based on the first codebook or the second codebook, the coding of the first encoder and the first decoder can be enriched. This way, the flexibility of processing channel information through the first encoder and the first decoder can be improved.
  • Step 402c The first device compresses the fifth channel information through the second encoder to obtain the second compressed channel information.
  • the second encoder may be: based on the first compression method, the channel information is processed into Row compression module.
  • the fourth channel information (that is, the compressed target channel information) includes: first compressed channel information and second compressed channel information.
  • the second compression method is a lossy compression method
  • using the second compression method to compress the third channel information will cause compression loss of the third channel information.
  • the third channel information is compressed by the first encoder, decompressed by the first decoder, and then compressed by the second encoder
  • the second compressed channel information obtained at this time does not have the band of the first encoder.
  • the compression loss will be reduced, but the diversification of channel characteristics will be reduced, that is, the third channel information can take on any floating point value, while at this time the second compressed channel information can only take on a limited value in the decompression space. For example, a certain floating point number of the third channel information can take on any floating point value between -1 and 1. If the first encoder uses 3-bit uniform quantization, the second compressed channel information can only have 8 values.
  • the first device can use the encoder compression method to compress the third channel information through the first encoder to obtain the first compressed channel information, and decompress the first decoder through the second encoder.
  • the first compressed channel information obtains the channel information and is compressed to obtain the second compressed channel information. Therefore, compression loss can be avoided, thereby improving the accuracy of channel information processing.
  • the first channel information includes at least one channel information
  • the second channel information includes: at least one compressed channel information corresponding to the at least one channel information
  • the second compression method is the above-mentioned channel information screening method.
  • step 402 can be specifically implemented through the following step 402d.
  • Step 402d The first device clusters the third channel information to obtain N channel information clusters, and selects at least one channel information from each of the M channel information clusters.
  • the above-mentioned N channel information clusters include the above-mentioned M channel information clusters, N is a positive integer, and M is a positive integer less than or equal to N.
  • the fourth channel information includes: channel information selected from the above-mentioned M channel information clusters.
  • the first device before the first device clusters the third channel information, it may first perform a dimensionality raising operation or a dimensionality reduction operation, and then perform clustering on the third channel information in the elevated high-dimensional space. Clustering, or clustering the third channel information in a low-dimensional space after dimensionality reduction.
  • the at least one channel information may be channel information corresponding to the center point of the channel information cluster or near the center point.
  • step 402 can be specifically implemented through the following step 402e.
  • Step 402e The first device divides the third channel information into P groups of channel information based on the first information, and selects at least one channel information from each group of Q groups of channel information.
  • the above-mentioned group P channel information includes the above-mentioned group Q channel information, P is a positive integer, and Q is a positive integer less than or equal to P.
  • the fourth channel information includes: channel information selected from the above Q group of channel information.
  • the first information includes at least one of the following: signal-to-noise ratio, line of sight (Line of Sight, LOS), Non Line of Sight (NLOS), frequency domain channel characteristics, time domain channel characteristics, air domain channel characteristics, and collection time information of channel information.
  • the first device can divide the third channel information into channel information with a signal-to-noise ratio of 10dB to 11dB based on the signal-to-noise ratio, and channel information with a signal-to-noise ratio of 11dB to 12dB.
  • the first device can divide the third channel information into: LOS channel information and NLOS channel information based on the LOS and NLOS.
  • the above collection time information of the channel information may include at least one of the following: collection time of the channel information, collection time stamp of the channel information.
  • the first device can use the above method to combine /or Method 2: filter the third channel information to compress the third channel information, so the flexibility of the first device in compressing the third channel information can be further improved.
  • Step 403 The first device sends the fourth channel information to the second device according to the compression result of compressing the third channel information.
  • the fourth channel information includes any of the following:
  • the fourth channel information includes the above (1), the first device compresses the second channel information in the third channel information; if the fourth channel information includes the above (2), the first device compresses the third channel information. The first channel information in the channel information; if the fourth channel information includes the above (3), the first device compresses the first channel information and the second channel information in the third channel information.
  • the first device may send the entire fourth channel information to the second device to save system overhead.
  • the first device can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then compress the first channel information and/or the second channel information according to the compression result. , sending the first channel information and the compressed second channel information to the second device, or sending the compressed first channel information, and the second channel information, or sending the compressed first channel information, and the compressed third channel information. Two channel information, so the redundancy of target channel information can be avoided, thereby reducing the overhead of transmitting channel information.
  • FIG. 5 shows a flow chart of the channel information processing method provided by an embodiment of the present application.
  • the channel information processing method provided by the embodiment of the present application may include the following steps 501 and 502.
  • Step 501 The second device receives the fourth channel information sent by the first device.
  • the fourth channel information includes any of the following:
  • the second channel information is: compressed information after using the first compression method to compress the first channel information. information.
  • Step 502 The second device uses the target decompression method to decompress the fourth channel information.
  • the target decompression method may be a decompression method corresponding to the above-mentioned second compression method.
  • the second device decompresses the fourth channel information to recover the first channel information and the second channel information, so that module training can be performed based on the recovered channel information to match the first channel information.
  • step 502 can be specifically implemented through the following step 502a.
  • Step 502a The second device uses the target decompression method to decompress the fourth channel information according to the decompression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the second device can receive the fourth channel information (ie, compressed channel information) sent by the first device, the overhead of receiving the channel information can be reduced, thereby The transmission efficiency of channel information can be improved; on the other hand, since the second device can use the target decompression method to decompress the fourth channel information, the encoding method of the second device can be matched with that of the first device, so that the second device can Enable joint working.
  • fourth channel information ie, compressed channel information
  • the channel information processing method provided by the embodiment of the present application is exemplarily described below.
  • the terminal can perform the following steps:
  • Step 1 The terminal trains the encoder model based on existing channel information.
  • the method for obtaining channel information required for training includes at least one of the following: the terminal estimates the channel information based on downlink reference signals (such as CSI-RS); the terminal receives channel information sent by other network nodes; and the terminal uses a simulation model to generate channel information.
  • downlink reference signals such as CSI-RS
  • the terminal trains the encoder in at least one of the following ways: first train the complete encoder-decoder model, and then take out the encoder part for use; use a semi-supervised method to directly train the encoder.
  • Step 2 The terminal selects a certain amount of test channel information and passes it through the encoder model to obtain paired channel information (i.e., target channel information), that is, paired test channel information (i.e., first channel information) and test channel compression information (i.e., second channel information), where the test channel information is the input of the encoder, and the test channel compression information is the output of the encoder.
  • paired channel information i.e., target channel information
  • test channel information i.e., first channel information
  • test channel compression information i.e., second channel information
  • the range of test channel information selected by the terminal is not limited and can overlap with the channel information in step 1; the number of test channel information selected can be instructed by the network side device or decided by the terminal itself.
  • Step 3 The terminal compresses the test channel information in Step 2 to obtain pairs of compressed test channel information and test channel compression information (ie, fourth channel information).
  • Step 4 The terminal reports the compressed test channel information, test channel compression information, and information indicating the corresponding decompression method to the base station.
  • Step 5 The base station receives the compressed test channel information and test channel compression information, and indicates the corresponding solution compression method information, and restore the channel information according to the corresponding decompression method.
  • Step 6 The base station trains the decoder based on the recovered channel information, and notifies the terminal of the relevant training results and performs subsequent model management.
  • the base station taking the base station to first train the encoder, and then send the input and output data required for the terminal side to train the encoder to the terminal to help train the encoder, the base station can perform the following steps:
  • Step a The base station trains the decoder model based on existing channel information.
  • the method for obtaining the channel information required for base station training includes at least one of the following: the base station estimates the channel information based on the uplink reference signal (such as SRS); the base station receives the channel information sent by other network nodes (such as collecting downlink channel information estimated by the terminal) ; The base station uses the simulated channel model to generate channel information.
  • the uplink reference signal such as SRS
  • the base station receives the channel information sent by other network nodes (such as collecting downlink channel information estimated by the terminal) ;
  • the base station uses the simulated channel model to generate channel information.
  • the base station trains the decoder by: first training the complete encoder-decoder model, and then taking out the decoder part for use.
  • Step b The base station selects a certain amount of test channel information and obtains paired channel information (ie, target channel information), that is, paired test channel information (ie, first channel information) and test channel compression information (ie, second channel information) ), where the test channel information is the input of the encoder, and the test channel compression information is the output of the encoder.
  • paired channel information ie, target channel information
  • test channel information ie, first channel information
  • test channel compression information ie, second channel information
  • the range of test channel information selected by the base station is not limited and can overlap with the channel information in step 1; the number of test channel information selected can be instructed by the higher layer or decided by the base station itself.
  • the selected test channel information needs to be able to adapt to the decoder model of the base station.
  • the base station mainly uses the decoder module to decompress the CSI, but the base station can also obtain the test by retaining the encoder module when training the decoder module. channel information.
  • Step c The base station compresses the test channel information in step b, and obtains pairs of compressed test channel information and test channel compression information (ie, fourth channel information).
  • Step d The base station delivers the compressed test channel information, test channel compression information, and information indicating the corresponding decompression method to the terminal requesting data or related functions (or other related network nodes, such as OTT servers, etc.).
  • Step e The terminal (or other related network node) receives the compressed test channel information and test channel compression information, as well as information indicating the corresponding decompression method, and recovers the channel information according to the corresponding decompression method.
  • Step f The terminal (or other related network node) trains the encoder based on the channel information it will pay, and reports the training results related to the base station and the model management information required for subsequent operations.
  • the execution subject may be a channel information processing device.
  • the channel information processing method performed by the channel information processing apparatus is used as an example to illustrate the channel information processing apparatus provided by the embodiments of the present application.
  • the channel information processing device 60 may include an acquisition module 61 , a compression module 62 and a sending module 63 .
  • the acquisition module 61 may be used to acquire target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is compressed channel information obtained by compressing the first channel information using the first compression method.
  • the compression module 62 may be configured to use a second compression method to compress third channel information.
  • the third channel information is: at least one of the first channel information and the second channel information.
  • the second compression method is different from the first compression method.
  • the sending module 63 may be configured to send fourth channel information to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and the compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the second compression method may include at least one of the following: an encoder compression method, a channel information screening method, a quantization method, a principal component analysis method, and a text compression algorithm.
  • the second compression method is the above-mentioned encoder compression method.
  • the compression module 62 may be specifically configured to use the encoder compression method to compress the third channel information through the first encoder to obtain the first compressed channel information, and decompress the first compressed channel information through the first decoder to obtain the third channel information.
  • the fifth channel information is compressed by the second encoder to obtain the second compressed channel information.
  • the fourth channel information includes: first compressed channel information and second compressed channel information.
  • the first encoder may be an encoder based on the first codebook, or may be an encoder based on the second codebook; and/or the first decoder may be an encoder based on the first codebook.
  • the decoder of this codebook may be a decoder based on the second codebook.
  • the second codebook is: a codebook after expanding the value range of some parameters in the first codebook.
  • the first channel information includes at least one channel information
  • the second channel information includes: at least one compressed channel information corresponding to the at least one channel information
  • the second compression method is the above-mentioned channel information screening method.
  • the compression module 62 may be specifically used to cluster the third channel information to obtain N channel information clusters, and select at least one channel information from each of the M channel information clusters; the N channel information clusters Including the M channel information clusters, N is a positive integer, and M is a positive integer less than or equal to N; wherein the fourth channel information includes: channel information selected from the M channel information clusters; and/or, specifically It can be used to divide the third channel information into P groups of channel information according to the first information, and select at least one channel information from each group of Q group of channel information; the P group of channel information includes the Q group of channel information, P is a positive integer, Q is a positive integer less than or equal to P; wherein, the fourth channel information includes: channel information selected from the Q group of channel information; the first information includes at
  • the above quantization method may include at least one of the following: a uniform quantization method, a non-uniform quantization method, a weight sharing quantization method, a grouped quantization method, a parameter coding method, a transform domain quantization method, and a product quantization method.
  • the third channel information is the first channel information and the second channel information.
  • the compression method used by the first device to compress the first channel information is the same as or different from the compression method used by the first device to compress the second channel information.
  • the compression module 62 may be configured to use the second compression method to compress the third channel information according to the compression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the channel information processing device can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then compress the first channel information and/or the second channel information according to the Compression result: sending the first channel information and the compressed second channel information to the second device, or sending the compressed first channel information, and the second channel information, or sending the compressed first channel information, and the compressed second channel information, so redundancy of target channel information can be avoided, thereby reducing the overhead of transmitting channel information.
  • the channel information processing device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system.
  • a device can also be a component in an electronic device, such as an integrated circuit or chip.
  • the electronic device may be a terminal or other devices other than the terminal.
  • terminals may include but are not limited to the types of terminals 11 listed above, and 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 information processing device provided by the embodiment of the present application can implement each process implemented by the method embodiment in Figure 4 and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • the channel information processing device 70 may include a receiving module 71 and a decompression module 72 .
  • the receiving module 71 may be configured to receive fourth channel information sent by the first device.
  • the fourth channel information includes any of the following: first channel information and compressed second channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the decompression module 72 may be used to decompress the fourth channel information using a target decompression method.
  • the second channel information is: compressed channel information obtained by using the first compression method to compress the first channel information.
  • the decompression module 72 may be configured to decompress the fourth channel information using a target decompression method according to the decompression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the channel information processing device can receive the fourth channel information (ie, compressed channel information) sent by the first device, the overhead of receiving the channel information can be reduced. , thereby improving the transmission efficiency of channel information; on the other hand, since the channel information processing device can use the target decompression method to decompress the fourth channel information, the encoding of the channel information processing device and the first device can be methods so that joint work can be achieved.
  • the fourth channel information ie, compressed channel information
  • the channel information processing device 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.
  • terminals may include but are not limited to the types of terminals 11 listed above, and other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiment of this application.
  • NAS Network Attached Storage
  • the channel information processing device provided by the embodiment of the present application can implement each process implemented by the method embodiment in Figure 5 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 800, which includes a processor 801 and a memory 802.
  • the memory 802 stores programs or instructions that can be run on the processor 801, such as , when the communication device 800 is a first device, when the program or instruction is executed by the processor 801, each step of the above-mentioned first device-side method embodiment is implemented, and the same technical effect can be achieved.
  • the communication device 800 is a second device, when the program or instruction is executed by the processor 801, each step of the above-mentioned second device-side method embodiment is implemented, and the same technical effect can be achieved. To avoid duplication, the details will not be described here.
  • An embodiment of the present application also provides a communication device, including a processor and a communication interface.
  • the communication interface is used to obtain target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is: using the first
  • the compression method compresses the compressed channel information after the first channel information is compressed;
  • the processor is configured to use the second compression method to compress the third channel information, and the third channel information is: at least one of the first channel information and the second channel information,
  • the second compression method is different from the first compression method;
  • the communication interface is also used to compress the third channel information according to The compression result is the fourth channel information sent to the second device; wherein the fourth channel information includes any of the following: the first channel information and the compressed second channel information; the compressed first channel information, and the second Channel information; compressed first channel information, and compressed second channel information; or,
  • the communication interface is used to receive fourth channel information sent by the first device.
  • the fourth channel information includes any of the following: first channel information and compressed second channel information; compressed first channel information, and second channel information. information; compressed first channel information, and compressed second channel information; the processor is configured to use a target decompression method to decompress the fourth channel information; wherein the second channel information is: using the first compression method Compressed channel information after compressing the first channel information.
  • This communication device embodiment corresponds to the above-mentioned channel information processing method embodiment.
  • Each implementation process and implementation manner of the above-mentioned channel information processing method embodiment can be applied to this communication device embodiment, and can achieve the same technical effect.
  • the communication device may be a terminal, or may be a network side device.
  • Figure 9 is a schematic diagram of the hardware structure of the terminal.
  • the terminal 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, a processor 1010, etc. At least some parts.
  • the terminal 1000 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 1010 through a power management system, thereby managing charging, discharging, and power consumption through the power management system. Management and other functions.
  • the terminal structure shown in FIG. 9 does not constitute a limitation on the terminal.
  • the terminal may include more or fewer components than shown in the figure, or may combine certain components, or arrange different components, which will not be described again here.
  • the input unit 1004 may include a graphics processing unit (Graphics Processing Unit, GPU) 10041 and a microphone 10042.
  • the graphics processor 10041 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 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072 .
  • Touch panel 10071 also known as touch screen.
  • the touch panel 10071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 10072 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 1001 after receiving downlink data from the network side device, can transmit it to the processor 1010 for processing; in addition, the radio frequency unit 1001 can send uplink data to the network side device.
  • the radio frequency unit 1001 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • Memory 1009 may be used to store software programs or instructions as well as various data.
  • the memory 1009 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 1009 may include volatile memory or nonvolatile memory, or memory 1009 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 memory Except for programmable PROM (EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • EPROM programmable PROM
  • EPROM electrically erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only 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 synchronous link dynamic random access memory
  • SLDRAM direct memory bus
  • the processor 1010 may include one or more processing units; optionally, the processor 1010 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 1010.
  • the radio frequency unit 1001 can be used to obtain target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is: using the first compression method Compressed channel information after compressing the first channel information.
  • the processor 1010 may be configured to use a second compression method to compress third channel information.
  • the third channel information is: at least one of the first channel information and the second channel information.
  • the second compression method is different from the first compression method.
  • the radio frequency unit 1001 may also be configured to send fourth channel information to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and compressed second Channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the second compression method may include at least one of the following: an encoder compression method, a channel information screening method, a quantization method, a principal component analysis method, and a text compression algorithm.
  • the second compression method is the above-mentioned encoder compression method.
  • the processor 1010 may specifically use the encoder compression method to compress the third channel information through the first encoder to obtain the first compressed channel information, and decompress the first compressed channel information through the first decoder to obtain the third channel information.
  • the fifth channel information is compressed by the second encoder to obtain the second compressed channel information.
  • the fourth channel information includes: first compressed channel information and second compressed channel information.
  • the first encoder may be an encoder based on the first codebook, or may be an encoder based on the second codebook; and/or the first decoder may be an encoder based on the first codebook.
  • the decoder of this codebook may be a decoder based on the second codebook.
  • the second codebook is: a codebook after expanding the value range of some parameters in the first codebook.
  • the first channel information includes at least one channel information
  • the second channel information includes: at least one compressed channel information corresponding to the at least one channel information
  • the second compression method is the above-mentioned channel information screening method.
  • the processor 1010 may be configured to cluster the third channel information to obtain N channel information clusters, and select at least one channel information from each of the M channel information clusters; the N channel information clusters Including the M channel information clusters, N is a positive integer, and M is a positive integer less than or equal to N; wherein the fourth channel information includes: channel information selected from the M channel information clusters; and/or, specifically It can be used to divide the third channel information into P groups of channel information according to the first information, and extract each group of channels from the Q group of channel information.
  • the P group of channel information includes the Q group of channel information, P is a positive integer, Q is a positive integer less than or equal to P; wherein, the fourth channel information includes: from the Q group of channel information
  • the first information includes at least one of the following: signal-to-noise ratio, LOS, NLOS, frequency domain channel characteristics, time domain channel characteristics, air domain channel characteristics, and collection time information of channel information.
  • the above quantization method may include at least one of the following: a uniform quantization method, a non-uniform quantization method, a weight sharing quantization method, a grouped quantization method, a parameter coding method, a transform domain quantization method, and a product quantization method.
  • the third channel information is the first channel information and the second channel information.
  • the compression method used by the first device to compress the first channel information is the same as or different from the compression method used by the first device to compress the second channel information.
  • the processor 1010 may be configured to use the second compression method to compress the third channel information according to the compression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the terminal can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then compress the first channel information and/or the second channel information in the target channel information according to the compression result.
  • the device sends the first channel information and the compressed second channel information, or sends the compressed first channel information, and the second channel information, or sends the compressed first channel information, and the compressed second channel information, Therefore, redundancy of target channel information can be avoided, thereby reducing the overhead of transmitting channel information.
  • the terminal provided by the embodiment of the present application can implement each process implemented by the first device in the above method embodiment, and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • the radio frequency unit 1001 can be used to receive the fourth channel information sent by the first device.
  • the fourth channel information includes any of the following: first channel information and compressed second channel Information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the processor 1010 may be configured to use a target decompression method to decompress the fourth channel information.
  • the second channel information is: compressed channel information obtained by using the first compression method to compress the first channel information.
  • the processor 1010 may be configured to decompress the fourth channel information using a target decompression method according to the decompression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the terminal on the one hand, because the terminal can receive the fourth channel information (that is, the compressed channel information) sent by the first device, the overhead of receiving the channel information can be reduced, thereby improving the channel information. transmission efficiency; on the other hand, because the terminal can use the target decompression method to decompress the fourth channel information, the terminal can be matched with the encoding method of the first device, so that joint work can be achieved.
  • the fourth channel information that is, the compressed channel information
  • the terminal provided by the embodiment of the present application can implement each process implemented by the second device in the above method embodiment, and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • FIG. 10 is a schematic diagram of the hardware structure of the network-side device.
  • the network side device 100 includes: an antenna 11 , a radio frequency device 12 , a baseband device 13 , a processor 14 and a memory 15 .
  • the antenna 11 is connected to the radio frequency device 12 .
  • the radio frequency device 12 passes The antenna 11 receives information and sends the received information to the baseband device 13 for processing.
  • the baseband device 13 processes the information to be sent and sends it to the radio frequency device 12.
  • the radio frequency device 12 processes the received information and then sends it out through the antenna 11.
  • the method performed by the network side device in the above embodiment can be implemented in the baseband device 13, which includes a baseband processor.
  • the baseband device 13 may include, for example, at least one baseband board, which is provided with multiple chips, one of which is, for example, a baseband processor, and is connected to the memory 15 through a bus interface to call the program in the memory 15 to execute the above method. Network device operation shown in the example.
  • the network side device may also include a network interface 16, which is, for example, a common public radio interface (CPRI).
  • a network interface 16 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 100 in the embodiment of the present application also includes: instructions or programs stored in the memory 15 and executable on the processor 14.
  • the processor 14 calls the instructions or programs in the memory 15 to execute Figures 6 to 7
  • the execution methods of each module are shown and achieve the same technical effect. To avoid repetition, they will not be described in detail here.
  • the radio frequency device 12 can be used to obtain target channel information.
  • the target channel information includes first channel information and second channel information.
  • the second channel information is: using the first Compressed channel information obtained by compressing the first channel information using a compression method.
  • the processor 14 may be configured to use a second compression method to compress third channel information.
  • the third channel information is: at least one of the first channel information and the second channel information.
  • the second compression method is different from the first compression method.
  • the radio frequency device 12 may also be configured to send fourth channel information to the second device according to the compression result of compressing the third channel information; wherein the fourth channel information includes any of the following: first channel information and compressed second Channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the second compression method may include at least one of the following: an encoder compression method, a channel information screening method, a quantization method, a principal component analysis method, and a text compression algorithm.
  • the second compression method is the above-mentioned encoder compression method.
  • the processor 14 may specifically use the encoder compression method to compress the third channel information through the first encoder to obtain the first compressed channel information, and decompress the first compressed channel information through the first decoder to obtain the third channel information.
  • the fifth channel information is compressed by the second encoder to obtain the second compressed channel information.
  • the fourth channel information includes: first compressed channel information and second compressed channel information.
  • the first encoder may be an encoder based on the first codebook, or may be an encoder based on the second codebook; and/or the first decoder may be an encoder based on the first codebook.
  • the decoder of this codebook may be a decoder based on the second codebook.
  • the second codebook is: a codebook after expanding the value range of some parameters in the first codebook.
  • the first channel information includes at least one channel information
  • the second channel information includes: at least one compressed channel information corresponding to the at least one channel information
  • the second compression method is the above-mentioned channel information screening method.
  • the processor 14 may be specifically configured to cluster the third channel information to obtain N channel information clusters, and select at least one channel information from each of the M channel information clusters; the N channel information clusters Including the M channel information clusters, N is a positive integer, and M is a positive integer less than or equal to N; wherein the fourth channel information includes: channel information selected from the M channel information clusters; and/or, specifically It can be used to divide the third channel information into P groups of channel information according to the first information, and extract each group of channels from the Q group of channel information.
  • the P group of channel information includes the Q group of channel information, P is a positive integer, Q is a positive integer less than or equal to P; wherein, the fourth channel information includes: from the Q group of channel information
  • the first information includes at least one of the following: signal-to-noise ratio, LOS, NLOS, frequency domain channel characteristics, time domain channel characteristics, air domain channel characteristics, and collection time information of channel information.
  • the above quantization method may include at least one of the following: a uniform quantization method, a non-uniform quantization method, a weight sharing quantization method, a grouped quantization method, a parameter coding method, a transform domain quantization method, and a product quantization method.
  • the third channel information is the first channel information and the second channel information.
  • the compression method used by the first device to compress the first channel information is the same as or different from the compression method used by the first device to compress the second channel information.
  • the processor 14 may be configured to use the second compression method to compress the third channel information according to the compression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the network side device can first use the second compression method to compress the first channel information and/or the second channel information in the target channel information, and then compress the first channel information and/or the second channel information according to the compression result. , sending the first channel information and the compressed second channel information to the second device, or sending the compressed first channel information, and the second channel information, or sending the compressed first channel information, and the compressed third channel information. Two channel information, so the redundancy of target channel information can be avoided, thereby reducing the overhead of transmitting channel information.
  • the network side device provided by the embodiment of the present application can implement each process implemented by the first device in the above method embodiment, and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • the radio frequency device 12 can be used to receive the fourth channel information sent by the first device.
  • the fourth channel information includes any of the following: the first channel information and the compressed third channel information. Two channel information; compressed first channel information, and second channel information; compressed first channel information, and compressed second channel information.
  • the processor 14 may be configured to use a target decompression method to decompress the fourth channel information.
  • the second channel information is: compressed channel information obtained by using the first compression method to compress the first channel information.
  • the processor 14 may be configured to decompress the fourth channel information using a target decompression method according to the decompression parameters configured by the third device.
  • the third device includes at least one of the following: a core network node, an access network node, and a third-party node.
  • the network side device on the one hand, because the network side device can receive the fourth channel information (that is, the compressed channel information) sent by the first device, the overhead of receiving the channel information can be reduced, thereby The transmission efficiency of channel information can be improved; on the other hand, since the network side device can use the target decompression method to decompress the fourth channel information, the network side device can match the encoding method of the first device. This enables joint working.
  • the fourth channel information that is, the compressed channel information
  • the network side device can use the target decompression method to decompress the fourth channel information
  • the network side device can match the encoding method of the first device. This enables joint working.
  • the network side device provided by the embodiment of the present application can implement each process implemented by the second device in the above method embodiment, and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • 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 above channel information processing method embodiment is implemented, and can achieve The same technical effects are not repeated here to avoid repetition.
  • 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 to implement the above embodiments of the channel information processing method. Each process can achieve the same technical effect. To avoid repetition, we will not go into details 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.
  • Embodiments of the present application further provide a computer program/program product.
  • the computer program/program product is stored in a storage medium.
  • the computer program/program product is executed by at least one processor to implement the above channel information processing method.
  • Each process in the example can achieve the same technical effect. To avoid repetition, we will not repeat it here.
  • An embodiment of the present application also provides a communication system, including: a first device and a second device as described in the above embodiments.
  • the first device can be used to perform various processes as in the above first device-side method embodiment.
  • the second device may be configured to perform the steps of each process of the above-mentioned second device-side method embodiment.
  • 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)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请公开了一种信道信息处理方法、装置、通信设备及存储介质,属于通信技术领域。该方法包括:第一设备获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;第一设备采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;第一设备根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。

Description

信道信息处理方法、装置、通信设备及存储介质
相关申请的交叉引用
本申请主张在2022年08月15日在中国提交的申请号为202210977681.1的中国专利的优先权,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,具体涉及一种信道信息处理方法、装置、通信设备及存储介质。
背景技术
为了确保不同网络节点之间可以联合工作,一个网络节点(以下称为节点A)可以将获取的信道信息输入节点A的编码器,得到输出的压缩信道信息,并将该信道信息和该压缩信道信息发送给另一个网络节点(以下称为节点B),以使节点B根据该信道信息和该压缩信道信息,校正节点B的编码器,从而可以使节点A的编码器与节点B的编码器相匹配,以实现不同网络节点之间的联合工作。
然而,按照上述方法,由于上述信道信息的数量和压缩信道信息的数量通常较多,因此导致传输信道信息的开销较大。
发明内容
本申请实施例提供一种信道信息处理方法、装置、通信设备及存储介质,能够解决传输信道信息的开销较大的问题。
第一方面,提供了一种信道信息处理方法,该方法包括:第一设备获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;第一设备采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;第一设备根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。
第二方面,提供了一种信道信息处理装置,该装置包括获取模块、压缩模块和发送模块;获取模块,用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;压缩模块,用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;发送模块,用于根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。
第三方面,提供了一种信道信息处理方法,该方法包括:第二设备接收第一设备 发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;第二设备采用目标解压缩方法,对第四信道信息进行解压缩;其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
第四方面,提供了一种信道信息处理装置,该装置包括接收模块和解压缩模块;接收模块,用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;解压缩模块,用于采用目标解压缩方法,对第四信道信息进行解压缩;其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
第五方面,提供了一种通信设备,该通信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,或者实现如第三方面所述的方法的步骤。
第六方面,提供了一种通信设备,包括处理器及通信接口,其中,所述通信接口用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;所述处理器用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;所述通信接口还用于根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;或者,
所述通信接口用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;所述处理器用于采用目标解压缩方法,对第四信道信息进行解压缩;其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
第七方面,提供了一种通信***,包括:如第一方面所述的第一设备和如第三方面所述的第二设备,所述第一设备可用于执行如第一方面所述的信道信息处理方法的步骤,所述第二设备可用于执行如第三方面所述的信道信息处理方法的步骤。
第八方面,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。
第九方面,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,或者实现如第三方面所述的方法。
第十方面,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所述的信道信息处理方法的步骤,或者实现如第三方面所述的信道信息处理方法的步骤。
在本申请实施例中,由于第一设备可以获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;且可以采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;并可以根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。通过该方案,由于第一设备可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
附图说明
图1是本申请实施例可应用的一种无线通信***的框图;
图2是一种神经网络的示意图;
图3是一种神经网络中的神经元的示意图;
图4是本申请实施例提供的一种信道信息处理方法的流程图之一;
图5是本申请实施例提供的一种信道信息处理方法的流程图之二;
图6是本申请实施例提供的一种信道信息处理装置的结构示意图之一;
图7是本申请实施例提供的一种信道信息处理装置的结构示意图之二;
图8是本申请实施例提供的通信设备的示意图;
图9是本申请实施例提供的通信设备为终端时的硬件结构示意图;
图10是本申请实施例提供的通信设备为网络侧设备时的硬件结构示意图。
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(VUE)、行人终端(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12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12可以包括基站、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。核心网设备可以包含但不限于如下至少一项:核心网节点、核心网功能、移动管理实体(Mobility Management Entity,MME)、接入移动管理功能(Access and Mobility Management Function,AMF)、会话管理功能(Session Management Function,SMF)、用户平面功能(User Plane Function,UPF)、策略控制功能(Policy Control Function,PCF)、策略与计费规则功能单元(Policy and Charging Rules Function,PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function,EASDF)、统一数据管理(Unified Data Management,UDM),统一数据仓储(Unified Data Repository,UDR)、归属用户服务器(Home Subscriber Server,HSS)、集中式网络配置(Centralized network configuration,CNC)、网络存储功能(Network Repository Function,NRF),网络开放功能(Network Exposure Function,NEF)、本地NEF(Local NEF,或L-NEF)、绑定支持功能(Binding Support Function,BSF)、应用功能(Application Function,AF)等。需要说明的是,在本申请实施例中仅以NR***中的核心网设备为例进行介绍,并不限定核心网设备的具体类型。
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信息处 理方法、装置、通信设备及存储介质进行详细地说明。
目前,人工智能在各个领域获得了广泛的应用,将人工智能融入无线通信网络,以显著提升吞吐量、时延以及用户容量等技术指标是未来的无线通信网络的重要任务。
人工智能模块有多种实现方式,例如,神经网络、决策树、支持向量机、贝叶斯分类器等。图2示出了一种神经网络的示意图,如图2所示,神经网络由神经元组成;图3示出了一种神经网络中的神经元的示意图,如图3所示,a为输入,w为权值(乘性系数),b为偏置(加性系数),σ(.)为激活函数。常见的激活函数可以包括Sigmoid(即S型生长曲线)、tanh(即双曲正切函数)、线性整流函数(Rectified Linear Unit,ReLU)等。神经网络的参数可以通过梯度优化算法进行优化。梯度优化算法是一类最小化或最大化目标函数(也称为损失函数)的算法,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,构建一个神经网络模型f(.),通过该神经网络模型f(.),可以输入x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。合适的w,b可以使该损失函数的值达到最小,而损失值越小,该神经网络模型越接近于真实情况。
目前常见的优化算法,基本均基于误差反向传播(error Back Propagation,BP)算法。BP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,GD)、随机梯度下降(Stochastic Gradient Descent,SGD)、mini-batch gradient descent(即小批量梯度下降)、动量法(即Momentum)、Nesterov(具体为带动量的随机梯度下降)、自适应梯度下降(ADAptive GRADient descent,Adagrad)、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,并将梯度传给上一层。
另一方面,由信息论可知,准确的信道状态信息(channel state information,CSI)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,更加匹配信道的状态。例如,信道质量指示(channel quality indicator,CQI)可以用于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)可以用于实现特征波束成形(即eigen beamforming),以最大化接收信号的强度,或者用于抑制干扰(如小区间干扰、多用户之间干扰等)。因此,自从多天线技术(multi-input multi-output,MIMO)被提出以来,CSI的获取一直都是研究热点。
通常,基站在某个时间单元的某些时频资源上发送CSI参考信号,终端可以根据 该CSI参考信号进行信道估计,计算这个时间单元上的信道信息,并通过码本将PMI反馈给基站,从而基站可以根据终端反馈的码本信息组合出信道信息,在下一次CSI上报之前,以此进行数据预编码及多用户调度。而为了进一步减少CSI反馈开销,终端可以将每个子带上报PMI改成按照delay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,即将delay域信息压缩之后再上报。同样,为了减少开销,基站可以先对CSI参考信号进行预编码,然后将编码后的CSI参考信号发送给终端,终端获取的是经过编码之后的CSI参考信号对应的信道,从而终端只需要在基站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。
结合人工智能,在基于人工智能的空口设计中存在一类用例,要求模型在多个不同的网络节点中分模块部署,而推理过程将由所有模块联合进行。其中最典型的用例之一是基于人工智能的信道信息压缩,要求在终端部署模型的编码器(即Encoder)部分,且在基站端部署模型的解码器(即Decoder)部分,并联合使用编码器与解码器进行推理。一般来讲,模型的所有模块需要联合进行训练,这一过程通常在某一个网络节点进行,然后将训练好的各模块分发至其他节点处。然而上述过程涉及到来自不同厂商的网络设备之间的模型交互,容易产生模型知识产权的泄露问题。而separate training(即单独训练)则是一种可以避免上述问题的方法,即各节点分别训练自己的模块,然后通过某种手段保证各模块之间能够配对使用。目前最常见的保证各模块之间能联合工作的方法是某节点训练完成自己的模块后,将发送该模块的输入输出数据至其他节点,其他节点依据接收到的数据再训练各自的模块,从而实现在***露节点各自的模型细节的情况下各模块间能够联合工作。
然而,由于某模块的输入输出数据中包括的信道信息数量通常较多,因此发送该模块的输入输出数据往往开销较大(远远大于传输模型的开销,甚至是百倍千倍的关系)。从而需要对输入输出数据再进行压缩,以将数据传输的开销降低到可接受的水平。但针对输入输出数据的二次压缩问题,目前业界尚无清晰的解决方案。
为了解决上述问题,在本申请实施例提供的信道信息处理方法中,由于第一设备可以获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;且可以采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;并可以根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。通过该方案,由于第一设备可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
本申请实施例提供一种信道信息处理方法,图4示出了本申请实施例提供的信道 信息处理方法的流程图。如图4所示,本申请实施例提供的信道信息处理方法可以包括下述的步骤401至步骤403。
步骤401、第一设备获取目标信道信息。
本申请实施例中,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
可选地,本申请实施例中,第一信道信息的数量可以为一个或多个,每个第二信道信息与一个第一信道信息对应。
可选地,本申请实施例中,第一信道信息可以包括以下至少之一:参考信号的信息、传输信道的信息、控制信道的信息。
可选地,本申请实施例中,上述参考信号可以为:同步信号块(Synchronization Signal Block,SSB)、CSI参考信号(即CSI-RS)、跟踪参考信号(Tracking Reference Signal,TRS)、相位跟踪参考信号(Phase-tracking Reference Signal,PTRS)或信道探测参考信号(Sounding Reference Signal,SRS)等。
可选地,本申请实施例中,上述传输信道可以为:物理下行共享信道(Physical downlink shared channel,PDSCH)或物理上行共享信道(Physical Uplink Shared Channel,PUSCH)等。
可选地,本申请实施例中,上述控制信道可以为:物理下行控制信道(Physical downlink control channel,PDCCH)或物理上行控制信道(Physical Uplink Control Channel,PUCCH)等。
可选地,本申请实施例中,第一压缩方法可以为:基于第三代合作伙伴计划(3rd Generation Partnership Project,3GPP)码本构成的编码器的压缩方法;其中,3GPP码本包括多种类型,例如,类型1(即Type I)码本、类型2(即Type II)码本等。
可选地,本申请实施例中,第一压缩方法可以用于将信道信息压缩为PMI。可选地,本申请实施例中,第一压缩方法可以包括层共享压缩(即layer common)方法,或层/秩单独特殊压缩(即layer/rank specific)方法等。其中,在层共享压缩方法中,数据是每个层共享压缩的,即无论多少层或秩为多少,每个层的信道信息均是并行、单独压缩的(例如,2层的每一层的压缩方法,与4层的每一层的压缩方法均相同),且不需要进行秩等信息的交互;在层/秩单独特殊压缩方法中,不同层数或不同秩采用不同的压缩方法(例如,2层的压缩方法,与4层的压缩方法不同),且还需要交互秩、层索引等信息,或者按照某个顺序映射压缩后的信道信息(例如,按照层强度从高到底的顺序映射每个层压缩后的信道信息)。
步骤402、第一设备采用第二压缩方法压缩第三信道信息。
本申请实施例中,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同。
可选地,本申请实施例中,第二压缩方法可以包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
本申请实施例中,由于第二压缩方法可以包括编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法和文本压缩算法中的至少之一,因此第一设备可以采用不同的压缩方法压缩第三信道信息,从而可以提高压缩信道信息的灵活性。
可选地,本申请实施例中,上述量化方法可以包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
可选地,本申请实施例中,在上述权值共享量化法或分组量化法中,可以将浮点数划分到多个集合,每个集合中的元素共享一个值。
可选地,本申请实施例中,在上述参数编码法中,可以对浮点数进行编码(包括有损编码或无损编码等),例如,对浮点数进行霍夫曼编码。
可选地,本申请实施例中,在上述变换域量化法中,可以先将浮点数变换到另一个域(例如,频域、S域、Z域等),再进行量化操作,然后再反变换回来。
可选地,本申请实施例中,在上述乘积量化方法中,可以把浮点数划分成多个子空间,并在每个子空间上进行量化操作。
本申请实施例中,由于上述量化方法可以包括均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法和乘积量化方法中的至少之一,因此可以丰富第一设备压缩第三信道信息时采用的压缩方法,从而可以进一步提高压缩信道信息的灵活性。
可选地,本申请实施例中,第三信道信息为第一信道信息和第二信道信息;那么,第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法相同或不同。
本申请实施例中,在第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法不同的情况下,第二压缩方法包括上述编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法和文本压缩算法中的至少之二。
本申请实施例中,由于第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法相同或不同,因此可以进一步提高压缩信道信息的灵活性。
可选地,本申请实施例中,上述步骤402具体可以通过下述的步骤402a实现。
步骤402a、第一设备根据第三设备配置的压缩参数,采用第二压缩方法压缩第三信道信息。
本申请实施例中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
可选地,本申请实施例中,上述核心网节点可以包括:网络数据分析功能(NWDAF,Network Data Analytics Function,NWDAF)、位置管理功能(Location Management Function,LMF)或神经网络处理节等。
可选地,本申请实施例中,上述接入网节点可以包括:基站或新定义的神经网络处理节点等。
可选地,本申请实施例中,上述第三方节点可以为在网络上层(Over the top,OTT)服务器,通常为不属于3GPP实体的节点或设备。
可选地,本申请实施例中,第一设备和第二设备均可以为终端或网络侧设备,第一设备与第二设备可以相同或不同。
可选地,本申请实施例中,上述压缩参数可以包括以下至少之一:压缩率、码本参数等。
本申请实施例中,由于第一设备可以根据核心网节点、接入网节点和第三方节点中的至少之一配置的压缩参数,采用第二压缩方法压缩第三信道信息,因此可以提高压缩信道信息的准确性。
下面对第一设备采用不同的第二压缩方法压缩第三信道信息的具体方法,进行详细说明。
可选地,本申请实施例中,第二压缩方法为上述编码器压缩方法;那么上述步骤402具体可以通过下述的步骤402b和步骤402c实现。
步骤402b、第一设备采用编码器压缩方法,通过第一编码器压缩第三信道信息,得到第一压缩信道信息,并通过第一译码器解压缩第一压缩信道信息,得到第五信道信息。可选地,本申请实施例中,第一压缩信道信息可以为:第一设备将第三信道信息输入第一编码器之后,第一编码器输出的与第三信道信息对应的PMI、编码比特或压缩信息等。
可选地,本申请实施例中,第一编码器可以为:基于3GPP码本构成的编码器;第一编码器可以用于将信道信息压缩为PMI。
可选地,本申请实施例中,第一译码器可以为:基于3GPP码本构成的译码器;第一译码器可以用于将PMI恢复成以下任一项:信道信息、预编码矩阵、预编码向量。
本申请实施例中,3GPP码本包括多种类型,例如,类型1(Type I)码本、类型2(Type II)码本等。
可选地,本申请实施例中,第一编码器可以为基于第一码本的编码器,或可以为基于第二码本的编码器。
可选地,本申请实施例中,第一译码器可以为基于第一码本的译码器,或可以为基于第二码本的译码器。
本申请实施例中,第二码本为:将第一码本中的部分参数扩大取值范围后的码本。
例如,第一码本中的L参数(用于选择波束数目的参数)的取值范围为[1,2,3,4,6],那么第二码本中的L参数的取值范围可以小于网络侧端的CSI参考信号天线端口接口;和/或,第一码本中的β参数(菲灵系数占全部系数比例)的取值为[1/4 1/2 3/4],那么第二码本中的β参数的取值还可以为1/8,3/8,1/16等;和/或,第一码本中的M参数(用于选择delay数)的取值为[1 2 4 8],那么第二码本中的M参数的取值还可以为16,32等;和/或,第一码本中的pv参数(用于计算M参数中用到的一个系数的参数)的取值为[1/8 1/4 1/2],那么第二码本中的pv参数的取值还可以为1/16,1/32,1/64等。
可选地,本申请实施例中,第一码本可以为基于3GPP的码本,例如,Type I码本、Type II码本等。
可选地,本申请实施例中,第二码本可以为基于3GPP的码本进行增强的码本。
本申请实施例中,由于第一编码器和第一译码器均可以是基于第一码本的或是基于第二码本的,因此可以丰富第一编码器和第一译码器的编码方式,从而可以提高通过第一编码器和第一译码器处理信道信息的灵活性。
步骤402c、第一设备通过第二编码器压缩第五信道信息,得到第二压缩信道信息。
可选地,本申请实施例中,第二编码器可以为:基于第一压缩方法将信道信息进 行压缩的模块。
本申请实施例中,第四信道信息(即压缩后的目标信道信息)中包括:第一压缩信道信息和第二压缩信道信息。
需要说明的是,由于第二压缩方法均为有损压缩的方法,因此使用第二压缩方法压缩第三信道信息,会带来第三信道信息的压缩损失。而将第三信道信息通过第一编码器进行压缩,且通过第一译码器解压缩之后,再通过第二编码器进行压缩,此时得到的第二压缩信道信息不存在第一编码器带来的压缩损失,但会减少信道特征多样化,即第三信道信息可以取任意浮点值,而此时第二压缩信道信息只能取解压缩空间的有限值。例如,第三信道信息的某个浮点数可以取-1至1之间的任意浮点值,若第一编码器为3bit均匀量化,则第二压缩信道信息只能有8个取值。
本申请实施例中,由于第一设备可以采用编码器压缩方法,通过第一编码器压缩第三信道信息,得到第一压缩信道信息,并通过第二编码器对第一译码器解压缩第一压缩信道信息得到信道信息进行压缩,得到第二压缩信道信息,因此可以避免压缩损失,从而可以提高信道信息处理的准确性。
可选地,本申请实施例中,第一信道信息包括至少一个信道信息,第二信道信息包括:与该至少一个信道信息对应的至少一个压缩信道信息,第二压缩方法为上述信道信息筛选方法;那么第一设备具体可以通过下述的方式一和/或方式二,压缩第三信道信息。
方式一
可选地,本申请实施例中,上述步骤402具体可以通过下述的步骤402d实现。
步骤402d、第一设备对第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息。
其中,上述N个信道信息簇包括上述M个信道信息簇,N为正整数,M为小于或等于N的正整数。
本申请实施例中,第四信道信息中包括:从上述M个信道信息簇中选取的信道信息。
可选地,本申请实施例中,在第一设备对第三信道信息进行聚类之前,可以先进行升维操作或降维操作,然后在升维后的高维空间对第三信道信息进行聚类,或者,在降维后的低维空间对第三信道信息进行聚类。
可选地,本申请实施例中,上述至少一个信道信息可以为对应信道信息簇的中心点或中心点附近的信道信息。
方式二
可选地,本申请实施例中,上述步骤402具体可以通过下述的步骤402e实现。
步骤402e、第一设备根据第一信息,将第三信道信息分为P组信道信息,并从Q组信道信息的每组信道信息中选取至少一个信道信息。
其中,上述P组信道信息包括上述Q组信道信息,P为正整数,Q为小于或等于P的正整数。
本申请实施例中,第四信道信息中包括:从上述Q组信道信息中选取的信道信息。
本申请实施例中,第一信息包括以下至少之一:信噪比、视距(Line of Sight,LOS)、 非视距(Non Line Of Sight,NLOS)、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
例如,以第一信息包括上述信噪比为例,第一设备可以根据该信噪比,将第三信道信息分为:信噪比为10dB~11dB的信道信息,信噪比为11dB~12dB的信道信息,信噪比为12dB~13dB的信道信息。
又例如,以第一信息包括上述LOS和NLOS为例,第一设备可以根据该LOS和NLOS,将第三信道信息分为:LOS的信道信息,NLOS的信道信息。
可选地,本申请实施例中,上述信道信息的收集时间信息可以包括以下至少之一:信道信息的收集时间,信道信息的收集时间戳。
本申请实施例中,由于在第一信道信息包括至少一个信道信息,第二信道信息包括:与该至少一个信道信息对应的至少一个压缩信道信息的情况下,第一设备可以通过上述方式一和/或方式二,对第三信道信息进行筛选以压缩第三信道信息,因此可以进一步提高第一设备压缩第三信道信息的灵活性。
步骤403、第一设备根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息。
本申请实施例中,第四信道信息包括以下任一项:
(1)第一信道信息和压缩后的第二信道信息;
(2)压缩后的第一信道信息,以及第二信道信息;
(3)压缩后的第一信道信息,以及压缩后的第二信道信息。
可以理解,若第四信道信息包括上述(1),则第一设备压缩了第三信道信息中的第二信道信息;若第四信道信息包括上述(2),则第一设备压缩了第三信道信息中的第一信道信息;若第四信道信息包括上述(3),则第一设备压缩了第三信道信息中的第一信道信息和第二信道信息。
可选地,本申请实施例中,第一设备可以将第四信道信息整体发送给第二设备,以节省***开销。
在本申请实施例提供的信道信息处理方法中,由于第一设备可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
本申请实施例提供一种信道信息处理方法,图5示出了本申请实施例提供的信道信息处理方法的流程图。如图5所示,本申请实施例提供的信道信息处理方法可以包括下述的步骤501和步骤502。
步骤501、第二设备接收第一设备发送的第四信道信息。
本申请实施例中,第四信道信息包括以下任一项:
(1)第一信道信息和压缩后的第二信道信息;
(2)压缩后的第一信道信息,以及第二信道信息;
(3)压缩后的第一信道信息,以及压缩后的第二信道信息。
其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信 道信息。
步骤502、第二设备采用目标解压缩方法,对第四信道信息进行解压缩。
可选地,本申请实施例中,目标解压缩方法可以为与上述第二压缩方法对应的解压缩方法。
可选地,本申请实施例中,第二设备对第四信道信息进行解压缩,以恢复出第一信道信息和第二信道信息,从而可以根据恢复出的信道信息进行模块训练,以匹配第一设备的编码解码方式,如此可以实现第一设备和第二设备的联合工作。
可选地,本申请实施例中,上述步骤502具体可以通过下述的步骤502a实现。
步骤502a、第二设备根据第三设备配置的解压缩参数,采用目标解压缩方法,对第四信道信息进行解压缩。
本申请实施例中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
对本申请实施例中的其它描述,以及各技术特征所能实现的效果,具体可以参照上述实施例中的相关描述,为了避免重复,此处不再赘述。
在本申请实施例提供的信道信息处理方法中,一方面,由于第二设备可以接收第一设备发送的第四信道信息(即压缩后的信道信息),因此可以降低接收信道信息的开销,从而可以提升信道信息的传输效率;另一方面,由于第二设备可以采用目标解压缩方法,对第四信道信息进行解压缩,因此可以使第二设备与第一设备的编码方式相匹配,从而可以实现联合工作。
下面对本申请实施例提供的信道信息处理方法进行示例性地说明。
示例性地,以终端先训练编码器,然后将该终端侧编码器的输入输出数据发送至基站,以帮助训练解码器的separate training为例,该终端可以执行以下步骤:
步骤1.终端根据已有的信道信息训练编码器模型。
训练所需信道信息的获取方法包括以下至少之一:终端根据下行参考信号(例如CSI-RS)估计得到信道信息;终端接收其他网络节点发送的信道信息;终端使用仿真模型生成信道信息。
终端训练编码器的方式包括以下至少之一:先训练完整的编码器解码器模型,然后取出编码器部分使用;使用半监督方式直接训练编码器。
步骤2.终端选取一定数量的测试信道信息通过编码器模型后得到成对的信道信息(即目标信道信息),即成对的测试信道信息(即第一信道信息)和测试信道压缩信息(即第二信道信息),其中,测试信道信息为编码器的输入,测试信道压缩信息为编码器的输出。
终端选取测试信道信息的范围不限,可以与步骤1中的信道信息重合;选取测试信道信息的数量可以由网络侧设备指示,也可以由终端自行决定。
步骤3.终端对步骤2中的测试信道信息进行压缩,得到成对的压缩后的测试信道信息和测试信道压缩信息(即第四信道信息)。
步骤4.终端将压缩后的测试信道信息和测试信道压缩信息,以及指示对应的解压缩方法的信息上报至基站。
步骤5.基站接收压缩后的测试信道信息和测试信道压缩信息,以及指示对应的解 压缩方法的信息,并按照恢对应的解压缩方法恢复信道信息。
步骤6.基站根据恢复出的信道信息训练解码器,并通知终端相关的训练结果以及进行后续的模型管理。
又示例性地,以基站先训练编码器,然后将终端侧训练编码器所需的输入输出数据发送至该终端来帮助训练编码器的separate training为例,该基站可以执行以下步骤:
步骤a.基站根据已有的信道信息训练解码器模型。
基站训练所需信道信息的获取方法包括以下至少之一:基站根据上行参考信号(例如SRS)估计得到信道信息;基站接收其他网络节点发送的信道西悉尼(如收集终端估计得到的下行信道信息);基站使用仿真信道模型生成信道信息。
基站训练解码器的方式包括:先训练完整的编码器解码器模型,然后取出解码器部分使用。
步骤b.基站选取一定数量的测试信道信息并得到成对的信道信息(即目标信道信息),即成对的测试信道信息(即第一信道信息)和测试信道压缩信息(即第二信道信息),其中,测试信道信息为编码器的输入,测试信道压缩信息为编码器的输出。
基站选取测试信道信息的范围不限,可以与步骤1中的信道信息重合;选取测试信道信息的数量可以由高层指示,也可以由基站自行决定。
选取的测试信道信息要求能够适应基站的解码器模型,一般来讲,基站主要使用解码器模块进行CSI的解压缩,但基站也可以通过保留训练解码器模块时的编码器模块等方法来获得测试信道信息。
步骤c.基站对步骤b中的测试信道信息进行压缩,得到成对的压缩后的测试信道信息和测试信道压缩信息(即第四信道信息)。
步骤d.基站将压缩后的测试信道信息和测试信道压缩信息,以及指示对应的解压缩方法的信息,下发至请求数据或相关功能的终端(或其他相关网络节点,例如OTT server等)。
步骤e.终端(或其他相关网络节点)接收压缩后的测试信道信息和测试信道压缩信息,以及指示对应的解压缩方法的信息,并按照对应的解压缩方法恢复出信道信息。
步骤f.终端(或其他相关网络节点)根据会付出的信道信息训练编码器,并上报基站相关的训练结果以及进行后续所需的模型管理信息。
本申请实施例提供的信道信息处理方法,执行主体可以为信道信息处理装置。本申请实施例中以信道信息处理装置执行信道信息处理方法为例,说明本申请实施例提供的信道信息处理装置。
结合图6,本申请实施例提供一种信道信息处理装置60,该信道信息处理装置60可以包括获取模块61、压缩模块62和发送模块63。获取模块61,可以用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。压缩模块62,可以用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同。发送模块63,可以用于根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及 第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。
一种可能的实现方式中,第二压缩方法可以包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
一种可能的实现方式中,第二压缩方法为上述编码器压缩方法。压缩模块62,具体可以用于采用该编码器压缩方法,通过第一编码器压缩第三信道信息,得到第一压缩信道信息,且通过第一译码器解压缩第一压缩信道信息,得到第五信道信息,并通过第二编码器压缩第五信道信息,得到第二压缩信道信息。其中,第四信道信息中包括:第一压缩信道信息和第二压缩信道信息。
一种可能的实现方式中,第一编码器可以为基于第一码本的编码器,或可以为基于第二码本的编码器;和/或,第一译码器可以为基于第一码本的译码器,或可以为基于第二码本的译码器。其中,第二码本为:将第一码本中的部分参数扩大取值范围后的码本。
一种可能的实现方式中,第一信道信息包括至少一个信道信息,第二信道信息包括:与该至少一个信道信息对应的至少一个压缩信道信息,第二压缩方法为上述信道信息筛选方法。压缩模块62,具体可以用于对第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息;该N个信道信息簇包括该M个信道信息簇,N为正整数,M为小于或等于N的正整数;其中,第四信道信息中包括:从该M个信道信息簇中选取的信道信息;和/或,具体可以用于根据第一信息,将第三信道信息分为P组信道信息,并从Q组信道信息的每组信道信息中选取至少一个信道信息;该P组信道信息包括该Q组信道信息,P为正整数,Q为小于或等于P的正整数;其中,第四信道信息中包括:从该Q组信道信息中选取的信道信息;第一信息包括以下至少之一:信噪比、LOS、NLOS、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
一种可能的实现方式中,上述量化方法可以包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
一种可能的实现方式中,第三信道信息为第一信道信息和第二信道信息。第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法相同或不同。
一种可能的实现方式中,压缩模块62,具体可以用于根据第三设备配置的压缩参数,采用第二压缩方法压缩第三信道信息。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的信道信息处理装置中,由于该信道信息处理装置可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
本申请实施例中的信道信息处理装置可以是电子设备,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信息处理装置能够实现图4的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。
结合图7,本申请实施例提供一种信道信息处理装置70,该信道信息处理装置70可以包括接收模块71和解压缩模块72。接收模块71,可以用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。解压缩模块72,可以用于采用目标解压缩方法,对第四信道信息进行解压缩。其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
一种可能的实现方式中,解压缩模块72,具体可以用于根据第三设备配置的解压缩参数,采用目标解压缩方法,对第四信道信息进行解压缩。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的信道信息处理装置中,一方面,由于该信道信息处理装置可以接收第一设备发送的第四信道信息(即压缩后的信道信息),因此可以降低接收信道信息的开销,从而可以提升信道信息的传输效率;另一方面,由于该信道信息处理装置可以采用目标解压缩方法,对第四信道信息进行解压缩,因此可以使该信道信息处理装置与第一设备的编码方式相匹配,从而可以实现联合工作。
本申请实施例中的信道信息处理装置可以是电子设备,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信息处理装置能够实现图5的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。
可选地,如图8所示,本申请实施例还提供一种通信设备800,包括处理器801和存储器802,存储器802上存储有可在所述处理器801上运行的程序或指令,例如,该通信设备800为第一设备时,该程序或指令被处理器801执行时实现上述第一设备侧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800为第二设备时,该程序或指令被处理器801执行时实现上述第二设备侧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通信设备,包括处理器和通信接口,通信接口用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息;处理器用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同;通信接口还用于根据压缩第三信道信息 的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;或者,
通信接口用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;处理器用于采用目标解压缩方法,对第四信道信息进行解压缩;其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
该通信设备实施例与上述信道信息处理方法实施例对应,上述信道信息处理方法实施例的各个实施过程和实现方式均可适用于该通信设备实施例中,且能达到相同的技术效果。具体地,该通信设备可以为终端,或者可以为网络侧设备。
以上述通信设备为终端为例,图9为该终端的硬件结构示意图。
该终端1000包括但不限于:射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009以及处理器1010等中的至少部分部件。
本领域技术人员可以理解,终端1000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1010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9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1004可以包括图形处理单元(Graphics Processing Unit,GPU)10041和麦克风10042,图形处理器10041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1006可包括显示面板10061,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10061。用户输入单元1007包括触控面板10071以及其他输入设备10072中的至少一种。触控面板10071,也称为触摸屏。触控面板10071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10072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1001接收来自网络侧设备的下行数据后,可以传输给处理器1010进行处理;另外,射频单元1001可以向网络侧设备发送上行数据。通常,射频单元1001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1009可用于存储软件程序或指令以及各种数据。存储器1009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1009可以包括易失性存储器或非易失性存储器,或者,存储器1009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1009包括但不限于这些和任意其它适合类型的存储器。
处理器1010可包括一个或多个处理单元;可选地,处理器1010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1010中。
其中,以终端1000为上述第一设备为例,射频单元1001,可以用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。处理器1010,可以用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同。射频单元1001,还可以用于根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。
一种可能的实现方式中,第二压缩方法可以包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
一种可能的实现方式中,第二压缩方法为上述编码器压缩方法。处理器1010,具体可以用于采用该编码器压缩方法,通过第一编码器压缩第三信道信息,得到第一压缩信道信息,且通过第一译码器解压缩第一压缩信道信息,得到第五信道信息,并通过第二编码器压缩第五信道信息,得到第二压缩信道信息。其中,第四信道信息中包括:第一压缩信道信息和第二压缩信道信息。
一种可能的实现方式中,第一编码器可以为基于第一码本的编码器,或可以为基于第二码本的编码器;和/或,第一译码器可以为基于第一码本的译码器,或可以为基于第二码本的译码器。其中,第二码本为:将第一码本中的部分参数扩大取值范围后的码本。
一种可能的实现方式中,第一信道信息包括至少一个信道信息,第二信道信息包括:与该至少一个信道信息对应的至少一个压缩信道信息,第二压缩方法为上述信道信息筛选方法。处理器1010,具体可以用于对第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息;该N个信道信息簇包括该M个信道信息簇,N为正整数,M为小于或等于N的正整数;其中,第四信道信息中包括:从该M个信道信息簇中选取的信道信息;和/或,具体可以用于根据第一信息,将第三信道信息分为P组信道信息,并从Q组信道信息的每组信道 信息中选取至少一个信道信息;该P组信道信息包括该Q组信道信息,P为正整数,Q为小于或等于P的正整数;其中,第四信道信息中包括:从该Q组信道信息中选取的信道信息;第一信息包括以下至少之一:信噪比、LOS、NLOS、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
一种可能的实现方式中,上述量化方法可以包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
一种可能的实现方式中,第三信道信息为第一信道信息和第二信道信息。第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法相同或不同。
一种可能的实现方式中,处理器1010,具体可以用于根据第三设备配置的压缩参数,采用第二压缩方法压缩第三信道信息。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的终端中,由于该终端可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
本申请实施例提供的终端能够实现上述方法实施例中第一设备实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
以终端1000为上述第二设备为例,射频单元1001,可以用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。处理器1010,可以用于采用目标解压缩方法,对第四信道信息进行解压缩。其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
一种可能的实现方式中,处理器1010,具体可以用于根据第三设备配置的解压缩参数,采用目标解压缩方法,对第四信道信息进行解压缩。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的终端中,一方面,由于该终端可以接收第一设备发送的第四信道信息(即压缩后的信道信息),因此可以降低接收信道信息的开销,从而可以提升信道信息的传输效率;另一方面,由于该终端可以采用目标解压缩方法,对第四信道信息进行解压缩,因此可以使该终端与第一设备的编码方式相匹配,从而可以实现联合工作。
本申请实施例提供的终端能够实现上述方法实施例中第二设备实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
以上述通信设备为网络侧设备为例,图10为该网络侧设备的硬件结构示意图。
如图10所示,该网络侧设备100包括:天线11、射频装置12、基带装置13、处理器14和存储器15。天线11与射频装置12连接。在上行方向上,射频装置12通过 天线11接收信息,将接收的信息发送给基带装置13进行处理。在下行方向上,基带装置13对要发送的信息进行处理,并发送给射频装置12,射频装置12对收到的信息进行处理后经过天线11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13中实现,该基带装置13包括基带处理器。
基带装置13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,其中一个芯片例如为基带处理器,通过总线接口与存储器15连接,以调用存储器15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16,该接口例如为通用公共无线接口(common public radio interface,CPRI)。
具体地,本申请实施例的网络侧设备100还包括:存储在存储器15上并可在处理器14上运行的指令或程序,处理器14调用存储器15中的指令或程序执行图6至图7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。
其中,以网络侧设备100为上述第一设备为例,射频装置12,可以用于获取目标信道信息,目标信道信息包括第一信道信息和第二信道信息,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。处理器14,可以用于采用第二压缩方法压缩第三信道信息,第三信道信息为:第一信道信息和第二信道信息中的至少之一,第二压缩方法与第一压缩方法不同。射频装置12,还可以用于根据压缩第三信道信息的压缩结果,向第二设备发送第四信道信息;其中,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。
一种可能的实现方式中,第二压缩方法可以包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
一种可能的实现方式中,第二压缩方法为上述编码器压缩方法。处理器14,具体可以用于采用该编码器压缩方法,通过第一编码器压缩第三信道信息,得到第一压缩信道信息,且通过第一译码器解压缩第一压缩信道信息,得到第五信道信息,并通过第二编码器压缩第五信道信息,得到第二压缩信道信息。其中,第四信道信息中包括:第一压缩信道信息和第二压缩信道信息。
一种可能的实现方式中,第一编码器可以为基于第一码本的编码器,或可以为基于第二码本的编码器;和/或,第一译码器可以为基于第一码本的译码器,或可以为基于第二码本的译码器。其中,第二码本为:将第一码本中的部分参数扩大取值范围后的码本。
一种可能的实现方式中,第一信道信息包括至少一个信道信息,第二信道信息包括:与该至少一个信道信息对应的至少一个压缩信道信息,第二压缩方法为上述信道信息筛选方法。处理器14,具体可以用于对第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息;该N个信道信息簇包括该M个信道信息簇,N为正整数,M为小于或等于N的正整数;其中,第四信道信息中包括:从该M个信道信息簇中选取的信道信息;和/或,具体可以用于根据第一信息,将第三信道信息分为P组信道信息,并从Q组信道信息的每组信道 信息中选取至少一个信道信息;该P组信道信息包括该Q组信道信息,P为正整数,Q为小于或等于P的正整数;其中,第四信道信息中包括:从该Q组信道信息中选取的信道信息;第一信息包括以下至少之一:信噪比、LOS、NLOS、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
一种可能的实现方式中,上述量化方法可以包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
一种可能的实现方式中,第三信道信息为第一信道信息和第二信道信息。第一设备压缩第一信道信息的压缩方法,与第一设备压缩第二信道信息的压缩方法相同或不同。
一种可能的实现方式中,处理器14,具体可以用于根据第三设备配置的压缩参数,采用第二压缩方法压缩第三信道信息。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的网络侧设备中,由于该网络侧设备可以先采用第二压缩方法,对目标信道信息中的第一信道信息和/或第二信道信息进行压缩,然后再根据压缩结果,向第二设备发送第一信道信息和压缩后的第二信道信息,或发送压缩后的第一信道信息,以及第二信道信息,或发送压缩后的第一信道信息,以及压缩后的第二信道信息,因此可以避免目标信道信息的冗余,从而可以降低传输信道信息的开销。
本申请实施例提供的网络侧设备能够实现上述方法实施例中第一设备实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
以网络侧设备100为上述第二设备为例,射频装置12,可以用于接收第一设备发送的第四信道信息,第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息。处理器14,可以用于采用目标解压缩方法,对第四信道信息进行解压缩。其中,第二信道信息为:采用第一压缩方法对第一信道信息进行压缩后的压缩信道信息。
一种可能的实现方式中,处理器14,具体可以用于根据第三设备配置的解压缩参数,采用目标解压缩方法,对第四信道信息进行解压缩。其中,第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
在本申请实施例提供的网络侧设备中,一方面,由于该网络侧设备可以接收第一设备发送的第四信道信息(即压缩后的信道信息),因此可以降低接收信道信息的开销,从而可以提升信道信息的传输效率;另一方面,由于该网络侧设备可以采用目标解压缩方法,对第四信道信息进行解压缩,因此可以使该网络侧设备与第一设备的编码方式相匹配,从而可以实现联合工作。
本申请实施例提供的网络侧设备能够实现上述方法实施例中第二设备实现的各个过程,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上述信道信息处理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,实现上述信道信息处理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上述信道信息处理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:如上述各实施例所述的第一设备和第二设备,所述第一设备可用于执行如上述第一设备侧方法实施例的各个过程的步骤,所述第二设备可用于执行如上述第二设备侧方法实施例的各个过程的步骤。
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 (22)

  1. 一种信道信息处理方法,所述方法包括:
    第一设备获取目标信道信息,所述目标信道信息包括第一信道信息和第二信道信息,所述第二信道信息为:采用第一压缩方法对所述第一信道信息进行压缩后的压缩信道信息;
    所述第一设备采用第二压缩方法压缩第三信道信息,所述第三信道信息为:所述第一信道信息和所述第二信道信息中的至少之一,所述第二压缩方法与所述第一压缩方法不同;
    所述第一设备根据压缩所述第三信道信息的压缩结果,向第二设备发送第四信道信息;
    其中,所述第四信道信息包括以下任一项:
    所述第一信道信息和压缩后的所述第二信道信息;
    压缩后的所述第一信道信息,以及所述第二信道信息;
    压缩后的所述第一信道信息,以及压缩后的所述第二信道信息。
  2. 根据权利要求1所述的方法,其中,所述第二压缩方法包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
  3. 根据权利要求2所述的方法,其中,所述第二压缩方法为所述编码器压缩方法;
    所述第一设备采用第二压缩方法压缩第三信道信息,包括:
    所述第一设备采用所述编码器压缩方法,通过第一编码器压缩所述第三信道信息,得到第一压缩信道信息,并通过第一译码器解压缩所述第一压缩信道信息,得到第五信道信息;
    所述第一设备通过第二编码器压缩所述第五信道信息,得到第二压缩信道信息;
    其中,所述第四信道信息中包括:所述第一压缩信道信息和所述第二压缩信道信息。
  4. 根据权利要求3所述的方法,其中,
    所述第一编码器为基于第一码本的编码器,或为基于第二码本的编码器;
    和/或,
    所述第一译码器为基于第一码本的译码器,或为基于第二码本的译码器;
    其中,所述第二码本为:将所述第一码本中的部分参数扩大取值范围后的码本。
  5. 根据权利要求2所述的方法,其中,所述第一信道信息包括至少一个信道信息,所述第二信道信息包括:与所述至少一个信道信息对应的至少一个压缩信道信息,所述第二压缩方法为所述信道信息筛选方法;
    所述第一设备采用第二压缩方法压缩第三信道信息,包括:
    所述第一设备对所述第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息;所述N个信道信息簇包括所述M个信道信息簇,N为正整数,M为小于或等于N的正整数;
    其中,所述第四信道信息中包括:从所述M个信道信息簇中选取的信道信息;
    和/或,
    所述第一设备根据第一信息,将所述第三信道信息分为P组信道信息,并从Q组 信道信息的每组信道信息中选取至少一个信道信息;所述P组信道信息包括所述Q组信道信息,P为正整数,Q为小于或等于P的正整数;
    其中,所述第四信道信息中包括:从所述Q组信道信息中选取的信道信息;
    所述第一信息包括以下至少之一:信噪比、视距LOS、非视距NLOS、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
  6. 根据权利要求2所述的方法,其中,所述量化方法包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
  7. 根据权利要求1至6中任一项所述的方法,其中,所述第三信道信息为所述第一信道信息和所述第二信道信息;
    所述第一设备压缩所述第一信道信息的压缩方法,与所述第一设备压缩所述第二信道信息的压缩方法相同或不同。
  8. 根据权利要求1至6中任一项所述的方法,其中,
    所述第一设备采用第二压缩方法压缩第三信道信息,包括:
    所述第一设备根据第三设备配置的压缩参数,采用所述第二压缩方法压缩所述第三信道信息;
    其中,所述第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
  9. 一种信道信息处理方法,所述方法包括:
    第二设备接收第一设备发送的第四信道信息,所述第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;
    所述第二设备采用目标解压缩方法,对所述第四信道信息进行解压缩;
    其中,所述第二信道信息为:采用第一压缩方法对所述第一信道信息进行压缩后的压缩信道信息。
  10. 根据权利要求9所述的方法,其中,所述第二设备采用目标解压缩方法,对所述第四信道信息进行解压缩,包括:
    所述第二设备根据第三设备配置的解压缩参数,采用所述目标解压缩方法,对所述第四信道信息进行解压缩;
    其中,所述第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
  11. 一种信道信息处理装置,所述装置包括获取模块、压缩模块和发送模块;
    所述获取模块,用于获取目标信道信息,所述目标信道信息包括第一信道信息和第二信道信息,所述第二信道信息为:采用第一压缩方法对所述第一信道信息进行压缩后的压缩信道信息;
    所述压缩模块,用于采用第二压缩方法压缩第三信道信息,所述第三信道信息为:所述第一信道信息和所述第二信道信息中的至少之一,所述第二压缩方法与所述第一压缩方法不同;
    所述发送模块,用于根据压缩所述第三信道信息的压缩结果,向第二设备发送第四信道信息;
    其中,所述第四信道信息包括以下任一项:
    所述第一信道信息和压缩后的所述第二信道信息;
    压缩后的所述第一信道信息,以及所述第二信道信息;
    压缩后的所述第一信道信息,以及压缩后的所述第二信道信息。
  12. 根据权利要求11所述的装置,其中,所述第二压缩方法包括以下至少之一:编码器压缩方法、信道信息筛选方法、量化方法、主成分分析方法、文本压缩算法。
  13. 根据权利要求12所述的装置,其中,所述第二压缩方法为所述编码器压缩方法;
    所述压缩模块,具体用于采用所述编码器压缩方法,通过第一编码器压缩所述第三信道信息,得到第一压缩信道信息,且通过第一译码器解压缩所述第一压缩信道信息,得到第五信道信息,并通过第二编码器压缩所述第五信道信息,得到第二压缩信道信息;
    其中,所述第四信道信息中包括:所述第一压缩信道信息和所述第二压缩信道信息。
  14. 根据权利要求13所述的装置,其中,
    所述第一编码器为基于第一码本的编码器,或为基于第二码本的编码器;
    和/或,
    所述第一译码器为基于第一码本的译码器,或为基于第二码本的译码器;
    其中,所述第二码本为:将所述第一码本中的部分参数扩大取值范围后的码本。
  15. 根据权利要求12所述的装置,其中,所述第一信道信息包括至少一个信道信息,所述第二信道信息包括:与所述至少一个信道信息对应的至少一个压缩信道信息,所述第二压缩方法为所述信道信息筛选方法;
    所述压缩模块,具体用于对所述第三信道信息进行聚类,得到N个信道信息簇,并从M个信道信息簇的每个信道信息簇中选取至少一个信道信息;所述N个信道信息簇包括所述M个信道信息簇,N为正整数,M为小于或等于N的正整数;
    其中,所述第四信道信息中包括:从所述M个信道信息簇中选取的信道信息;
    和/或,
    具体用于根据第一信息,将所述第三信道信息分为P组信道信息,并从Q组信道信息的每组信道信息中选取至少一个信道信息;所述P组信道信息包括所述Q组信道信息,P为正整数,Q为小于或等于P的正整数;
    其中,所述第四信道信息中包括:从所述Q组信道信息中选取的信道信息;
    所述第一信息包括以下至少之一:信噪比、LOS、NLOS、频域信道特征、时域信道特征、空域信道特征、信道信息的收集时间信息。
  16. 根据权利要求12所述的装置,其中,所述量化方法包括以下至少之一:均匀量化方法、非均匀量化方法、权值共享量化法、分组量化法、参数编码法、变换域量化法、乘积量化方法。
  17. 根据权利要求11至16中任一项所述的装置,其中,所述第三信道信息为所述第一信道信息和所述第二信道信息;
    所述第一设备压缩所述第一信道信息的压缩方法,与所述第一设备压缩所述第二信道信息的压缩方法相同或不同。
  18. 根据权利要求11至16中任一项所述的装置,其中,
    所述压缩模块,具体用于根据第三设备配置的压缩参数,采用所述第二压缩方法压缩所述第三信道信息;
    其中,所述第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
  19. 一种信道信息处理装置,所述装置包括接收模块和解压缩模块;
    所述接收模块,用于接收第一设备发送的第四信道信息,所述第四信道信息包括以下任一项:第一信道信息和压缩后的第二信道信息;压缩后的第一信道信息,以及第二信道信息;压缩后的第一信道信息,以及压缩后的第二信道信息;
    所述解压缩模块,用于采用目标解压缩方法,对所述第四信道信息进行解压缩;
    其中,所述第二信道信息为:采用第一压缩方法对所述第一信道信息进行压缩后的压缩信道信息。
  20. 根据权利要求19所述的装置,其中,
    所述解压缩模块,具体用于根据第三设备配置的解压缩参数,采用所述目标解压缩方法,对所述第四信道信息进行解压缩;
    其中,所述第三设备包括以下至少之一:核心网节点、接入网节点、第三方节点。
  21. 一种通信设备,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1至8中任一项所述的信道信息处理方法的步骤,或者实现如权利要求9至10中任一项所述的信道信息处理方法的步骤。
  22. 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8中任一项所述的信道信息处理方法的步骤,或者实现如权利要求9至10中任一项所述的信道信息处理方法的步骤。
PCT/CN2023/111731 2022-08-15 2023-08-08 信道信息处理方法、装置、通信设备及存储介质 WO2024037380A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210977681.1 2022-08-15
CN202210977681.1A CN117641446A (zh) 2022-08-15 2022-08-15 信道信息处理方法、装置、通信设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024037380A1 true WO2024037380A1 (zh) 2024-02-22

Family

ID=89940702

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/111731 WO2024037380A1 (zh) 2022-08-15 2023-08-08 信道信息处理方法、装置、通信设备及存储介质

Country Status (2)

Country Link
CN (1) CN117641446A (zh)
WO (1) WO2024037380A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019237344A1 (en) * 2018-06-15 2019-12-19 Qualcomm Incorporated Joint spatial and frequency domain compression of csi feedback
CN113508545A (zh) * 2019-01-21 2021-10-15 高通股份有限公司 用于具有频域压缩的信道状态信息的频域限制的技术
US20220052739A1 (en) * 2018-09-28 2022-02-17 Qualcomm Incorporated Channel state information (csi) with spatial and time domain compression
WO2022148490A1 (zh) * 2021-01-08 2022-07-14 北京紫光展锐通信技术有限公司 Csi的上报方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019237344A1 (en) * 2018-06-15 2019-12-19 Qualcomm Incorporated Joint spatial and frequency domain compression of csi feedback
US20220052739A1 (en) * 2018-09-28 2022-02-17 Qualcomm Incorporated Channel state information (csi) with spatial and time domain compression
CN113508545A (zh) * 2019-01-21 2021-10-15 高通股份有限公司 用于具有频域压缩的信道状态信息的频域限制的技术
WO2022148490A1 (zh) * 2021-01-08 2022-07-14 北京紫光展锐通信技术有限公司 Csi的上报方法及装置

Also Published As

Publication number Publication date
CN117641446A (zh) 2024-03-01

Similar Documents

Publication Publication Date Title
WO2023246618A1 (zh) 信道矩阵处理方法、装置、终端及网络侧设备
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
KR20230138538A (ko) 정보 리포팅 방법, 장치, 제1 장치 및 제2 장치
WO2023179473A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024032606A1 (zh) 信息传输方法、装置、设备、***及存储介质
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023179570A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023185995A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024104126A1 (zh) 更新ai网络模型的方法、装置和通信设备
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
WO2024055974A1 (zh) Cqi传输方法、装置、终端及网络侧设备
WO2023185980A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024027683A1 (zh) 模型匹配方法、装置、通信设备及可读存储介质
WO2024093999A1 (zh) 信道信息的上报和接收方法、终端及网络侧设备
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024055993A1 (zh) Cqi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
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024041420A1 (zh) 测量反馈处理方法、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
CN117335849A (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
CN116939647A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
CN118055420A (zh) 波束测量方法、装置、终端、网络侧设备及存储介质

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: 23854283

Country of ref document: EP

Kind code of ref document: A1