Wireless communication method, terminal device and network device

By using bitstream feedback and decoder model training in wireless communication to generate a second decoder, the problem of insufficient accuracy of model performance monitoring of terminal equipment is solved, and the accuracy and adaptability of model performance monitoring are improved.

WO2024243879A1PCT designated stage expired Publication Date: 2024-12-05GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/097537
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

The prior art is difficult to effectively monitor model performance in terminal equipment, resulting in insufficient accuracy of model performance monitoring, especially in wireless communications, AI-based CSI feedback performance, especially in wireless communications, model generalization is weak, Unable to adapt to a changing wireless channel environment.

Method used

Through bitstream feedback between the network device and the terminal device and training of the decoder model, a second decoder is generated. The terminal device can locally monitor model performance through the first encoder and the second decoder to ensure the accuracy of model performance monitoring. .

Benefits of technology

The accuracy of model performance monitoring is improved, the model switching overhead is reduced, and the second decoder is adapted to different configurations through generalization performance optimization, improving the monitoring performance on the terminal side.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023097537_05122024_PF_FP_ABST
    Figure CN2023097537_05122024_PF_FP_ABST
Patent Text Reader

Abstract

A wireless communication method, a terminal device, and a network device. The method comprises: a network device acquires a first bitstream group, wherein the first bitstream group comprises bitstreams fed back by terminals in a first terminal group to the network device, each terminal in the first terminal group is deployed with a first encoder, and the bitstreams are obtained by the terminals encoding channel state information on the basis of the first encoders; the network device decodes the first bitstream group on the basis of a first decoder to obtain a first output information group, wherein the first output information group comprises output information obtained by the network device decoding the bitstreams in the first bitstream group; the network device performs training on the basis of the first bitstream group and the first output information group to obtain a second decoder; and the network device sends model information of the second decoder to the terminals in the first terminal group.
Need to check novelty before this filing date? Find Prior Art

Description

Wireless communication method, terminal device and network device Technical Field

[0001] The embodiments of the present application relate to the field of communications, and specifically to a wireless communication method, terminal device, and network device. Background Art

[0002] In related technologies, to ensure the performance of artificial intelligence (AI)-based channel state information (CSI) feedback, consideration has been given to introducing model performance monitoring methods, for example, by monitoring model performance through terminals. Therefore, ensuring the accuracy of model performance monitoring by terminals is an urgent issue.

[0003] Summary of the Invention

[0004] The present application provides a wireless communication method, terminal device and network device, which can ensure the accuracy of model performance monitoring.

[0005] In a first aspect, a method for wireless communication is provided, including: a method for wireless communication, a network device and a terminal device, the method including: the network device obtains a first bit stream group, the first bit stream group including a bit stream fed back to the network device by each terminal in a first terminal group, wherein a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by each terminal encoding channel state information based on the first encoder; the network device decodes the first bit stream group based on a first decoder to obtain a first output information group, wherein the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group; the network device performs training based on the first bit stream group and the first output information group to obtain a second decoder; the network device sends model information of the second decoder to each terminal in the first terminal group.

[0006] In a second aspect, a method for wireless communication is provided, including: a network device sends a first bit stream group and / or a first output information group to a first terminal, the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to the network device, a first encoder is deployed on each terminal in the first terminal group, the bit stream is obtained by each terminal encoding input channel state information based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder.

[0007] According to a third aspect, a method for wireless communication is provided, comprising: a first terminal sends a first bit stream to a network device, wherein a first encoder is deployed on the first terminal, the first bit stream is obtained by the first terminal encoding channel state information based on the first encoder, and a first decoder is deployed on the network device; the first terminal receives model information of a second decoder sent by the network device, the second decoder is obtained by training the network device based on the first bit stream group and a first output information group, the first bit stream group includes the bit stream fed back by each terminal in the first terminal group to the network device, the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on the first decoder, and the first terminal group includes the first terminal.

[0008] In a fourth aspect, a method for wireless communication is provided, including: a first terminal obtains a first bit stream group and a first output information group, the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to a network device, a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by each terminal encoding the input channel state information based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder; the first terminal is trained based on the first bit stream group and the first output information group to obtain a second decoder.

[0009] In a fifth aspect, a terminal device is provided for executing the method in any one of the third to fourth aspects or their respective implementations. Specifically, the terminal device includes a functional module for executing the method in any one of the third to fourth aspects or their respective implementations.

[0010] In a sixth aspect, a network device is provided for executing the method of any one of the first to second aspects or their respective implementations.

[0011] Specifically, the network device includes a functional module for executing the method in any one of the first to second aspects or their respective implementations.

[0012] In a seventh aspect, a terminal device is provided, comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of any one of the third to fourth aspects or their respective implementations.

[0013] In an eighth aspect, a network device is provided, comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of any one of the first to second aspects or their respective implementations.

[0014] In a ninth aspect, a chip is provided for implementing the method described in any one of the first to fourth aspects or their respective implementations. Specifically, the chip includes a processor configured to load and execute a computer program from a memory, causing a device equipped with the chip to perform the method described in any one of the first to fourth aspects or their respective implementations.

[0015] In a tenth aspect, a computer-readable storage medium is provided for storing a computer program, which enables a computer to execute the method of any one of the first to fourth aspects or its various implementations.

[0016] In an eleventh aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method of any one of the first to fourth aspects or any of their implementations.

[0017] In the twelfth aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method in any one of the above-mentioned first to fourth aspects or their respective implementations.

[0018] Through the above technical solution, a network device or terminal device can use the feedback bitstream and the output information of the first decoder deployed on the network device as a data set to train a second decoder, thereby enabling the second decoder to simulate the functions of the first decoder and establish a relationship between the feedback bitstream and the output of the first decoder. In this way, the terminal device can locally monitor the model functions of the first encoder and first decoder through its own first encoder and second decoder, thereby ensuring the accuracy of model performance monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.

[0020] FIG2 is a schematic diagram of a neuron structure.

[0021] FIG3 is a schematic diagram of a neural network.

[0022] FIG4 is a schematic diagram of a convolutional neural network.

[0023] FIG5 is a schematic diagram of an LSTM unit.

[0024] FIG6 is a schematic structural diagram of a CSI autoencoder.

[0025] FIG7 is a schematic diagram of a model performance monitoring method provided in an embodiment of the present application.

[0026] FIG8 is a schematic diagram of another model performance monitoring method provided in an embodiment of the present application.

[0027] FIG9 is a schematic interaction diagram of a wireless communication method provided according to an embodiment of the present application.

[0028] FIG10 is a schematic interaction diagram of a model training method according to an embodiment of the present application.

[0029] FIG11 is a schematic interaction diagram of a model training method according to another embodiment of the present application.

[0030] FIG12 is a schematic interaction diagram of another wireless communication method provided according to an embodiment of the present application.

[0031] FIG13 is a schematic interaction diagram of a model training method according to an embodiment of the present application.

[0032] Figure 14 is a schematic interaction diagram of a model training method according to another embodiment of the present application.

[0033] Figure 15 is a schematic block diagram of a network device provided according to an embodiment of the present application.

[0034] Figure 16 is a schematic block diagram of a terminal device provided according to an embodiment of the present application.

[0035] Figure 17 is a schematic block diagram of a terminal device provided according to an embodiment of the present application.

[0036] Figure 18 is a schematic block diagram of a network device provided according to an embodiment of the present application.

[0037] Figure 19 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

[0038] Figure 20 is a schematic block diagram of a chip provided according to an embodiment of the present application.

[0039] Figure 21 is a schematic block diagram of a communication system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. With respect to the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0041] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.

[0042] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0043] Optionally, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.

[0044] Optionally, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, where the authorized spectrum can also be considered as an unshared spectrum.

[0045] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0046] The terminal device can be a station (STA) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0047] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0048] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0049] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0050] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0051] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.

[0052] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0053] For example, a communication system 100 used in an embodiment of the present application is shown in FIG1 . The communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal or terminal). The network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices within the coverage area.

[0054] FIG1 exemplarily shows a network device and two terminal devices. Optionally, the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0055] Optionally, the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0056] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system 100 shown in FIG1 as an example, the communication device may include a network device 110 and a terminal device 120 having a communication function. The network device 110 and the terminal device 120 may be the specific devices described above and will not be described in detail here. The communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0057] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0058] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0059] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0060] In the embodiments of the present application, "pre-defined" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device or a network device). The present application does not limit the specific implementation method. For example, pre-defined may refer to information defined in a protocol.

[0061] In the embodiments of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and this application does not limit this.

[0062] To facilitate a better understanding of the embodiments of the present application, the neural network and deep learning related to the present application are explained.

[0063] A neural network is a computational model consisting of multiple interconnected neuron nodes, where the connections between nodes represent weighted values ​​from input signals to output signals, called weights. Each node performs a weighted summation (SUM) on different input signals and outputs them through a specific activation function (f). Figure 2 is a schematic diagram of a neuron structure, where a1, a2, …, an represent input signals, w1, w2, …, wn represent weights, f represents the activation function, and t represents the output.

[0064] A simple neural network, shown in Figure 3, consists of an input layer, hidden layers, and an output layer. By using different connections, weights, and activation functions among multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. Each node in the previous level is connected to all nodes in the next level. This neural network is a fully connected neural network, also known as a deep neural network (DNN).

[0065] Deep learning utilizes deep neural networks with multiple hidden layers, significantly improving the network's ability to learn features and fitting complex, nonlinear mappings from input to output. Consequently, it has found widespread application in speech and image processing. In addition to deep neural networks, deep learning also includes other commonly used basic structures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for different tasks.

[0066] The basic structure of a convolutional neural network includes an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer, as shown in Figure 4. Each neuron in the convolution kernel of the convolutional layer is locally connected to its input, and the introduction of the pooling layer extracts the local maximum or average features of a certain layer, effectively reducing the network parameters and mining local features, enabling the convolutional neural network to converge quickly and achieve excellent performance.

[0067] RNNs are neural networks that model sequential data and have achieved remarkable success in natural language processing applications such as machine translation and speech recognition. Specifically, the network memorizes information from past moments and uses it in the calculation of current outputs. This means that nodes in the hidden layers are no longer disconnected but connected, and the input to a hidden layer includes not only the input layer but also the output of the previous hidden layer. Common RNN structures include long short-term memory (LSTM) and gated recurrent unit (GRU). Figure 5 shows a basic LSTM cell structure, which can include a tanh activation function. Unlike RNNs, which only consider the most recent state, the LSTM cell state determines which states should be retained and which should be forgotten, addressing the shortcomings of traditional RNNs in long-term memory.

[0068] To facilitate a better understanding of the embodiments of the present application, a codebook-based channel state information (CSI) feedback scheme related to the present application is described.

[0069] In the NR system, codebook-based eigenvector feedback is usually used to enable the base station to obtain downlink CSI. Specifically, the base station sends a downlink CSI-RS to the terminal, and the terminal uses the CSI-RS to estimate the CSI of the downlink channel, and performs eigenvalue decomposition on the estimated downlink channel to obtain the eigenvector corresponding to the downlink channel. Furthermore, the NR system provides two codebook design schemes: Type 1 and Type 2. Among them, the Type 1 codebook is used for CSI feedback of conventional accuracy, mainly for CSI feedback in single-user multiple input multiple output (SU-MIMO) scenarios, and the Type 2 codebook is mainly used to improve the transmission performance of multiple user multiple input multiple output (MU-MIMO).

[0070] Both Type 1 and Type 2 codebooks use a two-level codebook feedback mechanism: W = W1W2. W1 describes the wideband, long-term characteristics of the channel, while W2 describes the subband, short-term characteristics of the channel. Generally, the Type 2 codebook utilizes a higher number of feedback bits, resulting in higher-precision CSI feedback performance.

[0071] To facilitate a better understanding of the embodiments of the present application, the CSI feedback solution based on artificial intelligence (AI) related to the present application is described.

[0072] Given the tremendous success of AI technology, especially deep learning, in computer vision and natural language processing, the communications field has begun to explore the use of deep learning to address technical challenges that are difficult to solve with traditional communications methods, such as deep learning. The neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal side as much as possible on the base station side. This ensures the restoration of channel information while also providing the possibility of reducing CSI feedback overhead on the terminal side. Deep learning-based CSI feedback treats channel information as an image to be compressed, uses a deep learning autoencoder to compress and feed back the channel information, and reconstructs the compressed channel image at the transmitter, which can preserve the channel information to a greater extent.

[0073] The structure of a typical channel information feedback system (or AI-based CSI autoencoder) is shown in Figure 6. The entire feedback system is divided into an encoder and a decoder, which are deployed at the terminal transmitter and the base station receiver, respectively. After the transmitter obtains the channel information through channel estimation, the encoder's neural network compresses and encodes the channel information matrix and feeds the compressed bit stream back to the receiver through the air interface feedback link. The receiver recovers the channel information based on the feedback bit stream through the decoder to obtain complete feedback channel information. The backbone network of the encoder and decoder shown in Figure 6 can adopt a DNN composed of multiple layers of fully connected layers, a CNN composed of multiple layers of convolutional layers, or an RNN with structures such as LSTM and GRU. Various neural network architectures such as residual and self-attention mechanisms can also be used to improve the performance of the encoder and decoder.

[0074] The CSI input of the encoder and the CSI output of the decoder can both be full channel information or feature vector information obtained based on full channel information. Therefore, the current deep learning-based channel information feedback methods are mainly divided into full channel information feedback and feature vector feedback. Although the former can achieve compression and feedback of full channel information, the feedback bit stream overhead is relatively high. The AI-based feature vector feedback method can achieve higher CSI feedback accuracy with the same feedback bit overhead, or significantly reduce the feedback overhead while achieving the same CSI feedback accuracy.

[0075] Codebook-based CSI feedback methods have good generalization capabilities for different users and various channel scenarios. However, because the codebook is pre-set, it does not effectively utilize the correlation between different antenna ports and subbands. Therefore, under the same feedback overhead, the feedback performance is poor; or under the same feedback performance, the feedback overhead is high.

[0076] The AI-based CSI feedback solution can extract the correlation of feature vectors in the time and frequency domains, thereby achieving better feedback performance with lower feedback overhead. However, the encoder and decoder used in this solution both use neural network models. When the training set environment is consistent with the actual deployment environment of the model (i.e., the test set environment), the AI-based CSI feedback solution can achieve significant gains in both feedback overhead and feedback performance. However, when the wireless channel environment changes due to factors such as cell switching and user mobility, the model may not be suitable for the current wireless channel environment due to its weak generalization, resulting in poor AI-based CSI feedback performance.

[0077] Therefore, it is necessary to design reasonable model monitoring and management methods to update and switch models in a timely manner.

[0078] In some scenarios, for AI-based CSI feedback, consider monitoring the performance of the AI ​​model based on intermediate key performance indicators (Intermediate KPIs).

[0079] In some implementations, the model performance is monitored on the network side. FIG7 is a schematic diagram showing the implementation of model performance monitoring by the network. Specifically, the terminal can periodically or non-periodically report the input information of the encoder as the true label to the network, and the network side calculates the intermediate key performance indicators between the output of the decoder and the reported true label, such as the squared generalized cosine similarity (SGCS), and determines whether the performance of the model meets the requirements based on the intermediate key performance indicators. For example, when the SGCS of the decoder output and the reported true label is greater than a certain threshold, the model performance is considered to meet the requirements, otherwise it does not meet the requirements. This solution requires the terminal to quantize and report the true label, for example, using float32, float16, or a high-precision Type2 codebook and other quantization methods, but the reporting of a large number of true labels will bring about a large uplink feedback overhead and delay.

[0080] In other implementations, model performance monitoring is implemented on the terminal side. Figure 8 shows a schematic diagram of model performance monitoring implemented by the terminal. Specifically, a second decoder needs to be deployed on the terminal side. The terminal uses the bitstream output by the encoder as the input of the second decoder to produce a second output. The terminal can calculate the intermediate key performance indicators of the encoder input information and the second output, and determines whether the model performance meets the requirements based on these intermediate key performance indicators. For example, when the SGCS of the encoder input information and the second output is greater than a certain threshold, the model performance is considered to meet the requirements; otherwise, it does not meet the requirements. This solution does not require the terminal to report the true label periodically or aperiodically, so there is no additional uplink overhead and latency. However, the accuracy of this model performance monitoring method depends on the implementation of the second decoder. Considering that the first decoder is usually trained on the network side, due to the privatization of the model implementation, the network side may not be able to send the implemented first decoder to the terminal for model performance monitoring. However, when the second decoder is implemented by the terminal itself, there may be a serious problem: there is a mismatch between the SGCS obtained on the terminal side (based on the encoder input and second output) and the actual SGCS (based on the encoder input and first output). For example, the SGCS performance obtained on the terminal side is good, but the actual SGCS performance is poor, resulting in missed detections; or the SGCS performance obtained on the terminal side is poor, but the actual SGCS performance is good, resulting in false detections. Both situations will greatly reduce the accuracy of the terminal-side model performance monitoring.

[0081] Therefore, how to improve the accuracy of model performance monitoring on the terminal side is an urgent problem to be solved.

[0082] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0083] FIG9 is a schematic flowchart of a wireless communication method 200 according to an embodiment of the present application. The method 200 may be executed by a terminal device in the communication system shown in FIG1 . As shown in FIG9 , the method 200 includes the following contents:

[0084] S201, a network device obtains a first bitstream group;

[0085] S202, the network device decodes the first bit stream group based on a first decoder to obtain a first output information group;

[0086] S203: The network device performs training based on the first bit stream group and the first output information group to obtain a second decoder;

[0087] S204: The network device sends the model information of the second decoder to each terminal in the first terminal group.

[0088] In some embodiments, the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to the network device, wherein a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by each terminal encoding the channel state information based on the first encoder.

[0089] In some embodiments, the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group.

[0090] In some embodiments, the first terminal group includes one terminal (denoted as case 1), or may include multiple terminals (denoted as case 2). Optionally, the multiple terminals may include some or all terminals in the serving cell corresponding to the network device.

[0091] In some embodiments, the first encoder and the first decoder correspond to each other. For example, the first encoder and the first decoder are jointly trained, or the first encoder and the first decoder form an AI-based CSI autoencoder.

[0092] It should be understood that when the first terminal group includes multiple terminals, the model information of the first encoders deployed on the multiple terminals may be the same, or may be different, and this application does not limit this.

[0093] In some embodiments, deploying a first encoder on the terminal may mean that the terminal stores model information of the first encoder, for example, the model structure, model parameters and other information of the first encoder. The model information of the first encoder may be obtained by training the terminal, or obtained by training the network device and sent to the terminal, or obtained by joint training of the terminal and the network device, or obtained by training the third-party device and sent to the terminal. This application does not specifically limit the method for obtaining the first encoder.

[0094] In some embodiments, deploying a first decoder on a network device may mean that the network device stores model information of the first decoder, for example, model structure, model parameters and other information of the first decoder. The model information of the first decoder may be obtained by training the network device, or obtained by terminal training and sent to the network device, or obtained by joint training of the terminal and the network device, or obtained by training by a third-party device and sent to the network device. This application does not specifically limit the method for obtaining the first decoder.

[0095] In some embodiments, the first terminal group includes a terminal, such as a first terminal, and the first bit stream group may include a first bit stream, which is a bit stream fed back by the first terminal to the network device, that is, the first bit stream is obtained by the network device from the first terminal.

[0096] Correspondingly, the first output information group may include first output information, and the first output information may be obtained by the network device decoding the first bit stream based on the first decoder.

[0097] It should be understood that the present application does not limit the number of bit streams included in the first bit stream. For example, the first terminal can feedback S bit streams to the network device. The number S is predefined, or configured by the network device, or can be selected by the first terminal itself.

[0098] In some embodiments, the first terminal group includes multiple terminals, and the first bit stream group may include a bit stream fed back by each of the multiple terminals, that is, the first bit stream group is obtained by the network device from the multiple terminals.

[0099] Correspondingly, the first output information group may include output information obtained by respectively decoding the bit streams fed back by the multiple terminals by the network device based on the first decoder.

[0100] It should be understood that in the embodiment of the present application, the number of bit streams fed back by the multiple terminals to the network device may be the same or different, and the length of the bit stream fed back by each terminal to the network device may be the same or different, and the present application does not limit this. For example, the number S of bit streams fed back by each terminal to the network device is predefined, or configured by the network device, or can be selected by each terminal. For example, the length L of the bit stream fed back by each terminal to the network device is predefined, or configured by the network device, or can be selected by each terminal.

[0101] In some embodiments, the bit stream fed back by the terminal in the first terminal group to the network device may be obtained by the terminal encoding the channel state information based on the first encoder deployed on the terminal. The channel state information may be full channel information, or it may be channel information obtained by processing the full channel information, such as feature vector information obtained based on the full channel information. This application does not limit this.

[0102] In some embodiments, the network device performs training based on the first bitstream group and the first output information group to obtain the second decoder, which may include:

[0103] The network device takes the first bit stream group as input and the first output information group as a label to train the second decoder.

[0104] It should be understood that the bit stream in the first bit stream group and the output information in the first output information group have a corresponding relationship. When training the second decoder, the network device uses the corresponding bit stream and output information as input and label respectively for model training.

[0105] It should be noted that since the label used to train the second decoder is the output information of the first decoder, rather than the actual downlink channel state information, the purpose of the second decoder is not to restore the most accurate downlink channel state information, but to simulate the function of the first decoder and establish a relationship between the bit stream fed back by the terminal and the output information of the first decoder. Generally speaking, the first decoder is implemented as a private model on the network device side, which may be relatively complex (for example, a deep CNN or Transformer model with a complex structure); while the second decoder is trained under the guidance of the output information of the first decoder, which can make the implementation of the model relatively simple (for example, a CNN or Transformer model with a shallow structure). By sending the second decoder to the terminal instead of directly sending the first decoder publicly, the network device can reduce the overhead of model downloading while protecting the privatization of the first decoder, and enable the terminal to monitor the model performance of the combination of the first encoder and the first decoder locally through the combination of the first encoder and the second decoder.

[0106] In some embodiments, the network device sending the model information of the second decoder to each terminal in the first terminal group may include:

[0107] If the first terminal group includes one terminal, the network device may send the model information of the second decoder to the one terminal in a unicast manner; or

[0108] If the first terminal group includes multiple terminals, the network device may send the model information of the second decoder to the one terminal in a broadcast, multicast, or unicast manner.

[0109] In some embodiments, the model information of the second decoder may include information such as the model structure and model parameters of the second decoder.

[0110] 10 and 11 , the specific processes of the second decoder training method in the above two cases are respectively described.

[0111] In the example of FIG10 , the first terminal group only includes the first terminal. As shown in FIG10 , the following steps may be included:

[0112] S211: The first terminal sends a first bit stream to a network device.

[0113] The first terminal is deployed with a first encoder, and the first terminal can encode the channel state information based on the first encoder to obtain a first bit stream, and further feed back the first bit stream to the network device.

[0114] For example, the first terminal measures S downlink CSI samples within a period of time, denoted as W, and outputs S bit streams of fixed length L (ie, the first bit stream may include S bit streams), denoted as B, through the first encoder.

[0115] S212: The network device may decode the first bit stream based on the first decoder to obtain first output information.

[0116] That is, the first output information is the channel state information recovered by the network device through the first decoder, or in other words, the decoding information of the bit stream fed back by the first terminal.

[0117] For example, the network device inputs S bit streams into the first decoder and outputs S output information (ie, the first output information may include S output information), which is recorded as

[0118] S213: The network device trains a second decoder based on the first bit stream and the first output information.

[0119] For example, the second decoder is trained using the first bit stream as input and the first output information as a label.

[0120] Continuing with the above example, the network device can take B as input and As labels, the second decoder is trained.

[0121] S214: The network device sends the model of the second decoder to the first terminal.

[0122] Furthermore, the first terminal can detect the model performance of the first encoder and the first decoder based on the combination of the first encoder and the second decoder. For example, the first terminal can obtain X downlink CSI samples by measurement, input the X downlink CSI samples into the first encoder to generate a second bit stream, input the second bit stream into the second decoder to obtain X output information, and then calculate the intermediate key performance indicators (such as SGCS) of the X output information and the X downlink CSI samples, and determine the model performance of the first encoder and the first decoder based on the intermediate key performance indicators. For example, if the SGCS of the X output information and the X downlink CSI samples is greater than the first threshold, it is considered that the model performance of the first encoder and the first decoder meets the requirements, otherwise it does not meet the requirements. The first threshold can be predefined, configured by the network device, or it can be determined by the first terminal itself.

[0123] In some embodiments, when the second decoder is trained based on the bit stream feedback from a single terminal, the second decoder can be considered to be exclusive to the terminal (UE-specific), or the second decoder can be considered to be adapted to the physical resource configuration (physical resource configuration, referred to as: pr-config) and channel state information feedback overhead configuration (CSI feedback payload configuration, referred to as: fp-config) of the single terminal.

[0124] In some embodiments, the physical resource configuration of the terminal may include, but is not limited to:

[0125] The number of subbands and antenna ports configured on the terminal.

[0126] In some embodiments, the channel state information feedback overhead configuration of the terminal may refer to, for example, the length of a bit stream for CSI feedback by the terminal.

[0127] In the example of FIG11 , the first terminal group includes multiple terminals, such as terminal 1, terminal 2, ..., terminal J, where J is a positive integer greater than 1. As shown in FIG11 , the following steps may be included:

[0128] S221: A terminal in the first terminal group sends a bit stream to a network device.

[0129] For example, the first terminal group may include J terminals, which are respectively recorded as terminal 1, terminal 2, ..., terminal J, and the first bit stream group may include bit streams fed back by the J terminals.

[0130] A first encoder is deployed on each of the J terminals, and the bit stream fed back by each terminal may be obtained by encoding the measured channel state information based on the first encoder deployed thereon.

[0131] For example, terminal j (1≤j≤J) measures S over a period of time. j downlink CSI samples, denoted as W j , after the first encoder deployed on terminal j, the generated S j Fixed length L j The bit stream is denoted as B j .

[0132] It should be understood that the length of the bit stream fed back by each of the J terminals (i.e., L) can be the same or different, and the number of bit streams fed back (i.e., S) can be the same or different, and this application does not limit this.

[0133] S222: The network device may decode the bit stream fed back by the terminals in the first terminal group using the first decoder to obtain a first output information group, that is, the first output information group includes decoding information corresponding to the bit stream fed back by each terminal in the first terminal group.

[0134] For example, the network device sends the S feedback from terminal j to j The bit stream is input into the first decoder and output S j Output information, recorded as

[0135] S223: The network device trains a second decoder based on the first bit stream group and the first output information group.

[0136] For example, the second decoder is trained with the first bitstream group as input and the first output information group as a label.

[0137] Continuing with the above example, the network device may combine the J feedback bit streams and output information B j As input, The labels form the training dataset and the second decoder is trained.

[0138] S224: The network device sends the model of the second decoder to the J terminals in the first terminal group.

[0139] In some embodiments, when the second decoder is trained based on a bitstream fed back by a terminal group (i.e., multiple terminals), the second decoder may be considered UE-group-specific, i.e., the second decoder may be adapted to all terminals in the terminal group. Alternatively, when the terminal group includes all terminals in a cell, the second decoder may be considered cell-specific, i.e., the second decoder may be adapted to all terminals in the cell.

[0140] In some embodiments, when the second decoder is trained based on the bit stream feedback from a terminal group (i.e., multiple terminals), the adaptability of the second decoder can be determined by the configuration of the multiple terminals, which configuration may include but is not limited to physical resource configuration and channel state information feedback overhead configuration.

[0141] In some embodiments, multiple terminals in the first terminal group have the same physical resource configuration (pr-config). In this case, it can be considered that the second decoder is adapted to the same physical resource configuration, that is, the second decoder is for a specific physical resource configuration, that is, the second decoder is pr-config-specific.

[0142] In some embodiments, the plurality of terminals in the first terminal group have different physical resource configurations. In this case, the second decoder can be considered to be generalizable to different physical resource configurations, or the second decoder can be considered to be adapted to the different physical resource configurations. For example, the plurality of terminals includes J terminals, and the number of antenna ports corresponding to terminal j is P. j , the number of antenna ports of the J terminals is different, then the second decoder can be considered to be adapted to any antenna port number configuration, or the second decoder can be considered to be adapted to P1, P2, ..., P J .

[0143] In some embodiments, the plurality of terminals in the first terminal group have the same channel state information feedback overhead configuration (fp-config). In this case, the second decoder may be considered adapted to the same channel state information feedback overhead configuration. In other words, the second decoder is adapted to a specific channel state information feedback overhead configuration, i.e., the second decoder is fp-config-specific.

[0144] In some embodiments, the plurality of terminals in the first terminal group have different channel state information feedback overhead configurations. In this case, the second decoder can be considered to be generalizable to different channel state information feedback overhead configurations, or the second decoder can be considered to be adapted to the different channel state information feedback overhead configurations. For example, the plurality of terminals includes J terminals, and the channel state information feedback overhead configuration corresponding to terminal j is L j , the channel state information feedback overhead configurations of the J terminals are different, then the second decoder can be considered to be adapted to any channel state information feedback overhead configuration, or the second decoder can be considered to be adapted to L1, L2, ..., L J .

[0145] In a specific embodiment, multiple terminals in the first terminal group have the same physical resource configuration and the same channel state information feedback overhead configuration. Then, the second decoder obtained by training the bitstream obtained based on the above configuration can be considered to be adapted to the specific physical resource configuration and channel state information feedback overhead configuration. In this case, the second decoder can be considered to be pr-fp-config-specific. In this case, the second decoder obtained by training can be considered to be a UE-group-specific model.

[0146] In another specific embodiment, multiple terminals in the first terminal group have different physical resource configurations and the same channel state information feedback overhead configuration. The second decoder trained using the bitstream obtained based on the above configuration can be considered fp-config-specific and generalizable to terminals with different pr-configs. In this case, the trained second decoder can be considered a UE-group-specific model.

[0147] In another specific embodiment, multiple terminals in the first terminal group have the same physical resource configuration and different channel state information feedback overhead configurations. The second decoder trained based on the bitstream obtained based on the above configuration can be considered pr-config-specific and generalizable to terminals with different fp-configs. In this case, the trained second decoder can be considered a UE-group-specific model.

[0148] In another specific embodiment, the multiple terminals in the first terminal group have different physical resource configurations and different channel state information feedback overhead configurations. The second decoder trained using the bitstream obtained based on these configurations can be considered generalizable to terminals with different pr-configs and fp-configs. In this case, the trained second decoder can be considered a cell-specific model.

[0149] Therefore, in an embodiment of the present application, the network device can train the second decoder based on the bitstream fed back by the terminal group (including multiple terminals), which can enable the network device side to collect sufficient data as a training set, thereby obtaining a second decoder with better generalization performance. At the same time, the second decoder can be UE-group-specific or cell-specific. By training with data of one or more different configurations within the terminal group, a second decoder with different generalization performance can be obtained, thereby reducing the switching overhead of the second decoder on the terminal side.

[0150] In some embodiments of the present application, the method 200 further includes:

[0151] The network device sends first indication information to the terminals in the first terminal group, where the first indication information is used to indicate adaptation information of the second decoder. For example, the first indication information is used to indicate a configuration adapted by the second decoder.

[0152] It should be understood that the present application does not limit the specific sending method of the first indication information. For example, the first indication information is sent through at least one of the following signaling: Radio Resource Control (RRC), Media Access Control Control Element (MAC CE), Downlink Control Information (DCI), or, alternatively, it can also be sent through other downlink signaling. The present application is not limited to this.

[0153] In some embodiments, the adaptation information of the second decoder includes at least one of the following:

[0154] The physical resource configuration adapted by the second decoder, the channel state information feedback overhead configuration adapted by the second decoder, and the cell adapted by the second decoder.

[0155] In some embodiments, the network device may explicitly indicate the physical resource configuration, channel state information feedback overhead configuration, and cell to which the second decoder is adapted, or may implicitly indicate the physical resource configuration, channel state information feedback overhead configuration, and cell to which the second decoder is adapted. This application does not limit the specific indication method.

[0156] In some embodiments, when the network device does not indicate the adaptation information of the second decoder, the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration currently adopted by the terminals in the first terminal group by default, or adapted to any physical resource configuration and channel state information feedback overhead configuration (that is, it is generalizable for different physical resource configurations and channel state information feedback overhead configurations), or adapted to the service cell corresponding to the network device, that is, all terminals under the service cell can use the second decoder.

[0157] In some embodiments, when the network device does not indicate the physical resource configuration to which the second decoder is adapted, the second decoder is adapted to the physical resource configuration currently used by the terminals in the first terminal group by default, or adapted to any physical resource configuration, that is, it is generalizable to different physical resource configurations.

[0158] In some embodiments, when the network device does not indicate the channel state information feedback overhead configuration to which the second decoder is adapted, the second decoder is adapted to the channel state information feedback overhead configuration currently adopted by the terminal in the first terminal group by default, or is adapted to any channel state information feedback overhead configuration, that is, it is generalizable to different channel state information feedback overhead configurations.

[0159] In some embodiments, when the network device does not indicate the cell to which the second decoder is adapted, it is assumed that the second decoder is adapted to the cell to which the first terminal group belongs.

[0160] The specific indication method of the first indication information is described below with reference to specific examples.

[0161] Example 1: The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group. In this case, the second decoder can be considered to be pr-fp-config-specific.

[0162] For example, the first indication information may explicitly indicate the physical resource configuration and channel state information feedback overhead configuration adapted by the second decoder. As an example, the first indication information may indicate an index of the physical resource configuration and an index of the channel state information feedback overhead configuration, or may also indicate specific content of the physical resource configuration and specific content of the channel state information feedback overhead configuration.

[0163] For another example, the first indication information may implicitly indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group. As an example, when the first indication information takes a specific value (e.g., 00), it indicates that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group. In this case, there is no need to additionally indicate the physical resource configuration and channel state information feedback overhead configuration.

[0164] Example 2: The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration used by the first terminal group. In this case, the second decoder can be considered to be pr-config-specific.

[0165] For example, the first indication information may explicitly indicate the physical resource configuration adapted by the second decoder. As an example, the first indication information may indicate an index of the physical resource configuration, or may also indicate specific content of the physical resource configuration.

[0166] For another example, the first indication information may implicitly indicate that the second decoder is adapted to the physical resource configuration used by the first terminal group. As an example, when the first indication information takes a specific value (e.g., 01), it indicates that the second decoder is adapted to the physical resource configuration used by the first terminal group. In this case, no additional indication of the physical resource configuration is required. Optionally, the channel state information feedback overhead configuration adapted by the second decoder needs to be additionally indicated.

[0167] Example 3: The first indication information is used to indicate that the second decoder is adapted to the channel state information feedback overhead configuration adopted by the first terminal group. In this case, the second decoder can be considered to be fp-config-specific.

[0168] For example, the first indication information may explicitly indicate the channel state information feedback overhead configuration adapted by the second decoder. As an example, the first indication information may indicate an index of the channel state information feedback overhead configuration, or may also indicate specific content of the channel state information feedback overhead configuration.

[0169] For another example, the first indication information may implicitly indicate that the second decoder is adapted to the channel state information feedback overhead configuration used by the first terminal group. As an example, when the first indication information takes a specific value (e.g., 10), it indicates that the second decoder is adapted to the channel state information feedback overhead configuration used by the first terminal group. In this case, there is no need to additionally indicate the channel state information feedback overhead configuration. Optionally, it is necessary to additionally indicate the physical resource configuration to which the second decoder is adapted.

[0170] Example 4: The first indication information is used to indicate that the second decoder is adapted to the cell to which the first terminal group belongs. In this case, the second decoder can be considered cell-specific.

[0171] For example, the first indication information may explicitly indicate the cell to which the second decoder is adapted, which cell may include a serving cell, or may also include a neighboring cell. As an example, the first indication information may indicate an identity (ID) of the cell to which the second decoder is adapted.

[0172] For another example, the first indication information may implicitly indicate that the second decoder is adapted to the cell to which the first terminal group belongs. As an example, when the first indication information takes a specific value (e.g., 11), it indicates that the second decoder is adapted to the cell to which the first terminal group belongs. In this case, no additional indication of physical resource configuration and channel state information feedback overhead configuration is required.

[0173] In some embodiments of the present application, the method 200 further includes:

[0174] When the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, the first terminal sends first request information to the network device, where the first request information is used to request updating of the model information of the second decoder.

[0175] For example, for Example 1, the second decoder is pr-fp-config-specific. When the physical resource configuration or channel state information feedback overhead configuration of the first terminal changes, the first terminal can request the network device to send a second decoder model adapted to the changed configuration.

[0176] For example, for Example 2, the second decoder is pr-config-specific. When the physical resource configuration of the first terminal changes, the first terminal can request the network device to send a second decoder model adapted to the changed physical resource configuration. When the channel state information feedback overhead configuration of the first terminal changes and the second decoder adapts to the changed channel state information feedback overhead configuration, the first terminal can continue to use the second decoder. Otherwise, the first terminal can request the network device to send a second decoder model adapted to the changed channel state information feedback overhead configuration.

[0177] For example, for Example 3, the second decoder is fp-config-specific. When the channel state information feedback overhead configuration of the first terminal changes, the first terminal can request the network device to send a second decoder model adapted to the changed channel state information feedback overhead configuration. When the physical resource configuration of the first terminal changes and the second decoder adapts to the changed physical resource configuration, the first terminal can continue to use the second decoder. Otherwise, the first terminal can request the network device to send a second decoder model adapted to the changed physical resource configuration.

[0178] For example, for Example 4, the second decoder is cell-specific. When the physical resource configuration or channel state information feedback overhead configuration of the first terminal changes, the first terminal can continue to use the second decoder without requesting the network device to update the model.

[0179] It should be understood that the present application does not limit the reporting method of the first request information. For example, the first request information is sent through uplink control information (UCI), or can also be sent through other uplink signaling. The present application is not limited to this.

[0180] In summary, in an embodiment of the present application, the network device can train the second decoder based on the bit stream fed back by one or more terminals and the output of the first decoder. Since the label for training the second decoder is the output of the first decoder, the role of the second decoder is to simulate the function of the first decoder and establish the relationship between the feedback bit stream of the terminal and the output of the first decoder. Furthermore, the network device sends the second decoder to the one or more terminals, so that the one or more terminals can monitor the model functions of the first encoder and the first decoder locally through the first encoder and the second decoder deployed by themselves, thereby ensuring the accuracy of the model performance monitoring.

[0181] In addition, since the first decoder is implemented as a private model on the network device side, the implementation may be more complicated; and the second decoder is trained under the guidance of the output of the first decoder, so the model implementation can be relatively simple. By issuing the second decoder instead of directly issuing the first decoder publicly, the privatization of the first decoder can be protected while reducing the overhead of model downloading and realizing model performance monitoring on the terminal side.

[0182] Furthermore, the network device trains the second decoder based on bitstreams fed back by multiple terminals, enabling the network device to collect sufficient data as a training set, thereby obtaining a second decoder with improved generalization performance. Furthermore, the second decoder can be UE-group-specific or cell-specific. By training with data from one or more configurations of multiple terminals, second decoders with varying degrees of generalization performance can be obtained, thereby reducing the switching overhead of the second decoder in the terminal.

[0183] The above describes in detail a method for wireless communication according to an embodiment of the present application in conjunction with Figures 9 to 11 , and the following describes in detail a method for wireless communication according to another embodiment of the present application in conjunction with Figures 12 to 14 .

[0184] FIG12 is a schematic flow chart of a wireless communication method 300 according to another embodiment of the present application. The method 300 may be executed by a network device in the communication system shown in FIG1 . As shown in FIG12 , the method 300 includes the following contents:

[0185] S301: A first terminal obtains a first bit stream group and a first output information group, where the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to a network device, each terminal in the first terminal group is deployed with a first encoder, and the bit stream is obtained by encoding input channel state information by each terminal using the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group using a first decoder;

[0186] S302: The first terminal performs training based on the first bit stream group and the first output information group to obtain a second decoder.

[0187] In the method 300, the terminal can train the second decoder, so that the network side does not need to perform model training and model transmission over the air interface, which is beneficial to reducing the overhead on the network side.

[0188] In some embodiments, the first bitstream group may be an input for training a second decoder, and the first output information group is a label for training the second decoder.

[0189] In some embodiments, the first terminal group includes only the first terminal (denoted as Case 1).

[0190] In this case, the first bitstream group may include a first bitstream, and the first output information group may include first output information. The first bitstream is a bitstream fed back by the first terminal to the network device, and the first output information may be obtained by the network device by decoding the first bitstream based on a first decoder. The first bitstream may be generated by the first terminal based on a first encoder, and the first output information may be obtained by the first terminal from the network device.

[0191] In some embodiments, the first terminal group includes only multiple terminals (denoted as Case 2), the first bitstream group may include the bitstream fed back by each of the multiple terminals, and the first output information group may include output information obtained by the network device decoding the bitstreams fed back by the multiple terminals based on the first decoder. The first bitstream group may be obtained by the first terminal from the network device, or the bitstream fed back by the first terminal may be generated by the first terminal based on the first encoder deployed thereon, and other bitstreams other than the bitstream fed back by the first terminal may also be obtained from other terminals in the first terminal group. The first output information group may be obtained by the first terminal from the network device.

[0192] Optionally, the multiple terminals may include some or all terminals in a service cell corresponding to the network device.

[0193] In some embodiments, the bit stream fed back by the terminal in the first terminal group to the network device may be obtained by the terminal encoding the channel state information based on the first encoder deployed on the terminal. The channel state information may be full channel information, or it may be channel information obtained by processing the full channel information, such as feature vector information obtained based on the full channel information. This application does not limit this.

[0194] In some embodiments, the first terminal performs training based on the first bitstream group and the first output information group to obtain the second decoder, which may include:

[0195] The first terminal takes the first bit stream group as input and the first output information group as a label to train the second decoder.

[0196] It should be understood that the bit streams in the first bit stream group and the output information in the first output information group have a corresponding relationship. When training the second decoder, the first terminal uses the corresponding bit streams and output information as input and labels for model training respectively.

[0197] Therefore, in method 300, model training and model transmission over the air interface are not required on the network device side. By simply sending the output information of the first decoder to the terminal side through the network device side, the terminal side can complete the training of the second decoder and monitor the model performance of the combination of the first encoder and the first decoder through the combination of the first encoder and the second decoder. Based on method 300, the terminal side can implement a local terminal-specific UE-specific second decoder, and different terminals can adopt different neural network architectures to match the terminal's local encoder to achieve better monitoring performance.

[0198] The specific processes of the second decoder training method in the above two cases are described below with reference to FIG13 and FIG14 .

[0199] In the example of Figure 13, the first terminal group only includes the first terminal. As shown in Figure 13, the following steps may be included:

[0200] S311: The first terminal sends a first bit stream to a network device.

[0201] The first terminal is deployed with a first encoder, and the first terminal can encode the channel state information based on the first encoder to obtain a first bit stream, and further feed back the first bit stream to the network device.

[0202] For example, the first terminal measures S downlink CSI samples within a period of time, denoted as W, and outputs S bit streams of fixed length L (ie, the first bit stream may include S bit streams), denoted as B, through the first encoder.

[0203] S312: The network device may decode the first bit stream based on the first decoder to obtain first output information.

[0204] That is, the first output information is the channel state information recovered by the network device through the first decoder, or in other words, the decoding information of the bit stream fed back by the first terminal.

[0205] For example, the network device inputs S bit streams into the first decoder and outputs S output information (ie, the first output information may include S output information), which is recorded as

[0206] S313: The network device sends the first output information to the first terminal.

[0207] S314: The first terminal trains a second decoder based on the first bit stream and the first output information.

[0208] For example, the second decoder is trained using the first bit stream as input and the first output information as a label.

[0209] Following the above example, the first terminal can take B as input and As labels, the second decoder is trained.

[0210] Furthermore, the first terminal can detect the model performance of the first encoder and the first decoder based on the combination of the first encoder and the second decoder. For example, the first terminal can obtain X downlink CSI samples by measurement, input the X downlink CSI samples into the first encoder to generate a second bit stream, input the second bit stream into the second decoder to obtain X output information, and then calculate the intermediate key performance indicators (such as SGCS) of the X output information and the X downlink CSI samples, and determine the model performance of the first encoder and the first decoder based on the intermediate key performance indicators. For example, if the SGCS of the X output information and the X downlink CSI samples is greater than the first threshold, it is considered that the model performance of the first encoder and the first decoder meets the requirements, otherwise it does not meet the requirements. The first threshold can be predefined, configured by the network device, or it can be determined by the first terminal itself.

[0211] In some embodiments, when the second decoder is trained only based on the bit stream fed back by the first terminal, the second decoder can be considered to be exclusive to the first terminal (UE-specific), or the second decoder can be considered to be adapted to the physical resource configuration (physical resource configuration, referred to as: pr-config) and channel state information feedback overhead configuration (CSI feedback payload configuration, referred to as: fp-config) of the first terminal.

[0212] In some embodiments, the physical resource configuration of the first terminal may include, but is not limited to:

[0213] The number of subbands and antenna ports configured on the terminal.

[0214] In some embodiments, the channel state information feedback overhead configuration of the first terminal may refer to, for example, the length of a bit stream for the terminal to perform CSI feedback.

[0215] In the example of FIG14 , the first terminal group includes multiple terminals, such as terminal 1, terminal 2, ..., terminal J, where J is a positive integer greater than 1. As shown in FIG14 , the following steps may be included:

[0216] S321: The terminal in the first terminal group sends a bit stream to the network device.

[0217] For example, the first terminal group may include J terminals, which are respectively recorded as terminal 1, terminal 2, ..., terminal J, and the first bit stream group may include bit streams fed back by the J terminals.

[0218] A first encoder is deployed on each of the J terminals, and the bit stream fed back by each terminal may be obtained by encoding the measured channel state information based on the first encoder deployed thereon.

[0219] For example, terminal j (1≤j≤J) measures S over a period of time. j downlink CSI samples, denoted as W j , after the first encoder deployed on terminal j, the generated S j Fixed length L j The bit stream is denoted as B j .

[0220] It should be understood that the length of the bit stream fed back by each of the J terminals (i.e., L) can be the same or different, and the number of bit streams fed back (i.e., S) can be the same or different, and this application does not limit this.

[0221] S322: The network device may decode the bit stream fed back by the terminals in the first terminal group using the first decoder to obtain a first output information group, that is, the first output information group includes decoding information corresponding to the bit stream fed back by each terminal in the first terminal group.

[0222] For example, the network device sends the S feedback from terminal j to j The bit stream is input into the first decoder and output S j Output information, recorded as

[0223] S323: The network device sends a first bit stream group and a first output information group to the terminals in the first terminal group.

[0224] Continuing with the above example, the network device may combine the J feedback bit streams and output information The combination of the J feedback bit streams and the output information The training data set is sent to the terminals in the first terminal group.

[0225] S324: The terminals in the first terminal group combine the first output information group based on the first bit stream and train the second decoder.

[0226] For example, based on the merged J The dataset is used to train the second decoder.

[0227] In some embodiments, when the second decoder is trained based on the bit stream feedback from a terminal group (i.e., multiple terminals), the second decoder can be considered to be exclusive to the terminal group (UE-group-specific), that is, the second decoder can be adapted to the terminal group, or, when the terminal group includes all terminals in a cell, the second decoder can be considered to be cell-specific (cell-specific), that is, the second decoder is adapted to all terminals in the cell.

[0228] In some embodiments, when the second decoder is trained based on the bit stream feedback from a terminal group (i.e., multiple terminals), the adaptability of the second decoder can be determined by the configuration of the multiple terminals, which configuration may include but is not limited to physical resource configuration and channel state information feedback overhead configuration.

[0229] In some embodiments, multiple terminals in the first terminal group have the same physical resource configuration (pr-config). In this case, it can be considered that the second decoder is adapted to the same physical resource configuration, that is, the second decoder is for a specific physical resource configuration, that is, the second decoder is pr-config-specific.

[0230] In some embodiments, the plurality of terminals in the first terminal group have different physical resource configurations. In this case, the second decoder can be considered to be generalizable to different physical resource configurations, or the second decoder can be considered to be adapted to the different physical resource configurations. For example, the plurality of terminals includes J terminals, and the number of antenna ports corresponding to terminal j is P. j , the number of antenna ports of the J terminals is different, then the second decoder can be considered to be adapted to any antenna port number configuration, or the second decoder can be considered to be adapted to P1, P2, ..., P J .

[0231] In some embodiments, the plurality of terminals in the first terminal group have the same channel state information feedback overhead configuration (fp-config). In this case, the second decoder may be considered adapted to the same channel state information feedback overhead configuration. In other words, the second decoder is adapted to a specific channel state information feedback overhead configuration, i.e., the second decoder is fp-config-specific.

[0232] In some embodiments, the plurality of terminals in the first terminal group have different channel state information feedback overhead configurations. In this case, the second decoder may be considered generalizable to different channel state information feedback overhead configurations, or the second decoder may be considered adapted to the different channel state information feedback overhead configurations. For example, the plurality of terminals includes J terminals, and the channel state information feedback overhead configuration corresponding to terminal j is L j , the channel state information feedback overhead configurations of the J terminals are different, then the second decoder can be considered to be adapted to any channel state information feedback overhead configuration, or the second decoder can be considered to be adapted to L1, L2, ..., L J .

[0233] In a specific embodiment, multiple terminals in the first terminal group have the same physical resource configuration and the same channel state information feedback overhead configuration. Then, the second decoder obtained by training the bitstream obtained based on the above configuration can be considered to be adapted to the specific physical resource configuration and channel state information feedback overhead configuration. In this case, the second decoder can be considered to be pr-fp-config-specific. In this case, the second decoder obtained by training can be considered to be a UE-group-specific model.

[0234] In another specific embodiment, multiple terminals in the first terminal group have different physical resource configurations and the same channel state information feedback overhead configuration. The second decoder trained using the bitstream obtained based on the above configuration can be considered fp-config-specific and generalizable to terminals with different pr-configs. In this case, the trained second decoder can be considered a UE-group-specific model.

[0235] In another specific embodiment, multiple terminals in the first terminal group have the same physical resource configuration and different channel state information feedback overhead configurations. The second decoder trained based on the bitstream obtained based on the above configuration can be considered pr-config-specific and generalizable to terminals with different fp-configs. In this case, the trained second decoder can be considered a UE-group-specific model.

[0236] In another specific embodiment, the multiple terminals in the first terminal group have different physical resource configurations and different channel state information feedback overhead configurations. The second decoder trained using the bitstream obtained based on the above configurations can be considered to be generalizable to terminals with different pr-configs and fp-configs. In this case, the trained second decoder can be considered a cell-specific model.

[0237] Therefore, in an embodiment of the present application, the second decoder can be trained based on the bitstream fed back by the terminal group (including multiple terminals), which enables the terminal side to collect sufficient data as a training set, thereby obtaining a second decoder with better generalization performance. At the same time, the second decoder can be UE-group-specific or cell-specific. By training with data from one or more different configurations within the terminal group, a second decoder with different generalization performance can be obtained, thereby reducing the switching overhead of the second decoder on the terminal side.

[0238] In some embodiments of the present application, the method 300 further includes:

[0239] When the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, the first terminal sends a second request message to the network device, where the second request message is used to request a data set for training a second decoder adapted to the configuration of the first terminal.

[0240] It should be understood that the present application does not limit the reporting method of the second request information. For example, the second request information is sent through UCI, or can also be sent through other uplink signaling. The present application is not limited to this.

[0241] In some embodiments, the configuration of the first terminal and the configuration adapted by the second decoder are inconsistent, including:

[0242] The physical resource configuration of the first terminal is inconsistent with the physical resource configuration adapted by the second decoder, and / or

[0243] The channel state information feedback overhead configuration of the first terminal and the channel state information feedback overhead configuration adapted by the second decoder.

[0244] In some embodiments, when the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration used by the first terminal group, that is, when the second decoder is pr-fp-config-specific, if the physical resource configuration or channel state information feedback overhead configuration of the first terminal changes, the first terminal can request the network device to send a new training data set for training the second decoder adapted to the changed physical resource configuration or channel state information feedback overhead configuration. In this case, the first terminal can optionally report a bitstream based on the changed physical resource configuration to the network device, so that the network device generates corresponding output information based on the bitstream.

[0245] In other embodiments, when the second decoder is adapted to the physical resource configuration used by the first terminal group, that is, the second decoder is pr-config-specific, if the physical resource configuration of the first terminal changes, the first terminal may request the network device to send a new training data set for training the second decoder adapted to the changed physical resource configuration. In this case, the first terminal may report a bit stream based on the changed physical resource configuration to the network device, so that the network device generates corresponding output information based on the bit stream. When the channel state information feedback overhead configuration of the first terminal changes and the second decoder adapts to the changed channel state information feedback overhead configuration, the first terminal may continue to use the second decoder. Otherwise, the first terminal may request the network device to send a new training data set for training the second decoder adapted to the changed channel state information feedback overhead configuration. In this case, the first terminal may report a bit stream based on the changed channel state information feedback overhead configuration to the network device, so that the network device generates corresponding output information based on the bit stream.

[0246] In some further embodiments, when the second decoder is adapted to the channel state information feedback overhead configuration adopted by the first terminal group, that is, when the second decoder is fp-config-specific, when the channel state information feedback overhead configuration of the first terminal changes, the first terminal can request the network device to send a new training data set for training the second decoder model adapted to the changed channel state information feedback overhead configuration. In this case, the first terminal can report a bit stream based on the changed channel state information feedback overhead configuration to the network device, so that the network device generates corresponding output information based on the bit stream. When the physical resource configuration of the first terminal changes and the second decoder adapts to the changed physical resource configuration, the first terminal can continue to use the second decoder. Otherwise, the first terminal can request the network device to send a new training data set for training the second decoder model adapted to the changed physical resource configuration. In this case, the first terminal can report a bit stream based on the changed physical resource configuration to the network device, so that the network device generates corresponding output information based on the bit stream.

[0247] In some further embodiments, when the second decoder is adapted to the cell to which the first terminal group belongs, that is, the second decoder is cell-specific, when the physical resource configuration or channel state information feedback overhead configuration of the first terminal changes, the first terminal can continue to use the second decoder without requesting a new training data set from the network device.

[0248] In summary, in an embodiment of the present application, the terminal can train the second decoder based on the bit stream fed back by one or more terminals and the output of the first decoder. Since the label for training the second decoder is the output of the first decoder, the role of the second decoder is to simulate the function of the first decoder and establish the relationship between the feedback bit stream of the terminal and the output of the first decoder. In this way, the one or more terminals can monitor the model functions of the first encoder and the first decoder locally through the first encoder and the second decoder deployed by themselves, thereby ensuring the accuracy of model performance monitoring.

[0249] Furthermore, when the terminal trains the second decoder, there is no need for the network side to perform model training and model transmission over the air interface. The terminal side can complete the training of the second decoder by simply sending the output of the first decoder to the terminal side through the network side, and monitor the model performance of the combination of the first encoder and the first decoder through the combination of the first encoder and the second decoder. Furthermore, based on the embodiments of the present application, a local terminal-specific UE-specific second decoder can be implemented on the terminal side, and different terminals can adopt different neural network architectures to match the terminal's local encoder to achieve better monitoring performance.

[0250] Furthermore, the terminal side trains the second decoder based on the bitstream fed back by the terminal group (including multiple terminals), which enables the terminal side to collect sufficient data as a training set, thereby obtaining a second decoder with better generalization performance. At the same time, the second decoder can be UE-group-specific or cell-specific. By training with data from one or more configurations of the joint terminal group, a second decoder with different degrees of generalization performance can be obtained, thereby reducing the switching overhead of the terminal's second decoder.

[0251] The above, in combination with Figures 9 to 14, describes in detail the method embodiment of the present application. The following, in combination with Figures 15 to 21, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0252] FIG15 shows a schematic block diagram of a network device 1000 according to an embodiment of the present application. As shown in FIG15 , the network device 1000 includes:

[0253] A communication unit 1010 is configured to obtain a first bit stream group, where the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to the network device, wherein each terminal in the first terminal group is deployed with a first encoder, and the bit stream is obtained by encoding channel state information by each terminal based on the first encoder;

[0254] a processing unit 1020 configured to decode the first bitstream group based on a first decoder to obtain a first output information group, wherein the first output information group includes output information obtained by the network device decoding each bitstream in the first bitstream group, and to perform training based on the first bitstream group and the first output information group to obtain a second decoder;

[0255] The communication unit 1010 is further configured to send the model information of the second decoder to each terminal in the first terminal group.

[0256] In some embodiments, the first terminal group includes one terminal, the first bitstream group includes a first bitstream, and the first bitstream is obtained by the network device from the one terminal.

[0257] In some embodiments, the second decoder adapts to a physical resource configuration and a channel state information feedback overhead configuration of the one terminal.

[0258] In some embodiments, the first terminal group includes a plurality of terminals.

[0259] In some embodiments, the plurality of terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or

[0260] The multiple terminals have different physical resource configurations, and the second decoder is adapted to the different physical resource configurations.

[0261] In some embodiments, the plurality of terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or

[0262] The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

[0263] In some embodiments, the communication unit 1010 is further configured to: send first indication information to terminals in the first terminal group, where the first indication information is used to indicate adaptation information of the second decoder.

[0264] In some embodiments, the adaptation information of the second decoder includes at least one of the following:

[0265] The physical resource configuration adapted by the second decoder, the channel state information feedback overhead configuration adapted by the second decoder, and the cell adapted by the second decoder.

[0266] In some embodiments, the first indication information is used to indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group; or

[0267] The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration adopted by the first terminal group; or

[0268] The first indication information is used to instruct the second decoder to adapt to the channel state information feedback overhead configuration adopted by the first terminal group; or

[0269] The first indication information is used to indicate that the second decoder is adapted to the cell to which the first terminal group belongs.

[0270] In some embodiments, the first indication information is sent via at least one of the following signaling: radio resource control RRC, media access control element MAC CE, and downlink control information DCI.

[0271] In some embodiments, the communication unit 1010 is also used to: receive a first request message sent by the first terminal in the first terminal group, the first request message being used to request an update of the model information of the second decoder, wherein the first request message is sent when the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder.

[0272] In some embodiments, the configuration of the first terminal and the configuration adapted by the second decoder are inconsistent, including:

[0273] The physical resource configuration of the first terminal is inconsistent with the physical resource configuration adapted by the second decoder, and / or

[0274] The channel state information feedback overhead configuration of the first terminal and the channel state information feedback overhead configuration adapted by the second decoder.

[0275] In some embodiments, the first request information is sent via uplink control information UCI.

[0276] In some embodiments, the network device performs training based on the first bitstream group and the first output information group to obtain a second decoder, including:

[0277] The network device uses the first bit stream group as input and the first output information group as a label for training to obtain the second decoder.

[0278] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0279] It should be understood that the network device 1000 according to the embodiment of the present application may correspond to the network device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the network device 1000 are respectively for implementing the corresponding processes of the network device in the method 200 shown in Figures 9 to 11. For the sake of brevity, they will not be repeated here.

[0280] FIG16 shows a schematic block diagram of a terminal device 1100 according to an embodiment of the present application. As shown in FIG16 , the terminal device 1100 includes:

[0281] a communication unit 1110 configured to send a first bit stream to a network device, wherein the terminal device is deployed with a first encoder, the first bit stream is obtained by the terminal device encoding channel state information based on the first encoder, and the network device is deployed with a first decoder; and

[0282] Receive model information of a second decoder sent by the network device, where the second decoder is trained by the network device based on a first bit stream group and a first output information group, where the first bit stream group includes the bit stream fed back by each terminal in the first terminal group to the network device, and the first output information group includes output information obtained by the network device by decoding each bit stream in the first bit stream group based on the first decoder, and the first terminal group includes the terminal device.

[0283] In some embodiments, the first terminal group includes only the terminal devices.

[0284] In some embodiments, the second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the terminal device.

[0285] In some embodiments, the first terminal group includes a plurality of terminals.

[0286] In some embodiments, the plurality of terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or

[0287] The multiple terminals have different physical resource configurations, and the second decoder is adapted to the different physical resource configurations.

[0288] In some embodiments, the plurality of terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or

[0289] The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

[0290] In some embodiments, the communication unit 1110 is further configured to:

[0291] First indication information sent by the network device is received, where the first indication information is used to indicate adaptation information of the second decoder.

[0292] In some embodiments, the first indication information is used to indicate at least one of a physical resource configuration, a channel state information feedback overhead configuration, and a cell adapted by the second decoder.

[0293] In some embodiments, the first indication information is used to indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group; or

[0294] The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration adopted by the first terminal group; or

[0295] The first indication information is used to instruct the second decoder to adapt to the channel state information feedback overhead configuration adopted by the first terminal group; or

[0296] The first indication information is used to indicate that the second decoder is adapted to the cell to which the first terminal group belongs.

[0297] In some embodiments, the first indication information is sent via at least one of the following signaling: radio resource control RRC, media access control element MAC CE, and downlink control information DCI.

[0298] In some embodiments, the communication unit 1110 is further configured to:

[0299] When the configuration of the terminal device is inconsistent with the configuration adapted by the second decoder, first request information is sent to the network device, where the first request information is used to request updating the model information of the second decoder.

[0300] In some embodiments, the configuration of the terminal device is inconsistent with the configuration adapted by the second decoder, including:

[0301] The physical resource configuration of the terminal device is inconsistent with the physical resource configuration adapted by the second decoder, and / or

[0302] The channel state information feedback overhead configuration of the terminal device and the channel state information feedback overhead configuration adapted by the second decoder.

[0303] In some embodiments, the first request information is sent via uplink control information UCI.

[0304] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0305] It should be understood that the terminal device 1100 according to an embodiment of the present application may correspond to the first terminal in an embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the terminal device 1100 are respectively for realizing the corresponding processes of the first terminal in the method 200 shown in Figures 9 to 11. For the sake of brevity, they will not be repeated here.

[0306] FIG17 shows a schematic block diagram of a terminal device 1200 according to an embodiment of the present application. As shown in FIG17 , the terminal device 1200 includes:

[0307] Communication unit 1210 is configured to obtain a first bitstream group and a first output information group, wherein the first bitstream group includes a bitstream fed back by each terminal in a first terminal group to a network device, each terminal in the first terminal group being deployed with a first encoder, the bitstream being obtained by encoding input channel state information by each terminal using the first encoder, and the first output information group includes output information obtained by the network device decoding each bitstream in the first bitstream group using a first decoder;

[0308] The processing unit 1210 is configured to perform training based on the first bit stream group and the first output information group to obtain a second decoder.

[0309] In some embodiments, the first terminal group includes only the terminal devices.

[0310] In some embodiments, the first bitstream group includes a first bitstream, and the first bitstream is determined by the terminal device;

[0311] The first output information group includes first output information, and the first output information is obtained from the network device.

[0312] In some embodiments, the second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the terminal device.

[0313] In some embodiments, the first terminal group includes a plurality of terminals.

[0314] In some embodiments, the first bitstream group and the first output information group are obtained from the network device.

[0315] In some embodiments, the plurality of terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or

[0316] The multiple terminals have different physical resource configurations, and the second decoder is adapted to the different physical resource configurations.

[0317] In some embodiments, the plurality of terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or

[0318] The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

[0319] In some embodiments, the communication unit 1210 is also used to: when the configuration of the terminal device and the configuration adapted by the second decoder are inconsistent, send a second request information to the network device, and the second request information is used to request to obtain a data set for training the second decoder adapted to the configuration of the terminal device.

[0320] In some embodiments, the configuration of the terminal device is inconsistent with the configuration adapted by the second decoder, including:

[0321] The physical resource configuration of the terminal device is inconsistent with the physical resource configuration adapted by the second decoder, and / or

[0322] The channel state information feedback overhead configuration of the terminal device and the channel state information feedback overhead configuration adapted by the second decoder.

[0323] In some embodiments, the second request information is sent via uplink control information UCI.

[0324] In some embodiments, the processing unit 1220 is further configured to:

[0325] The first bit stream group is used as input and the first output information group is used as a label for training to obtain the second decoder.

[0326] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0327] It should be understood that the terminal device 1200 according to an embodiment of the present application may correspond to the first terminal in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the terminal device 1200 are respectively for realizing the corresponding processes of the first terminal in the method 300 shown in Figures 12 to 14. For the sake of brevity, they will not be repeated here.

[0328] FIG18 shows a schematic block diagram of a network device 1300 according to an embodiment of the present application. As shown in FIG18 , the network device 1300 includes:

[0329] Communication unit 1310 is used to send a first bit stream group and / or a first output information group to a first terminal, where the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to the network device, and a first encoder is deployed on each terminal in the first terminal group. The bit stream is obtained by each terminal encoding the input channel state information based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder.

[0330] In some embodiments, the first bitstream group and / or the first output information group are used by the first terminal to train a second decoder.

[0331] In some embodiments, the first terminal group includes only the first terminal.

[0332] In some embodiments, the second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the first terminal.

[0333] In some embodiments, the first terminal group includes a plurality of terminals.

[0334] In some embodiments, the plurality of terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or

[0335] The multiple terminals have different physical resource configurations, and the second decoder is adapted to the different physical resource configurations.

[0336] In some embodiments, the plurality of terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or

[0337] The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

[0338] In some embodiments, the communication unit 1310 is further configured to: receive second request information sent by the first terminal, where the second request information is used to request acquisition of a data set for training a second decoder adapted to the configuration of the first terminal.

[0339] In some embodiments, the second request information is sent via uplink control information UCI.

[0340] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0341] It should be understood that the network device 1300 according to the embodiment of the present application may correspond to the network device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the network device 1300 are respectively for realizing the corresponding processes of the network device in the method 300 shown in Figures 12 to 14. For the sake of brevity, they will not be repeated here.

[0342] Figure 19 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 shown in Figure 19 includes a processor 610, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0343] Optionally, as shown in FIG19 , the communication device 600 may further include a memory 620. The processor 610 may call and execute a computer program from the memory 620 to implement the method in the embodiment of the present application.

[0344] The memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .

[0345] Optionally, as shown in FIG19 , the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0346] The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of antennas may be one or more.

[0347] Optionally, the communication device 600 may specifically be a network device in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0348] Optionally, the communication device 600 may specifically be a mobile terminal / terminal device / first terminal in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the mobile terminal / terminal device / first terminal in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0349] Figure 20 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 700 shown in Figure 20 includes a processor 710, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0350] Optionally, as shown in FIG20 , the chip 700 may further include a memory 720 , wherein the processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application.

[0351] The memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .

[0352] Optionally, the chip 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0353] Optionally, the chip 700 may further include an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0354] Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0355] Optionally, the chip can be applied to the mobile terminal / terminal device / first terminal in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device / first terminal in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0356] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0357] FIG21 is a schematic block diagram of a communication system 900 provided in an embodiment of the present application. As shown in FIG21 , the communication system 900 includes a terminal device 910 and a network device 920 .

[0358] Among them, the terminal device 910 can be used to implement the corresponding functions implemented by the mobile terminal / terminal device / first terminal in the above method, and the network device 920 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, they will not be repeated here.

[0359] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0360] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0361] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0362] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0363] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0364] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device / first terminal in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device / first terminal in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0365] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0366] Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0367] Optionally, the computer program product can be applied to the mobile terminal / terminal device / first terminal in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal / terminal device / first terminal in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0368] The embodiment of the present application also provides a computer program.

[0369] Optionally, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.

[0370] Optionally, the computer program can be applied to the mobile terminal / terminal device / first terminal in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the mobile terminal / terminal device / first terminal in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0371] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0372] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0373] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0374] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0375] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0376] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0377] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The network device obtains a first bit stream group, where the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to the network device, wherein a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by encoding channel state information by each terminal based on the first encoder; The network device decodes the first bit stream group based on a first decoder to obtain a first output information group, wherein the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group; The network device performs training based on the first bit stream group and the first output information group to obtain a second decoder; The network device sends the model information of the second decoder to each terminal in the first terminal group.

2. The method according to claim 1, characterized in that: The first terminal group includes one terminal, the first bit stream group includes a first bit stream, and the first bit stream is obtained by the network device from the one terminal.

3. The method according to claim 2, characterized in that The second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the one terminal.

4. The method according to claim 1, characterized in that: The first terminal group includes a plurality of terminals.

5. The method according to claim 4, characterized in that The multiple terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or The multiple terminals have different physical resource configurations, and the second decoder is adapted to different physical resource configurations.

6. The method according to claim 4 or 5, characterized in that: The multiple terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The network device sends first indication information to the terminals in the first terminal group, where the first indication information is used to indicate adaptation information of the second decoder.

8. The method according to claim 7, characterized in that The adaptation information of the second decoder includes at least one of the following: The physical resource configuration adapted by the second decoder, the channel state information feedback overhead configuration adapted by the second decoder, and the cell adapted by the second decoder.

9. The method according to claim 8, characterized in that The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to a channel state information feedback overhead configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to the cell to which the first terminal group belongs.

10. The method according to any one of claims 7 to 9, characterized in that: The first indication information is sent via at least one of the following signaling: radio resource control RRC, media access control element MAC CE, and downlink control information DCI.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: The network device receives first request information sent by the first terminal in the first terminal group, where the first request information is used to request updating of model information of the second decoder, wherein the first request information is sent when the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder.

12. The method according to claim 11, characterized in that The configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, including: The physical resource configuration of the first terminal is inconsistent with the physical resource configuration adapted by the second decoder, and / or, The channel state information feedback overhead configuration of the first terminal and the channel state information feedback overhead configuration adapted by the second decoder.

13. The method according to claim 11 or 12, characterized in that: The first request information is sent via uplink control information UCI.

14. The method according to any one of claims 1 to 13, characterized in that The network device performs training based on the first bit stream group and the first output information group to obtain a second decoder, including: The network device uses the first bit stream group as input and the first output information group as a label for training to obtain the second decoder.

15. A wireless communication method, characterized in that: include: A first terminal sends a first bit stream to a network device, wherein a first encoder is deployed on the first terminal, the first bit stream is obtained by the first terminal encoding channel state information based on the first encoder, and a first decoder is deployed on the network device; The first terminal receives model information of a second decoder sent by the network device, the second decoder is trained by the network device based on a first bit stream group and a first output information group, the first bit stream group includes a bit stream fed back to the network device by each terminal in the first terminal group, the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on the first decoder, and the first terminal group includes the first terminal.

16. The method according to claim 15, characterized in that The first terminal group includes only the first terminal.

17. The method according to claim 16, characterized in that The second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the first terminal.

18. The method according to claim 15, characterized in that The first terminal group includes a plurality of terminals.

19. The method according to claim 18, characterized in that The multiple terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or The multiple terminals have different physical resource configurations, and the second decoder is adapted to different physical resource configurations.

20. The method according to claim 18 or 19, characterized in that The multiple terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

21. The method according to any one of claims 15 to 20, characterized in that The method further comprises: The first terminal receives first indication information sent by the network device, where the first indication information is used to indicate adaptation information of the second decoder.

22. The method according to claim 21, characterized in that The first indication information is used to indicate at least one of a physical resource configuration, a channel state information feedback overhead configuration, and a cell adapted by the second decoder.

23. The method according to claim 22, characterized in that The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration and channel state information feedback overhead configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to the physical resource configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to a channel state information feedback overhead configuration adopted by the first terminal group; or The first indication information is used to indicate that the second decoder is adapted to the cell to which the first terminal group belongs.

24. The method according to any one of claims 21 to 23, characterized in that The first indication information is sent via at least one of the following signaling: radio resource control RRC, media access control element MAC CE, and downlink control information DCI.

25. The method according to any one of claims 15 to 24, characterized in that The method further comprises: In the case that the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, the first terminal sends first request information to the network device, where the first request information is used to request to update the model information of the second decoder.

26. The method according to claim 25, characterized in that The configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, including: The physical resource configuration of the first terminal is inconsistent with the physical resource configuration adapted by the second decoder, and / or, The channel state information feedback overhead configuration of the first terminal and the channel state information feedback overhead configuration adapted by the second decoder.

27. The method according to claim 25 or 26, characterized in that The first request information is sent via uplink control information UCI.

28. A wireless communication method, characterized in that: include: The first terminal obtains a first bit stream group and a first output information group, wherein the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to the network device, a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by encoding input channel state information by each terminal based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder; The first terminal performs training based on the first bit stream group and the first output information group to obtain a second decoder.

29. The method according to claim 28, characterized in that The first terminal group includes only the first terminal.

30. The method according to claim 29, characterized in that The first bit stream group includes a first bit stream, and the first bit stream is determined by the first terminal; The first output information group includes first output information, and the first output information is obtained from the network device.

31. The method according to claim 29 or 30, characterized in that The second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the first terminal.

32. The method according to claim 28, characterized in that The first terminal group includes a plurality of terminals.

33. The method according to claim 32, characterized in that The first bit stream group and the first output information group are obtained from the network device.

34. The method according to claim 32 or 33, characterized in that The multiple terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or The multiple terminals have different physical resource configurations, and the second decoder is adapted to different physical resource configurations.

35. The method according to any one of claims 32 to 34, characterized in that The multiple terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

36. The method according to any one of claims 28 to 35, characterized in that The method further comprises: When the configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, the first terminal sends a second request message to the network device, where the second request message is used to request a data set for training a second decoder adapted to the configuration of the first terminal.

37. The method according to claim 36, characterized in that The configuration of the first terminal is inconsistent with the configuration adapted by the second decoder, including: The physical resource configuration of the first terminal is inconsistent with the physical resource configuration adapted by the second decoder, and / or, The channel state information feedback overhead configuration of the first terminal and the channel state information feedback overhead configuration adapted by the second decoder.

38. The method according to claim 36 or 37, characterized in that The second request information is sent via uplink control information UCI.

39. The method according to any one of claims 28 to 38, characterized in that The first terminal performs training based on the first bit stream group and the first output information group to obtain a second decoder, including: The first terminal uses the first bit stream group as input and the first output information group as a label for training to obtain the second decoder.

40. A method of wireless communication, characterized in that: include: A network device sends a first bit stream group and / or a first output information group to a first terminal, wherein the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to the network device, a first encoder is deployed on each terminal in the first terminal group, and the bit stream is obtained by encoding input channel state information by each terminal based on the first encoder, and the first output information group includes output information obtained by decoding each bit stream in the first bit stream group by the network device based on a first decoder, and the first bit stream group and / or the first output information group are used by the first terminal to train a second decoder.

41. The method according to claim 40, characterized in that The first terminal group includes only the first terminal.

42. The method according to claim 41, characterized in that The first bit stream group and / or the first output information group are used by the first terminal to train a second decoder, and the second decoder adapts to the physical resource configuration and channel state information feedback overhead configuration of the first terminal.

43. The method according to claim 40, characterized in that The first terminal group includes a plurality of terminals.

44. The method according to claim 43, characterized in that The multiple terminals have the same physical resource configuration, and the second decoder is adapted to the same physical resource configuration; or The multiple terminals have different physical resource configurations, and the second decoder is adapted to different physical resource configurations.

45. The method according to claim 43 or 44, characterized in that The multiple terminals have the same channel state information feedback overhead configuration, and the second decoder is adapted to the same channel state information feedback overhead configuration; or The multiple terminals have different channel state information feedback overhead configurations, and the second decoder adapts to different channel state information feedback overhead configurations.

46. ​​The method according to any one of claims 40 to 45, characterized in that The method further comprises: The network device receives second request information sent by the first terminal, where the second request information is used to request acquisition of a data set for training a second decoder adapted to the configuration of the first terminal.

47. The method according to claim 46, characterized in that The second request information is sent via uplink control information UCI.

48. A network device, characterized in that: include: A communication unit is configured to obtain a first bit stream group, wherein the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to the network device, wherein a first encoder is deployed on each terminal in the first terminal group, and the bit stream is The terminal encodes the channel state information based on the first encoder; a processing unit, configured to decode the first bit stream group based on a first decoder to obtain a first output information group, wherein the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group, and to perform training based on the first bit stream group and the first output information group to obtain a second decoder; The communication unit is further configured to send the model information of the second decoder to each terminal in the first terminal group.

49. A terminal device, characterized in that: include: A communication unit, configured to send a first bit stream to a network device, wherein a first encoder is deployed on the terminal device, the first bit stream is obtained by the terminal device encoding channel state information based on the first encoder, and a first decoder is deployed on the network device; as well as Receive model information of a second decoder sent by the network device, where the second decoder is trained by the network device based on a first bit stream group and a first output information group, where the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to the network device, where the first output information group includes output information obtained by the network device by decoding each bit stream in the first bit stream group based on the first decoder, and where the first terminal group includes the terminal devices.

50. A terminal device, characterized in that: include: a communication unit, configured to obtain a first bit stream group and a first output information group, wherein the first bit stream group includes a bit stream fed back by each terminal in a first terminal group to a network device, a first encoder is deployed on each terminal in the first terminal group, the bit stream is obtained by encoding input channel state information by each terminal based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder; A processing unit is used to perform training based on the first bit stream group and the first output information group to obtain a second decoder.

51. A network device, characterized in that: include: A communication unit, used to send a first bit stream group and / or a first output information group to a first terminal, the first bit stream group includes a bit stream fed back by each terminal in the first terminal group to the network device, a first encoder is deployed on each terminal in the first terminal group, the bit stream is obtained by encoding input channel state information by each terminal based on the first encoder, and the first output information group includes output information obtained by the network device decoding each bit stream in the first bit stream group based on a first decoder.

52. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 15 to 27, or the method according to any one of claims 28 to 39.

53. A network device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 14, or the method according to any one of claims 40 to 47.

54. A chip, characterized in that: include: A processor, configured to call and run a computer program from a memory so that a device equipped with the chip performs a method as described in any one of claims 1 to 14, or a method as described in any one of claims 15 to 27, or a method as described in any one of claims 28 to 39, or a method as described in any one of claims 40 to 47.

55. A computer-readable storage medium, characterized in that: Used to store a computer program, the computer program causing a computer to execute the method according to any one of claims 1 to 14, or the method according to any one of claims 15 to 27, or the method according to any one of claims 28 to 39, or the method according to any one of claims 40 to 47.

56. A computer program product, characterized in that Comprising computer program instructions which cause a computer to perform the method of any one of claims 1 to 14, or the method of any one of claims 15 to 27, or the method of any one of claims 28 to 39, or the method of any one of claims 40 to 47.

57. A computer program, characterized in that The computer program causes a computer to execute the method of any one of claims 1 to 14, or the method of any one of claims 15 to 27, or the method of any one of claims 28 to 39, or the method of any one of claims 40 to 47.

Citation Information

Patent Citations

  • Channel state information (CSI) learning

    CN115136518A

  • Channel state information feedback system and method

    CN115189740A

  • Compression model updating method, device and system and storage medium

    CN116033456A

  • Neural network based channel state information feedback

    WO2021173331A1