Communication method and apparatus

Abstract

Disclosed in the present application are a communication method and apparatus. The method comprises: transmitting first data, wherein the first data comprises M pieces of channel information feedback and N first identifiers, the N first identifiers are used for indicating N first data sets stored at a receiving end, the N first identifiers correspond to the N first data sets on a one-to-one basis, N and M are positive integers, each of the N first data sets comprises one or more pieces of ground-truth channel information, the M pieces of channel information feedback correspond to M pieces of ground-truth channel information, the N first data sets comprise the M pieces of ground-truth channel information, and each of the N first data sets comprises at least one of the M pieces of ground-truth channel information. The method can reduce data set transmission overheads.

Description

Communication method and device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on March 30, 2024, with application number 202410385900.6 and application name “Communication Method and Device”. This application claims priority to the Chinese patent application filed with the China Patent Office on April 3, 2024, with application number 202410417512.1 and application name “Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of communication technologies, and in particular to communication methods and devices. Background Art

[0003] In existing communication systems, user equipment (UE) measures the channel state information reference signal (CSI-RS) or synchronization signal block (SSB) to obtain downlink CSI. Then, the UE generates a CSI report as predefined by the protocol or configured by the base station, and feeds the CSI back to the base station so that it can obtain downlink CSI.

[0004] CSI feedback can be implemented through a dual-end model. For example, a terminal-side device (such as a UE) compresses and quantizes CSI through an encoder (such as a CSI generator), and a network-side device (such as a base station) recovers CSI through a decoder (such as a CSI reconstructor). The dual-end model can be implemented through joint training or separate training (independent training). Joint training refers to the joint training of the sub-models on the same node or on different nodes; independent training refers to the independent training of the two sub-models (such as the encoder and decoder mentioned above) using the same dataset or a related dataset.

[0005] To enable independent training of dual-end models, network-side devices and terminal-side devices exchange datasets consisting of ground-truth CSI and CSI feedback. Because model training typically requires a large amount of data, exchanging such datasets between network-side and terminal-side devices results in significant data transmission overhead. Summary of the Invention

[0006] The present application discloses a communication method and apparatus, which can reduce the data set transmission overhead between a network-side device and a terminal-side device.

[0007] The present application is introduced below from different aspects. It should be understood that the implementation methods and beneficial effects of the following different aspects can be referenced to each other.

[0008] In the first aspect, the present application discloses a communication method, which can be executed by a network side device or a module in the network side device (for example, a chip), or a terminal side device or a module in the terminal side device (for example, a chip). The method may include: transmitting first data, the first data including M channel information feedbacks and N first identifiers, the N first identifiers being used to indicate N first data sets stored at the receiving end, the N first identifiers corresponding one-to-one to the N first data sets, N and M being positive integers, each of the N first data sets including one or more true value channel information, the M channel information feedbacks corresponding to the M true value channel information, the N first data sets including M true value channel information, and each of the N first data sets including at least one of the M true value channel information.

[0009] In this embodiment of the present application, only channel information feedback and a first identifier are transmitted between the transmitting end and the receiving end. The first identifier is used to indicate the first data set stored by the receiving end. Therefore, the transmitting end does not need to send the first data set, and the receiving end can obtain the first data set corresponding to the first identifier from storage based on the first identifier. It is understandable that the amount of data in the first identifier is smaller than the amount of data in the first data set, so the above method can reduce the transmission overhead of the data set.

[0010] In an embodiment of the present application, if the network side device is the sending end, the terminal side device is the receiving end, then the above-mentioned transmission of the first data means: the network side device sends the first data to the terminal side device, and accordingly, the terminal side device receives the first data from the network side device; if the terminal side device is the sending end, the network side device is the receiving end, then the above-mentioned transmission of the first data means: the terminal side device sends the first data to the network side device, and accordingly, the network side device receives the first data from the terminal side device.

[0011] Exemplarily, the true-value channel information is true-value CSI, the channel information feedback is CSI feedback, and the first data set is a true-value CSI data set.

[0012] Among them, the network side device can be a network device or an entity communicating with the network device; the terminal side device can be a user device or an entity communicating with the user device.

[0013] In conjunction with the first aspect, in one possible implementation, N is 1, and the M pieces of true-valued channel information are part or all of the true-valued channel information in the first data set. This method does not limit the correspondence between the M pieces of true-valued channel information and the first data set. The M pieces of true-valued channel information may correspond to one or more first data sets, thereby increasing flexibility in selecting the first data set.

[0014] In combination with the first aspect, in a possible embodiment, the first data also includes at least one of the following: the format of the channel information feedback, the identifier of one or more second data sets to which the M channel information feedbacks belong, the number of M channel information feedbacks, or first indication information, wherein the first indication information is used to indicate the correspondence between the M channel information feedbacks and the true value channel information in the N first data sets.

[0015] Exemplarily, the second data set is a CSI feedback data set.

[0016] In combination with the first aspect, in a possible implementation, the method further includes: training a first model based on M channel information feedbacks and M true value channel information, the first model being an encoder or decoder in an artificial intelligence model, the encoder being deployed on a terminal side device, and the decoder being deployed on a network side device.

[0017] In an embodiment of the present application, the artificial intelligence model is a two-end model. The terminal-side device and the network-side device can train the model deployed on their own end by transmitting M channel information feedback and M true channel information. That is, the M channel information feedback and M true channel information serve as training data for the two-end model. This method can reduce the transmission overhead of the training data of the two-end model.

[0018] With reference to the first aspect, in a possible implementation, the M pieces of true value channel information are predefined or pre-acquired.

[0019] In combination with the first aspect, in a possible embodiment, the method also includes: transmitting one of the first information, the second information, or the third information, and any one of the first information, the second information, or the third information is used for inference or determination of the encoder and / or decoder for monitoring; wherein the first information includes N first identifiers and second information, the second information is the identifier of one or more second data sets to which the M channel information feedback belongs, and the third information is the identifier of the third data set, and the third data set is a data set including N first data sets and second data sets.

[0020] In an embodiment of the present application, the sending end and the receiving end can achieve dual-end model pairing through the identifier of the data set (such as one of the first information, second information or third information mentioned above).

[0021] In a second aspect, the present application discloses a communication method, which can be executed by a network side device or a module (for example, a chip) in the network side device, or a terminal side device or a module (for example, a chip) in the terminal side device. The method may include: transmitting a first data set and multiple second data sets corresponding to the first data set, the first data set including one or more true value channel information, the multiple second data sets including M channel information feedbacks, M is a positive integer; the one or more true value channel information include true value channel information corresponding to M channel information feedbacks; the one or more true value channel information include first true value channel information, the first true value channel information corresponds to first channel information feedback and second channel information feedback, the first channel information feedback and the second channel information feedback respectively belong to two data sets in the multiple second data sets.

[0022] In an embodiment of the present application, at least one piece of the plurality of true-value channel information corresponds to two channel information feedbacks, and the two channel information feedbacks respectively belong to two data sets among the plurality of second data sets. This method allows the true-value channel information to correspond to multiple channel information feedbacks, thereby avoiding the repeated transmission of the true-value channel information when the true-value channel information corresponds to the channel information feedback one-to-one. This can reduce the amount of transmitted true-value channel information data, thereby reducing the transmission overhead of the data set.

[0023] Exemplarily, each of the multiple second data sets includes at least two channel information feedbacks, and the total number of channel information feedbacks of the multiple second data sets is the above-mentioned M, that is, all channel information feedbacks of the multiple second data sets are the above-mentioned M channel information feedbacks; each true-value channel information in the above-mentioned first data set corresponds to at least one of the above-mentioned M channel information feedbacks, and the number of true-value channel information included in the first data set is less than the above-mentioned M.

[0024] Exemplarily, the true-value channel information is true-value CSI, the channel information feedback is CSI feedback, the first data set is a true-value CSI data set, and the second data set is a CSI feedback data set.

[0025] In combination with the second aspect, in a possible implementation, the method further includes: transmitting first indication information, where the first indication information is used to indicate a correspondence between the M channel information feedbacks and true value channel information in the first data set.

[0026] In combination with the second aspect, in a possible implementation, the method further includes: training a first model based on M channel information feedbacks and true channel information corresponding to the M channel information feedbacks, the first model being an encoder or decoder in an artificial intelligence model, the encoder being deployed on a terminal side device, and the decoder being deployed on a network side device.

[0027] In an embodiment of the present application, the artificial intelligence model is a two-end model. The terminal-side device and the network-side device can train the model deployed on their own end by transmitting M channel information feedbacks and the true channel information corresponding to the M channel information feedbacks. That is, the M channel information feedbacks and the true channel information corresponding to the M channel information feedbacks serve as training data for the two-end model. This method can reduce the transmission overhead of the training data for the two-end model.

[0028] In conjunction with the second aspect, in a possible implementation manner, the true value channel information corresponding to the M channel information feedbacks is predefined or pre-acquired.

[0029] In combination with the second aspect, in a possible embodiment, the method also includes: transmitting one of the first information, the second information, or the third information, any one of the first information, the second information, or the third information is used for inference or determination of the encoder and / or decoder for monitoring; wherein the first information includes an identification of the first data set and the second information, the second information is an identification of multiple second data sets, the third information is an identification of the third data set, and the third data set is a data set including the first data set and multiple second data sets.

[0030] In an embodiment of the present application, the sending end and the receiving end can achieve dual-end model pairing through the identifier of the data set (such as one of the first information, second information or third information mentioned above).

[0031] In a third aspect, the present application discloses a communication method, which can be executed by a network-side device or a module (for example, a chip) in a network-side device, or a terminal-side device or a module (for example, a chip) in a terminal-side device. The method may include: transmitting one of the first information, the second information, or the third information, and any one of the first information, the second information, or the third information is used for inference or determination of an encoder or / and decoder for monitoring; wherein the first information includes an identifier of a first data set and the second information, the second information is an identifier of a second data set, the third information is an identifier of a third data set, and the third data set is a data set including the first data set and the second data set; the first data set includes multiple true value channel information, and the second data set includes multiple channel information feedbacks.

[0032] In an embodiment of the present application, the sending end and the receiving end can achieve dual-end model pairing through the identifier of the data set (such as one of the first information, second information or third information mentioned above).

[0033] In an embodiment of the present application, if the network side device is the sending end, the terminal side device is the receiving end, then the above-mentioned transmission of one of the first information, the second information or the third information means: the network side device sends one of the first information, the second information or the third information to the terminal side device, and accordingly, the terminal side device receives one of the first information, the second information or the third information from the network side device; if the terminal side device is the sending end, the network side device is the receiving end, then the above-mentioned transmission of one of the first information, the second information or the third information means: the terminal side device sends one of the first information, the second information or the third information to the network side device, and accordingly, the network side device receives one of the first information, the second information or the third information from the terminal side device.

[0034] Exemplarily, the true-value channel information is true-value CSI, the channel information feedback is CSI feedback, the first data set is a true-value CSI data set, and the second data set is a CSI feedback data set.

[0035] In combination with the third aspect, in one possible implementation, the dual-end model includes the above-mentioned encoder and / or decoder, the encoder is deployed on the terminal side device, and the decoder is deployed on the network side device.

[0036] In conjunction with the third aspect, in a possible implementation, the encoder and / or decoder determined by any one of the first information, second information, or third information is obtained by training the data set corresponding to the information. For example, the second data set is CSI feedback data set 1, and the artificial intelligence model obtained by training the CSI feedback data set 1 and the true value CSI data set 2 corresponding to the CSI feedback data set is model 1. The model 1 includes encoder 1 and decoder 1. Then, the identifier of the CSI feedback data set 1 can be used to determine at least one of model 1, encoder 1, or decoder 1. The identifier of the CSI feedback data set 1 and the identifier of the true value CSI data set 2 can be used to determine at least one of model 1, encoder 1, or decoder 1. For another example, the third data set is data set 1, which includes a CSI feedback data set and a true value CSI data set. The artificial intelligence model obtained by training the data set 1 is model 2. The model 2 includes encoder 2 and decoder 2. Then, the identifier of data set 1 can be used to determine at least one of model 2, encoder 2, or decoder 2.

[0037] In a fourth aspect, the present application provides a communication device, which may be a terminal-side device or a chip / circuit therein, or a network-side device or a chip / circuit therein. The communication device is configured to perform the method of the first aspect or any possible implementation of the first aspect. The communication device includes a unit configured to perform the method of the first aspect or any possible implementation of the first aspect.

[0038] In a fifth aspect, the present application provides a communication device, which may be a terminal-side device or a chip / circuit therein, or a network-side device or a chip / circuit therein. The communication device is configured to perform the method of the second aspect or any possible implementation of the second aspect. The communication device includes a unit configured to perform the method of the second aspect or any possible implementation of the second aspect.

[0039] In a sixth aspect, the present application provides a communication device, which may be a terminal-side device or a chip / circuit therein, or a network-side device or a chip / circuit therein. The communication device is configured to perform the method of the third aspect or any possible implementation of the third aspect. The communication device includes a unit configured to perform the method of the third aspect or any possible implementation of the third aspect.

[0040] In the fourth, fifth, or sixth aspects, the communication device may include a transceiver unit and a processing unit. For a detailed description of the transceiver unit and the processing unit, reference may be made to the device embodiments described below. The beneficial effects of the fourth to sixth aspects may be referenced to the relevant descriptions of the first to third aspects, and are not further elaborated here.

[0041] In a seventh aspect, the present application provides a communication device, which may include a processor and an interface circuit, and the processor is connected to the interface circuit. Wherein, the interface circuit is used to interact (or receive and send or input and output) information or data, and the processor is used to run program instructions so that the communication device executes the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of the aspects above. Wherein, the interface circuit may be a communication interface, or a transceiver. The transceiver may be a radio frequency module in a communication device, or a combination of a radio frequency module and an antenna, or an input and output interface of a chip or circuit.

[0042] In an eighth aspect, the present application provides a readable storage medium having program instructions stored thereon, which, when executed on a computer, enables the computer to execute the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any one of the aspects above.

[0043] In a ninth aspect, the present application provides a program product comprising program instructions, which, when executed, enables the method described in the first aspect, the second aspect, the third aspect, or any possible implementation of any of the aspects to be executed.

[0044] In the tenth aspect, the present application provides a device, which can be implemented in the form of a chip or in the form of a device, and the device includes a processor. The processor is used to read and execute a program stored in a memory to execute the information interaction method provided by one or more of the above-mentioned first aspect, or the above-mentioned second aspect, or the third aspect, or any possible implementation of any aspect thereof. Optionally, the device also includes a memory, which is connected to the processor through a circuit. Further optionally, the device also includes a communication interface, and the processor is connected to the communication interface. The communication interface is used to receive information to be processed, and the processor obtains the information from the communication interface, processes the information, and outputs the processing results through the communication interface. The communication interface can be an input and output interface.

[0045] In a possible implementation, the processor and memory may be physically independent units, or the memory may be integrated with the processor.

[0046] In an eleventh aspect, the present application provides a communication system, which includes a communication device; the communication device is used to execute the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any one of the aspects above.

[0047] The technical effects achieved in the above-mentioned aspects can be referred to each other or to the beneficial effects in the method embodiments shown below, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] FIG1 is a schematic diagram of a neuron structure provided in an embodiment of the present application;

[0049] FIG2 is a schematic diagram of the layer relationship of a neural network provided in an embodiment of the present application;

[0050] FIG3 is a schematic diagram of a double-terminal model provided in an embodiment of the present application;

[0051] FIG4A is a schematic diagram of a communication system applicable to the communication method according to an embodiment of the present application;

[0052] FIG4B is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application;

[0053] FIG4C is a schematic diagram of a possible application framework in a communication system;

[0054] FIG4D is a schematic diagram of a possible application framework in a communication system;

[0055] FIG5 is a schematic diagram of the chip system architecture used in this application;

[0056] FIG6 is a flow chart of a communication method provided in an embodiment of the present application;

[0057] FIG7 is a flow chart of another communication method provided in an embodiment of the present application;

[0058] FIG8 is a flow chart of another communication method provided in an embodiment of the present application;

[0059] FIG9 is a flow chart of another communication method provided in an embodiment of the present application;

[0060] FIG10 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0061] FIG11 is another schematic structural diagram of a communication device provided in an embodiment of the present application;

[0062] FIG12 is another structural diagram of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0064] In the description of this application, words such as "first" and "second" are used only to distinguish different objects and do not limit the quantity or execution order. Moreover, words such as "first" and "second" do not necessarily mean different. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to the process, method, product, or device.

[0065] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one (item)", "the following one (item) or more (items)" or similar expressions refer to any combination of these items, including any combination of single or plural items (items). For example, at least one item (item) of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a, b, and c. Among them, a, b, and c can be single or multiple.

[0066] In the description of this application, words such as "exemplary" or "for example" are used to indicate an example, illustration, or description. Any embodiment or design described in this application as "exemplary," "for example," or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete way.

[0067] It should be understood that in the description of this application, the terms "when," "if," and "if" all refer to the device performing a corresponding action under certain objective circumstances. They do not limit the time, do not require the device to perform a judgment action during implementation, and do not imply any other limitations. Specifically, "the device performing a corresponding action under certain objective circumstances" includes: the device performing the corresponding action under certain objective circumstances can perform the corresponding action only if the objective circumstances are met; or the device performing the corresponding action can perform the corresponding action only if the objective circumstances and other circumstances are met.

[0068] The term "simultaneously" in this application may be understood as at the same time point, within a period of time, or within the same cycle, and may be understood in conjunction with the context.

[0069] Elements used in the singular herein are intended to mean "one or more" rather than "one and only one" unless specifically stated otherwise.

[0070] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0071] It should be understood that in the various embodiments of the present application, "A corresponds to B," "A corresponds to B," "A corresponds to B," or similar expressions indicate that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information.

[0072] The following is an introduction to the technical terms and related technologies designed in this application.

[0073] 1. Artificial Intelligence, Machine Learning, AI Models, and Neural Networks

[0074] (1) Artificial intelligence (AI): The technology that presents human intelligence through ordinary computer programs. Understandably, AI can make machines have human intelligence, using computer hardware and software to simulate certain human intelligent behaviors, including machine learning and many other methods.

[0075] Artificial intelligence can be defined as machines or computers that mimic humans and possess cognitive functions associated with the human mind, such as learning and problem-solving. AI is able to learn from past experiences, make rational decisions, and respond quickly. The goal of AI is to understand intelligence by building computer programs capable of symbolic reasoning or deduction.

[0076] (2) Machine learning: learning models or rules from raw data. There are many different machine learning methods, such as neural networks (NN), decision trees, support vector machines, etc.

[0077] Machine learning is a path to artificial intelligence (AI), specifically using machine learning to solve AI problems. Machine learning theory primarily involves the design and analysis of algorithms that enable computers to automatically "learn." Machine learning algorithms automatically analyze data to identify patterns and use these patterns to make predictions about unknown data. Because learning algorithms involve extensive statistical theory, machine learning is particularly closely linked to inferential statistics, also known as statistical learning theory.

[0078] (3) AI model: This refers to a function model that maps input of a certain dimension to output of a certain dimension, and its model parameters are obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be regarded as an AI model. a and b correspond to the parameters of the model and can be obtained through machine learning training.

[0079] An AI model is an algorithm or computer program that implements AI functions. It represents the mapping relationship between the model's input and output. An AI model can be a neural network or other machine learning model.

[0080] (4) Neural network: Here it refers to artificial neural network, which is a mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing. It is a special form of AI model.

[0081] Neural networks are a specific implementation of machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, enabling them to learn arbitrary mappings. Therefore, neural networks can accurately abstractly model complex, high-dimensional problems.

[0082] The idea of ​​a neural network is derived from the neuron structure of the brain. Each neuron performs a weighted sum operation on its input values ​​and passes the weighted sum result through an activation function to produce an output.

[0083] Figure 1 is a schematic diagram of an exemplary neuron structure of the present invention. Assume that the input of the neuron is x = [x0, x1, ..., xn ], and the weights corresponding to each input are w=[w,w1,…,w n ], the bias of the weighted sum is b. The activation function can be diversified. Assuming that the activation function of a neuron is: y = f(z) = max(0,z), the output of the neuron is: For example, if the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: b can take any possible value, such as a decimal, an integer (0, a positive integer or a negative integer), or a complex number. The activation functions of different neurons in a neural network can be the same or different.

[0084] A neural network generally comprises a multi-layer structure, with each layer comprising one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. Figure 2 is a schematic diagram of the layer relationship of a neural network. In one implementation, the neural network comprises an input layer and an output layer. The input layer of the neural network processes the input received by the neurons and passes the result to the output layer, which then obtains the output of the neural network. In another implementation, the neural network comprises an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the input received by the neurons and passes the result to an intermediate hidden layer. The hidden layer then passes the calculation result to the output layer or an adjacent hidden layer, and finally the output layer obtains the output of the neural network. A neural network can comprise one or more sequentially connected hidden layers, without limitation. During the training process of a neural network, a loss function can be defined. The loss function describes the gap or difference between the output value of the neural network and the ideal target value. This application does not limit the specific form of the loss function. The training process of a neural network is to adjust the neural network parameters, such as the number of neural network layers, width, neuron weights, and / or parameters in the neuron activation function, so that the value of the loss function is less than the threshold value or meets the target requirements.

[0085] (5) Terms related to AI models

[0086] Dataset: Data used for model training, validation, and testing in machine learning. The quantity and quality of data will affect the effectiveness of machine learning.

[0087] In the embodiment of the present application, the data set may refer to a true CSI data set, a CSI feedback data set, or a data set including true CSI and CSI feedback.

[0088] Model training: By selecting a suitable loss function and using an optimization algorithm to train the model parameters, the loss function value is minimized.

[0089] Hyperparameters: parameters such as the number of neural network layers, the number of neurons, activation function, loss function, etc.

[0090] Loss function: used to measure the difference between the model's predicted value and the true value.

[0091] Model application: Use the trained model to solve practical problems.

[0092] 2. Channel Information Feedback

[0093] In existing long-term evolution (LTE) and new radio (NR) communication systems, base stations obtain downlink channel state information (CSI) to determine one or more of the following configurations: resources, modulation and coding scheme (MCS), and precoding for scheduling downlink or uplink data channels of user equipment (UE). In time division duplex (TDD) systems, due to the reciprocity of uplink and downlink channels, base stations can obtain uplink CSI by measuring uplink reference signals, and then infer more accurate downlink CSI, for example, using uplink CSI as downlink CSI. In frequency division duplex (FDD) systems, uplink and downlink reciprocity cannot be guaranteed. Downlink CSI is obtained by the UE measuring downlink reference signals, such as CSI-RS or synchronization signal blocks (synchronizing signal / physical broadcast channel block, SSB). Therefore, the UE needs to generate a CSI report according to the protocol pre-defined or base station configured method and feed the CSI back to the base station so that it can obtain downlink CSI. The CSI in this application is not limited to traditional CSI, such as one or more of channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), and channel state information reference signal resource indicator (CSI-RS CRI), and can also be channel response information, such as channel response matrix, or reference signal receiving power (RSRP), or signal to interference plus noise ratio (SINR). In this application, CSI feedback may also be referred to as channel information feedback, CSI report, or channel information report, CSI compression, or channel information compression.

[0094] 3. Two-End Model

[0095] A two-end model generally refers to a network structure consisting of two or more sub-models. It can also be called a bilateral model or a collaborative model. The sub-models of a bilateral model are typically deployed on different network nodes. To ensure compatibility, the two-end models must be trained jointly or using the same dataset.

[0096] 4. CSI Feedback Based on the Dual-End Model

[0097] CSI feedback can be achieved through a two-end model.

[0098] For example, as shown in Figure 3, the terminal side device deploys an encoder (CSI generator), and the network side (such as the base station) deploys a decoder (CSI reconstructor). The terminal side device compresses and quantizes the channel information (such as CSI) through the CSI generator, and the base station recovers the CSI through the decoder (CSI reconstructor). In Figure 3, H represents the input of the CSI generator, which can be called input CSI or true CSI or original CSI or target CSI; Figure 3 uses z to represent the feedback from the UE to the base station, which can be called CSI feedback or CSI report or compressed CSI or latent space CSI; Figure 3 uses represents the output of the CSI reconstructor, which can be called output CSI, recovered CSI, or reconstructed CSI.

[0099] In this application, the dual-end model includes an encoder (CSI generator) deployed on the UE and a decoder (CSI reconstructor) deployed on the network device.

[0100] 5. Dataset Transfer

[0101] The dual-end model can be implemented through joint training or separate training (independent training). Joint training refers to the joint training of two sub-models at the same node or at different nodes. Independent training refers to the independent training of two sub-models using the same dataset or associated datasets. For example, for the dual-end model in Figure 3, the input of the CSI generator is H and the label is z, and the input of the CSI reconstructor is z and the label is H. Therefore, the dataset consisting of (H, z) can be used to train both the CSI generator and the CSI reconstructor. If the CSI generator and the CSI reconstructor are trained using the same dataset, the CSI generator and the CSI reconstructor can be used in combination, that is, the CSI reconstructor can restore the z output by the CSI generator to a value sufficiently similar to H.

[0102] In this application, independent training can be initiated by a network-side device or a terminal-side device.

[0103] For example, the network-side device trains the CSI generator and CSI reconstructor of the network-side device based on the true CSI, generates CSI feedback based on the trained CSI generator, and sends a data set consisting of the CSI feedback and the corresponding true CSI to the terminal-side device. The terminal-side device trains the CSI generator of the terminal-side device based on the received CSI feedback and the corresponding true CSI.

[0104] For another example, the terminal-side device trains the CSI generator and CSI reconstructor of the terminal-side device based on the true CSI, generates CSI feedback based on the trained CSI generator, and sends a data set consisting of the CSI feedback and the corresponding true CSI to the network-side device. The network-side device trains the CSI reconstructor of the network-side device based on the received CSI feedback and the corresponding true CSI.

[0105] To enable independent training of dual-end models, network-side devices and terminal-side devices can exchange datasets consisting of ground-truth CSI and CSI feedback. However, model training typically requires a large amount of data, so exchanging datasets consisting of ground-truth CSI and CSI feedback between network-side devices and terminal-side devices results in significant dataset transmission overhead.

[0106] In this embodiment of the present application, the aforementioned data set (H, z) can be split into a true CSI data set and a CSI feedback data set. Furthermore, the network-side device and the terminal-side device only exchange the CSI feedback data set, and indicate the true CSI data set corresponding to the CSI feedback data set through indication information. This true CSI data set is standardized (i.e., predefined) or has already been sent by the network device to the UE. Therefore, the network-side device and the terminal-side device do not exchange the true CSI data set. This method can reduce data set transmission overhead.

[0107] In some embodiments of the present application, the network-side device and the terminal-side device may further transmit an identifier of a true CSI dataset and an identifier of a CSI feedback dataset, or an identifier of a CSI feedback dataset, or an identifier of a third dataset, where the third dataset is a data set including the true CSI dataset and the CSI feedback dataset. This method can achieve dual-end model pairing.

[0108] Based on the above, in order to better understand the communication method and related devices proposed in this application, the system architecture of the embodiment of this application is described below.

[0109] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, such as sixth generation (6G) mobile communication systems, or a fusion system of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0110] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the network element as an example for description. For example, the communication system may include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It is understandable that the terminal device in the present disclosure can be replaced by the first network element, and the network device can be replaced by the second network element, and the two perform the corresponding communication methods in the present disclosure.

[0111] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, and therefore the demands that need to be met are becoming increasingly diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as network functionality becomes increasingly powerful, such as supporting increasingly high spectrum, supporting new technologies such as high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting beam management, network energy saving has become a hot research topic. These new demands, new scenarios, and new features have brought unprecedented challenges to network planning, maintenance, and efficient operation. To meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence. In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0112] Figure 4A is a schematic diagram of a communication system applicable to the communication method of an embodiment of the present application. As shown in Figure 4A, the communication system 100 may include at least one network device, such as the network device 110 shown in Figure 4A; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in Figure 4A. The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via multi-antenna technology.

[0113] In an embodiment of the present application, the network device 110 and the at least one terminal device (i.e., the terminal device 120 and / or the terminal device 130) can transmit data through the communication method provided by the present application. For example, the decoder of the dual-end model can be deployed on the network device 110, which can be referred to as a network-side device; the encoder of the dual-end model can be deployed on the at least one terminal device, which can be referred to as a terminal-side device; the network-side device and the terminal-side device can transmit the training data (such as the first data) of the dual-end model through the communication method provided by the present application. The details of the first data can be found below and will not be expanded here.

[0114] Figure 4B is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application. Compared to the communication system 100 shown in Figure 4A, the communication system 200 shown in Figure 4B also includes an AI network element 140. AI network element 140 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0115] In the embodiment of the present application, AI network element 140 transmits data to a terminal device via network device 110. For example, the decoder of the dual-end model can be deployed on the aforementioned AI network element 140, which can be referred to as a network-side device; the encoder of the dual-end model can be deployed on at least one of the aforementioned terminal devices, which can be referred to as a terminal-side device; and the network-side device and the terminal-side device can transmit training data (such as the first data) of the dual-end model via the communication method provided in this application.

[0116] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0117] It should be understood that FIG4B illustrates only the example of a direct connection between AI network element 140 and network device 110. In other scenarios, AI network element 140 may also be connected to a terminal device. Alternatively, AI network element 140 may be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 may be connected to network device 110 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0118] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG4A .

[0119] It should be noted that Figures 4A and 4B are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 4A and 4B. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0120] In an embodiment of the present application, 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.

[0121] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0122] 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.

[0123] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0124] The network device in the embodiments of the present application may include a device for communicating with a terminal device, and the network device may include an access network device, a radio access network device, or a core network device. For example, the network device may be a base station, or an operation, management, and maintenance OAM device or a CN device. The access network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects the terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip that is set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0125] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0126] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0127] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0128] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0129] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0130] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0131] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open access network (open RAN, ORAN / O-RAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit in the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0132] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0133] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0134] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0135] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0136] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0137] An AI node can be an AI network element or an AI module.

[0138] Figure 4C is a schematic diagram of a possible application framework in a communication system. As shown in Figure 4C, network elements in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more of these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals or operations, administration and maintenance (OAM) equipment (for clarity, only one is shown in Figure 4C). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0139] In an embodiment of the present application, the decoder of the dual-end model can be deployed in any AI module in the above-mentioned core network device, access network node (RAN node) or OAM, and the device deploying the above-mentioned decoder can be called a network-side device; the encoder of the dual-end model is deployed in the AI ​​module of the above-mentioned terminal, and the device deploying the above-mentioned encoder can be called a terminal-side device; the network-side device and the terminal-side device can transmit data through the communication method provided in this application, such as the training data (such as the first data) of the interactive dual-end model. It can be understood that the network-side device belongs to the network device side, and the terminal-side device belongs to the user device side.

[0140] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0141] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0142] The network device may be a network device provided with one or more AI modules. The network device may include one or more devices in the core network device, access network node (RAN node) or OAM device shown in Figure 4C. For example, the AI ​​module may be the RIC shown in Figure 4D, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in the RAN node (for example, in the CU, DU), and the non-real-time RIC is set in the OAM, in the cloud server, in the core network device, or in other network devices. RIC can obtain subsets from multiple terminal devices from the RAN node (for example, CU, CU-CP, CU-UP, DU and / or RU), reorganize them into training data set #2, and train based on training data set #2. Exemplarily, near real-time RIC and non-real-time RIC can also be set separately as a network element, and the network device can be a near real-time RIC or a non-real-time RIC.

[0143] Figure 4D is a schematic diagram of a possible application framework in a communication system. As shown in Figure 4D, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 4C, which is used to implement AI-related functions. The RIC includes a near-real time RIC (near-real time RIC, near-RT RIC) and a non-real time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of the data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of the data is in the order of tens of milliseconds.

[0144] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near real-time RIC delivers the reasoning result to the DU, and the DU sends it to the RU.

[0145] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0146] The near real-time RIC and non-real-time RIC may also be separately configured as a network element. Optionally, the near real-time RIC and non-real-time RIC may also be part of other devices. For example, the near real-time RIC is configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network device.

[0147] In an embodiment of the present application, the decoder of the two-end model can be deployed in the above-mentioned RIC, and the RIC can be called a network-side device; the encoder of the two-end model is deployed in the above-mentioned terminal, and the terminal can be called a terminal-side device; the network-side device and the terminal-side device can transmit data through the communication method provided in this application, such as the training data of the interactive two-end model (such as the first data).

[0148] For example, the chip system architecture used in this application is shown in FIG5 . This chip system architecture can be used in network devices and / or terminal devices, as described above.

[0149] Input / output control manages the input and output signals of a device. For example, input / output control can be represented by a modem, keyboard, mouse, touchscreen, and so on. Input / output control may also be part of the processor. A receiver / transmitter is used to communicate with other devices. A receiver / transmitter may include a modem, which modulates information or demodulates modulated information. An antenna is used to transmit and receive signals. Storage may include random access memory (RAM) or read-only memory (ROM). Storage may be used to store code that can be executed by the processor to implement corresponding functions. Processors may include intelligent hardware devices such as general-purpose processors, digital signal processors (DSPs), central processing units (CPUs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), and neural processing units (NPUs).

[0150] In the embodiment of the present application, assuming that FIG5 is a chip system of a UE, the UE establishes a communication connection with a network device through a communication control module. The UE processor sends data (such as CSI feedback data set information) to the network device through a transmitter and antenna. The UE receives data (such as CSI feedback data set information) sent by the network device through an antenna and a receiver. The UE stores the received data in a memory, and the UE processes the received data through the processor. The details of the CSI feedback data set information are described below and are not expanded here.

[0151] In combination with the above system architecture, a communication method provided in an embodiment of the present application is described below.

[0152] Please refer to Figure 6, which is a flow chart of a communication method provided by an embodiment of the present application. In Figure 6, the dashed boxes represent optional steps, that is, the method may not include steps S602 and S603, or may include steps S602 and / or S603.

[0153] The functions performed by the network side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the network side device, and the functions performed by the terminal side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the terminal side device.

[0154] Among them, the network side device can be a network device or an entity that communicates with a network device; the terminal side device can be a user device or an entity that communicates with a user device. For example, the network side device can be the network device 110 in FIG. 4A above, and the terminal side device can be the terminal device 120 and / or the terminal device 130 in FIG. 4A above; for another example, the network side device can be the network device 110 in FIG. 4B above, and the terminal side device can be the terminal device 120 and / or the terminal device 130 in FIG. 4B above; for another example, the network side device can be the network device 110 or the AI ​​network element 140 in FIG. 4B above, and the terminal side device can be the terminal device 120 and / or the terminal device 130 in FIG. 4C above. Equipment 120 terminal device 130, or AI network element 140; for another example, the above-mentioned network side device can be any one of the access network node, core network device and OAM in Figure 4C above, or the AI ​​module of any one of the access network node, core network device and OAM in Figure 4C above, or a network element with an AI module, and the above-mentioned terminal side device can be the terminal in Figure 4C above or a network element with an AI module; for another example, the above-mentioned network side device can be any network element except the terminal in Figure 4D above, and the above-mentioned terminal side device can be the terminal in Figure 4D above.

[0155] As shown in FIG6 , the communication method may include the following steps:

[0156] S601: First data is transmitted between a network-side device and a terminal-side device, where the first data includes M channel information feedbacks and N first identifiers, where the N first identifiers are used to indicate N first data sets stored at the receiving end, and the N first identifiers correspond one-to-one to the N first data sets, where N and M are positive integers, and each of the N first data sets includes one or more true-value channel information, the M channel information feedbacks correspond to M true-value channel information, the N first data sets include M true-value channel information, and each of the N first data sets includes at least one of the M true-value channel information.

[0157] In an embodiment of the present application, if the network side device is a sending end, the terminal side device is a receiving end, then, the transmission of the first data between the above-mentioned network side device and the terminal side device means: the network side device sends the first data to the terminal side device, and accordingly, the terminal side device receives the first data from the network side device; if the terminal side device is a sending end, the network side device is a receiving end, then, the transmission of the first data between the above-mentioned network side device and the terminal side device means: the terminal side device sends the first data to the network side device, and accordingly, the network side device receives the first data from the terminal side device.

[0158] It should be understood that since the N first data sets are data sets stored by the receiving end, then, assuming that the receiving end is a terminal-side device, the device storing the N first data sets can be a user device or an entity communicating with the user device; assuming that the receiving end is a network-side device, the device storing the N first data sets can be a network device or an entity communicating with the network device. In an embodiment of the present application, the sending end sends the identifier of the data set stored by the receiving end (i.e., the above-mentioned N first identifiers), so that the sending end does not need to send the N first data sets indicated by the above-mentioned N first identifiers. Since the amount of data of the N first identifiers is less than the amount of data of the N first data sets, the data transmission overhead can be reduced.

[0159] Optionally, the M pieces of true channel information are predefined or pre-acquired. That is to say, the N first data sets may be predefined or pre-acquired. For example, the N first data sets are predefined data sets. After receiving the N first identifiers, the receiving end may obtain the N first data sets indicated by the N first identifiers from the predefined data set, and obtain the M pieces of true channel information from the N first data sets. For another example, the N first data sets are previously sent by the transmitting end or other communication devices corresponding to the transmitting end (such as network devices or user devices) to the receiving end or other communication devices corresponding to the receiving end. Accordingly, the receiving end stores the N first data sets, and thus the M pieces of true channel information may be obtained from the storage. For another example, the N first data sets are previously acquired and stored by other communication devices (such as network devices or user devices). The other communication devices are entities communicating with the receiving end. After receiving the N first identifiers, the receiving end obtains the N first data sets from the storage of the other communication devices.

[0160] Optionally, assuming N is 1, the M pieces of true channel information are part or all of the true channel information in the first data set. That is, the first data includes M channel information feedbacks and a first identifier, the first identifier being used to indicate a first data set stored by the receiving end, and the M pieces of true channel information are part or all of the true channel information in the first data set. Assuming N>1, each of the N first data sets includes at least one of the M pieces of true channel information. For example, all or part of the true channel information in each first data set belongs to the M pieces of true channel information. When only part of the true channel information in the first data set belongs to the M pieces of true channel information, the first data set also includes other pieces of true channel information that do not belong to the M pieces of true channel information. For another example, N=M, only one or more pieces of true channel information in each first data set belong to the M pieces of true channel information. Each first data set also includes other pieces of true channel information that do not belong to the M pieces of true channel information. For another example, the total number of true channel information in the N first data sets is M, that is, all the true channel information in the N first data sets is the M pieces of true channel information.

[0161] Optionally, the first data also includes at least one of the following: the format of the channel information feedback, the identifier of one or more second data sets to which the M channel information feedbacks belong, the number of the M channel information feedbacks, or first indication information, wherein the first indication information is used to indicate the correspondence between the M channel information feedbacks and the true value channel information in the N first data sets.

[0162] Exemplarily, the above-mentioned correspondence can be indicated by rules and / or parameters, wherein the rule can be any one or more of the following rules: corresponding to the first n, or the last n, or the consecutive n starting from the kth, or the i-th among every m, or the i-th among every m starting from the kth, of the true value channel information in each of the multiple first data sets; the parameter refers to the values ​​of n, k, i, and m in the above-mentioned rules. The rules and parameters can be predefined or indicated by the first indication information. For example, the rule can be predefined, and the parameter can be indicated by the first indication information. If the number of first data sets is 1, that is, N=1, then the rule can be: corresponding to the first M, or the last M, or the consecutive M starting from the kth, or the i-th among every m, or the i-th among every m starting from the kth, of the first data set, a total of M i-th channel information feedbacks are obtained. Optionally, if the M channel information feedbacks correspond to multiple first data sets, it is also necessary to indicate the correspondence with each first data set, such as the first indication information is also used to indicate the correspondence between each channel information feedback in the M channel information feedbacks and the N first data sets, that is, which data set of the N first data sets each channel information feedback in the M channel information feedbacks corresponds to and which true value channel information in the first data set.

[0163] Optionally, the channel information may be any one or more of the following: channel response, channel matrix, channel characteristic matrix, precoding matrix, CSI, reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), optimal top K beam identifier (ID), where K is a positive integer of 1 or greater than 1.

[0164] Optionally, the solution in this application can be applied to a scenario where an AI model is used to output CSI feedback, and the CSI feedback can be applied to one or more of channel prediction, MCS determination, beam management, or precoding, without limitation herein. The output CSI feedback may include compressed CSI, predicted CSI, or compressed information of the predicted CSI.

[0165] Exemplarily, the channel information feedback may be CSI feedback, the true channel information may be true CSI, the first data set may be a true CSI data set, and the second data set may be a CSI feedback data set.

[0166] The following introduction is made by taking the sending end as a network device and the receiving end as a UE as an example, that is, the network side device sending the first data to the terminal side device as an example.

[0167] For example, if the network device has sent true-value CSI dataset 1 to the UE, and true-value CSI dataset 1 includes part or all of the M true-value CSI data, then the N first identifiers may include the identifier of true-value CSI dataset 1. For another example, if the network device has sent dataset 2 to the UE, and dataset 2 includes true-value CSI and CSI feedback, and dataset 2 includes part or all of the M true-value CSI data, then the N first identifiers may include the identifier of dataset 2.

[0168] Optionally, the receiving end can obtain the CSI feedback dataset and the ground-truth CSI dataset corresponding to the CSI feedback dataset from different devices. For example, when network device 1 sends a ground-truth CSI dataset to UE1 and network device 2 sends a CSI feedback dataset to UE2, the receiving end can indicate the identifier of the ground-truth CSI dataset sent by network device 1 to UE1. If UE1 and UE2 are from the same manufacturer, UE1 and UE2 can share data through the server.

[0169] S602: The network side device trains the decoder in the artificial intelligence model based on M channel information feedback and M true value channel information.

[0170] Among them, the artificial intelligence model can be a two-end model, which includes an encoder and a decoder. The encoder is deployed on the terminal side device and the decoder is deployed on the network side device.

[0171] Exemplarily, the above-mentioned M channel information feedbacks are M CSI feedbacks, the above-mentioned M true-value channel information are M true-value CSI, and the above-mentioned decoder is a CSI reconstructor; the network-side device can use the above-mentioned M CSI feedbacks as input and the above-mentioned M true-value CSI as labels to train the CSI reconstructor; when the value of the loss function is less than the threshold value or meets the target requirement, a trained CSI reconstructor is obtained. This application does not limit the specific form of the loss function. Exemplarily, the two-end model can be as shown in Figure 3, where the M CSI feedbacks are z and the M true-value CSIs are H.

[0172] Assume that the transmitting end is a UE, the receiving end is a network device, and the above-mentioned decoder is a CSI reconstructor; independent training can be initiated by the UE, and the UE trains the CSI generator and CSI reconstructor of the terminal-side device based on the true CSI, generates CSI feedback based on the trained CSI generator, and then sends the CSI feedback (i.e., the above-mentioned M channel information feedback) and the label of the true CSI data set including the above-mentioned true CSI (i.e., the above-mentioned N first labels) to the network device; the network device obtains the above-mentioned true CSI (i.e., the above-mentioned M true channel information) from storage or other devices based on the label of the true CSI data set, and trains the CSI reconstructor of the network-side device based on the received CSI feedback and the obtained true CSI.

[0173] S603: The terminal side device trains the encoder in the artificial intelligence model based on M channel information feedback and M true value channel information.

[0174] Among them, the artificial intelligence model can be a two-end model, which includes an encoder and a decoder. The encoder is deployed on the terminal side device and the decoder is deployed on the network side device.

[0175] Exemplarily, the M channel information feedbacks are M CSI feedbacks, the M true-value channel information are M true-value CSI, and the encoder is a CSI generator. The network-side device can use the M true-value CSI as input and the M CSI feedbacks as labels to train the CSI generator. When the value of the loss function is less than a threshold value or meets the target requirement, a trained CSI generator is obtained. This application does not limit the specific form of the loss function.

[0176] Assume that the transmitting end is a network device, the receiving end is a UE, and the above-mentioned encoder is a CSI generator; independent training can be initiated by the network device, and the network device trains the CSI generator and CSI reconstructor of the network-side device based on the true CSI, generates CSI feedback based on the trained CSI generator, and then sends the CSI feedback (i.e., the above-mentioned M channel information feedback) and the label of the true CSI data set including the above-mentioned true CSI (i.e., the above-mentioned N first labels) to the UE; the UE obtains the above-mentioned true CSI (i.e., the above-mentioned M true channel information) from storage or other devices based on the label of the true CSI data set, and trains the CSI generator of the terminal-side device based on the received CSI feedback and the obtained true CSI.

[0177] It should be noted that S602 and S603 are optional steps.

[0178] In some embodiments of the present application, one of the first information, the second information, or the third information can also be transmitted between the network side device and the terminal side device, and any one of the first information, the second information, or the third information is used for inference or determination of the encoder and / or decoder for monitoring; wherein the first information includes N first identifiers and second information, the second information is the identifier of one or more second data sets to which the M channel information feedback belongs, the third information is the identifier of the third data set, and the third data set is a data set including N first data sets and second data sets.

[0179] In one implementation, the first data set may be a true CSI data set, and the second data set may be a CSI feedback data set. Then, the first information is an identifier of the true CSI data set and an identifier of the CSI feedback data set; and the second information is an identifier of the CSI feedback data set.

[0180] For example, the receiving end receives the identifier of the true-value CSI dataset and the identifier of the CSI feedback dataset, and the receiving end may determine the decoder and / or encoder obtained by training the true-value CSI dataset and part or all of the data of the CSI feedback dataset as the model for monitoring or inference. For another example, the receiving end receives the identifier of the CSI feedback dataset, and the receiving end may determine the true-value CSI dataset corresponding to the CSI feedback dataset, and determine the decoder and / or encoder obtained by training the true-value CSI dataset and part or all of the data of the CSI feedback dataset as the model for monitoring or inference. For another example, the receiving end receives the identifier of a third dataset, and the receiving end may determine the decoder and / or encoder obtained by training based on part or all of the data of the third dataset as the model for monitoring or inference.

[0181] Optionally, an embodiment of the present application can be applied to an open RAN structure scenario, and the above-mentioned network side device can be a near real-time RIC or a non-real-time RIC, and the near real-time RIC or the non-real-time RIC performs model training of the network side device; the near real-time RIC or the non-real-time RIC transmits the above-mentioned first data to the above-mentioned terminal side device (such as UE) through the access network device, and / or, the near real-time RIC or the non-real-time RIC transmits one of the above-mentioned first information, second information or third information to the above-mentioned terminal side device (such as UE) through the access network device.

[0182] The method embodiment shown in Figure 6 above includes many possible implementation schemes. Some of the implementation schemes are illustrated below in conjunction with Figure 7. It should be noted that the relevant concepts, operations or logical relationships not explained in Figure 7 can refer to the corresponding descriptions in the embodiment shown in Figure 6.

[0183] In this application, the embodiment shown in FIG7 can be used as a separate embodiment, and the embodiment shown in FIG7 can be independent of the technical solution of FIG6 ; some steps in the embodiment shown in FIG7 can also be used as separate embodiments.

[0184] Figure 7 is a flowchart of another communication method provided by an embodiment of the present application. In Figure 7, dashed boxes represent optional steps, that is, the method may not include one or more of steps S702, S703 or S704.

[0185] In the embodiment of the present application, the network side device is a network device and the terminal side device is a UE. For example, the communication method provided by the present application is described in detail. The functions performed by the UE in the embodiment of the present application can also be performed by a module (e.g., a chip) in the UE, and the functions performed by the network device in the embodiment of the present application can also be performed by a module (e.g., a chip) in the network device.

[0186] Exemplarily, in an embodiment of the present application, the above-mentioned channel information feedback is CSI feedback, and the above-mentioned true channel information is true CSI; the above-mentioned first data set is a true CSI data set, and the above-mentioned second data set is a CSI feedback data set; the above-mentioned artificial intelligence model is a two-end model, the above-mentioned encoder is a CSI generator, and the above-mentioned decoder is a CSI reconstructor.

[0187] S701: CSI feedback data set information is transmitted between a network device and a UE. The CSI feedback data set information includes multiple CSI feedbacks and one or more true value CSI data set identifiers.

[0188] Optionally, step S701 may specifically be that the network device sends the CSI feedback data set information to the UE, or the UE sends the CSI feedback data set information to the network device.

[0189] The CSI feedback dataset information includes multiple CSI feedbacks; the CSI feedback dataset information is further used to indicate which true-value CSI dataset(s) the dataset corresponds to. For example, the CSI feedback dataset information includes one or more true-value CSI dataset identifiers, or includes a bit map corresponding to one or more true-value CSI datasets.

[0190] Optionally, the CSI feedback may be unquantized or quantized. The quantizer may be a scalar quantizer or a vector quantizer. It should be understood that the quantizer described above refers to the quantizer in the two-end model. That is, even if the CSI feedback is not quantized, floating-point numbers must be converted to bits during transmission. For example, floating-point numbers can be represented using float32 or float64, which can be considered nearly lossless, i.e., with approximately no quantization loss.

[0191] Optionally, the above-mentioned true-value CSI dataset may be a predefined true-value CSI dataset, or a true-value CSI dataset exchanged between the network device and the UE. For example, if the network device has previously sent true-value CSI dataset 1 to the UE, the above-mentioned true-value CSI dataset identifier may be the identifier of true-value CSI dataset 1. For another example, if the network device has previously sent dataset 2 to the UE, and dataset 2 includes true-value CSI, the above-mentioned true-value CSI dataset identifier may be the identifier of dataset 2.

[0192] Optionally, the UE can obtain a CSI feedback dataset and the true CSI dataset corresponding to the CSI feedback dataset from different devices; network devices can also obtain a CSI feedback dataset and the true CSI dataset corresponding to the CSI feedback dataset from different devices. For example, when network device 1 sends true CSI dataset 1 to UE1 and network device 2 sends CSI feedback dataset 1 to UE2, the identifier of the true CSI dataset 1 sent by network device 1 to UE1 can be indicated. If UE1 and UE2 are from the same manufacturer, they can share data through a server, that is, UE1 and UE2 can share the true CSI dataset 1 through the server.

[0193] Optionally, the CSI feedback data set information may further include the format of the CSI feedback. Exemplarily, the format of the CSI feedback may include at least one of floating-point number information of the CSI feedback and dimension information of the CSI feedback. For example, the floating-point number information of the CSI feedback may refer to the correspondence between floating-point numbers and bits of the CSI feedback, i.e., the number of bits corresponding to each floating-point number; the dimension information of the CSI feedback may refer to the structural information of the dimensions to which the CSI feedback data should be converted when used, i.e., the number of dimensional arrays to which each CSI feedback data should be converted when used, the length of each dimension, and the order between the dimensions.

[0194] Optionally, the CSI feedback data set information may further include an identifier of the CSI feedback data set.

[0195] Optionally, the CSI feedback data set information may further include the number of CSI feedbacks in the CSI feedback data set.

[0196] Optionally, the CSI feedback dataset information may further include a correspondence between the CSI feedback dataset and the true-value CSI dataset, that is, which true-value CSIs in the true-value CSI dataset the CSI feedback in the CSI feedback dataset corresponds to.

[0197] Exemplarily, the above-mentioned correspondence can be indicated by rules and parameters, wherein the rule can be any one or more of the following rules: the first n, or the last n, or the consecutive n starting from the kth, or the i-th of every m, or the i-th of every m starting from the kth, corresponding to one or more true-value CSI datasets in each true-value CSI dataset; the parameter refers to the values ​​of n, k, i, and m in the above-mentioned rules. The rules and parameters can be predefined or indicated by the CSI feedback dataset information. For example, the rules can be predefined, and the parameters can be indicated by the CSI feedback dataset information. Optionally, if the CSI feedback dataset corresponds to multiple true-value CSI datasets, it is necessary to indicate the correspondence with each true-value CSI dataset.

[0198] S702: The network device trains a CSI reconstructor based on the CSI feedback data set information.

[0199] For example, please refer to the above step S602, which will not be described in detail here. When the CSI feedback data set is generated by the network side device, S702 is optional.

[0200] S703: The UE trains a CSI generator based on the CSI feedback data set information.

[0201] For example, please refer to the above step S603, which will not be described in detail here. When the CSI feedback data set is generated by the terminal side device, S703 is optional.

[0202] S704: The UE and the network device transmit the identifier of the true CSI data set and the identifier of the CSI feedback data set, or the identifier of the CSI feedback data set, or the identifier of a third data set, where the third data set is a data set including the true CSI data set and the CSI feedback data set.

[0203] In some embodiments, during the model pairing process, the network device and the UE can achieve model pairing by exchanging CSI feedback dataset identifiers, or true value CSI dataset identifiers and CSI feedback dataset identifiers, or identifiers of third datasets, i.e., notifying the other end which model to use, or instructing the other end which model to use, or notifying the other end which model or models they have, where the model refers to the terminal-side model and / or the network-side model, or a dual-end model; indicating a dual-end model is equivalent to indicating the terminal-side model or network-side model corresponding to the dual-end model. For ease of understanding, this application refers to the dataset including true value CSI and CSI feedback as the third dataset.

[0204] For example, Table 1 is a schematic diagram of the correspondence between a data set and an AI model provided in this application.

[0205] Table 1 Correspondence between datasets and AI models

[0206] The terminal-side model is the aforementioned CSI generator, and the network-side model is the aforementioned CSI reconstructor. The AI ​​model in a row includes both the terminal-side model and the network-side model in that row. For example, in the second row, AI model 1 includes terminal-side model 1 and network-side model 1; in the third row, AI model 2 includes terminal-side model 3 and network-side model 2. It should be understood that the AI ​​models in Table 1 are used to indicate dual-end models. For example, indicating AI model 1 is equivalent to indicating both terminal-side model 1 and network-side model 1.

[0207] It is understandable that the CSI feedback dataset interaction process can realize the identification of the third dataset. The CSI feedback dataset information (one or more true value CSI dataset identifiers) indicates the true value CSI dataset corresponding to the CSI feedback dataset. Therefore, there is a correspondence between the CSI feedback dataset and the third dataset (including true value CSI and CSI feedback), that is, the third dataset can be indicated by the CSI feedback dataset identifier. For example, CSI feedback dataset 1 corresponds to true value CSI dataset 2, then the identifier of CSI feedback dataset 1 can indicate the third dataset consisting of CSI feedback dataset 1 and its corresponding true value CSI dataset 2 (a subset). For another example, CSI feedback dataset 1 corresponds to true value CSI dataset 1 and true value CSI dataset 2, then the identifier of CSI feedback dataset 1 can indicate the third dataset consisting of CSI feedback dataset 1 and its corresponding true value CSI dataset 1 (a subset) and true value CSI dataset 2 (a subset).

[0208] It is understandable that the CSI feedback dataset interaction process can realize model identification. The CSI feedback dataset identifier can indicate the AI ​​model (such as a decoder) trained by the CSI feedback dataset and its corresponding true value CSI dataset, or indicate the AI ​​model (such as an encoder) that generates the CSI feedback dataset. For example, in Table 1 above, CSI feedback dataset 1 is associated with true value CSI dataset 1, and terminal side model 1 and base station side model 1 are both trained by CSI feedback dataset 1 and true value CSI dataset 1. Then, the identifier of CSI feedback dataset 1 can indicate AI model 1 (composed of terminal side model 1 and network side model 1), or it can indicate terminal side model 1, or it can indicate network side model 1.

[0209] The method embodiment shown in Figure 6 above includes many possible implementation schemes. Some of the implementation schemes are illustrated below in conjunction with Figure 8. It should be noted that the relevant concepts, operations or logical relationships not explained in Figure 8 can refer to the corresponding descriptions in the embodiment shown in Figure 6.

[0210] In this application, the embodiment shown in FIG8 can be used as a separate embodiment, and the embodiment shown in FIG8 can be independent of the technical solutions of FIG6 or FIG7; some steps in the embodiment shown in FIG8 can also be used as separate embodiments. Optionally, the embodiment shown in FIG8 can also be applied in combination with the embodiment shown in FIG6 or FIG7.

[0211] Please refer to Figure 8, which is a flowchart of another communication method provided in an embodiment of the present application. In Figure 8, the dashed boxes represent optional steps, that is, the method may not include steps S802, S803, and S804, or may include at least one of steps S802, S803, or S804.

[0212] The functions performed by the network side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the network side device, and the functions performed by the terminal side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the terminal side device.

[0213] Among them, the network side device may include a network device and / or an entity communicating with the network device, such as a server, such as an OTT device, or a cloud server; the terminal side device may be a user device and / or an entity communicating with the user device, such as a server, such as an OTT device, or a cloud server.

[0214] As shown in FIG8 , the communication method may include the following steps:

[0215] S801: A first data set and multiple second data sets corresponding to the first data set are transmitted between a network side device and a terminal side device, where the first data set includes one or more true-value channel information, and the multiple second data sets include M channel information feedbacks, where M is a positive integer; the one or more true-value channel information include true-value channel information corresponding to the M channel information feedbacks; the one or more true-value channel information include first true-value channel information, the first true-value channel information corresponds to first channel information feedback and second channel information feedback, and the first channel information feedback and the second channel information feedback respectively belong to two data sets among the multiple second data sets.

[0216] Exemplarily, each of the multiple second data sets includes at least two channel information feedbacks, and the total number of channel information feedbacks of the multiple second data sets is the above-mentioned M, that is, all channel information feedbacks of the multiple second data sets are the above-mentioned M channel information feedbacks; each true-value channel information in the above-mentioned first data set corresponds to at least one of the above-mentioned M channel information feedbacks, and the number of true-value channel information included in the first data set is less than the above-mentioned M.

[0217] Optionally, the true value channel information corresponding to the M channel information feedbacks is predefined or pre-acquired.

[0218] In some embodiments, the true channel information is true CSI, the channel information feedback is CSI feedback, the first data set is a true CSI data set, and the second data set is a CSI feedback data set.

[0219] For example, the network-side device is a base station, and the terminal-side device is a user equipment terminal (UE). The base station sends a true-value CSI dataset and multiple CSI feedback datasets corresponding to the true-value CSI dataset to the UE. The true-value CSI dataset includes N true-value CSIs, and the multiple CSI feedback datasets include a total of M CSI feedbacks, where N < M. The correspondence between the N true-value CSIs and the M CSI feedbacks includes: each true-value CSI in the N true-value CSIs corresponds to at least one CSI feedback in the M CSI feedbacks; at least one true-value CSI in the N true-value CSIs corresponds to at least two CSI feedbacks in the M CSI feedbacks, and the at least two CSI feedbacks belong to different CSI feedback datasets.

[0220] For example, a base station sends a true-value CSI dataset 1 and two CSI feedback datasets (CSI feedback dataset 1 and CSI feedback dataset 2) corresponding to the true-value CSI dataset 1 to a UE. The true-value CSI dataset 1 includes two true-value CSIs, namely, a first true-value CSI and a second true-value CSI; CSI feedback dataset 1 includes two CSI feedbacks, a first CSI feedback and a second CSI feedback; and CSI feedback dataset 2 includes two CSI feedbacks, a third CSI feedback and a fourth CSI feedback. The first true-value CSI corresponds to the first and third CSI feedbacks, and the second true-value CSI corresponds to the second and fourth CSI feedbacks. Therefore, the first true-value channel information mentioned above may refer to the first true-value CSI or the second true-value CSI. If the first true-value channel information is the first true-value CSI, then the first channel information feedback and the second channel information feedback corresponding to the first true-value channel information are the first CSI feedback and the third CSI feedback; if the first true-value channel information is the second true-value CSI, then the first channel information feedback and the second channel information feedback corresponding to the first true-value channel information are the second CSI feedback and the fourth CSI feedback.

[0221] S802: First indication information is transmitted between the network side device and the terminal side device, where the first indication information is used to indicate a correspondence between M channel information feedbacks and true value channel information in a first data set.

[0222] It can be understood that the first indication information is used to indicate which true value CSIs in the first data set the M channel information feedbacks correspond to.

[0223] For example, the first indication information may be a rule and / or a parameter, i.e., the corresponding relationship is indicated by a rule and a parameter. The rule may be any one or more of the following rules: the first n, last n, consecutive n starting from the kth, or the i-th of every m, or the i-th of every m starting from the kth, corresponding to one or more true-value CSI data sets. The parameter refers to the values ​​of n, k, i, and m in the above rules. For example, the rule may be predefined, and the parameter may be indicated by the CSI feedback data set information.

[0224] S803: The network side device trains the decoder in the artificial intelligence model based on the M channel information feedbacks and the true channel information corresponding to the M channel information feedbacks.

[0225] Among them, the artificial intelligence model can be a two-end model, which includes an encoder and a decoder. The encoder is deployed on the terminal side device and the decoder is deployed on the network side device.

[0226] For example, please refer to the above step S602, which will not be repeated here.

[0227] S804: The terminal side device trains the encoder in the artificial intelligence model based on the M channel information feedbacks and the true channel information corresponding to the M channel information feedbacks.

[0228] The artificial intelligence model may be a dual-end model, which includes an encoder and a decoder, wherein the encoder is deployed on the terminal side device and the decoder is deployed on the network side device. For example, step S804 may refer to step S603 above and will not be repeated here.

[0229] S802, S803 and S804 are optional steps.

[0230] In some embodiments of the present application, one of the first information, the second information, or the third information may be transmitted between the network-side device and the terminal-side device, and any one of the first information, the second information, or the third information is used for inference or determination of an encoder and / or decoder for monitoring; wherein the first information includes N first identifiers and second information, the second information is the identifier of one or more second data sets to which the M channel information feedback belongs, the third information is the identifier of a third data set, and the third data set is a data set including N first data sets and second data sets. For specific implementation, please refer to the relevant contents of Figures 6 and 7 above (such as the relevant contents of step S704), which will not be repeated here.

[0231] The method embodiment shown in Figure 6 above includes many possible implementation schemes. Some of the implementation schemes are illustrated below in conjunction with Figure 9. It should be noted that the relevant concepts, operations or logical relationships not explained in Figure 9 can refer to the corresponding descriptions in the embodiment shown in Figure 6.

[0232] In this application, the embodiment shown in FIG9 can be used as a separate embodiment, and the embodiment shown in FIG9 can be independent of the technical solutions shown in FIG6, FIG7, or FIG8; some steps in the embodiment shown in FIG9 can also be used as separate embodiments. Optionally, the embodiment shown in FIG9 can be applied in combination with the embodiment shown in FIG6, FIG7, or FIG8.

[0233] Please refer to Figure 9, which is a flowchart of another communication method provided by an embodiment of the present application. In Figure 9, the dashed boxes represent optional steps, for example, the method may only include step S902 or step S903.

[0234] The functions performed by the network side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the network side device, and the functions performed by the terminal side device in the embodiment of the present application can also be performed by a module (for example, a chip) in the terminal side device.

[0235] The network-side device may be a network device or an entity communicating with the network device; the terminal-side device may be a user device or an entity communicating with the user device. An exemplary introduction can be found above and will not be repeated here.

[0236] S901: One of the first information, the second information or the third information is transmitted between the network side device and the terminal side device; wherein the first information includes an identifier of a first data set and the second information, the second information is an identifier of a second data set, the third information is an identifier of a third data set, and the third data set is a data set including the first data set and the second data set; the first data set includes multiple true value channel information, and the second data set includes multiple channel information feedbacks.

[0237] In an embodiment of the present application, if the network side device is the sending end, the terminal side device is the receiving end, then the above-mentioned transmission of one of the first information, the second information or the third information means: the network side device sends one of the first information, the second information or the third information to the terminal side device, and accordingly, the terminal side device receives one of the first information, the second information or the third information from the network side device; if the terminal side device is the sending end, the network side device is the receiving end, then the above-mentioned transmission of one of the first information, the second information or the third information means: the terminal side device sends one of the first information, the second information or the third information to the network side device, and accordingly, the network side device receives one of the first information, the second information or the third information from the terminal side device.

[0238] Exemplarily, the true-value channel information is true-value CSI, the channel information feedback is CSI feedback, the first data set is a true-value CSI data set, and the second data set is a CSI feedback data set. Assuming that the network-side device is a base station and the terminal-side device is a UE, the UE and the base station can transmit an identifier of the true-value CSI data set and an identifier of the CSI feedback data set, or an identifier of the CSI feedback data set, or an identifier of a third data set; the UE and the base station can determine the encoder and / or decoder to be monitored or monitored based on the transmitted identifier.

[0239] S902: The network-side device determines an encoder and / or decoder to be inferred or monitored based on any one of the first information, the second information, or the third information.

[0240] In one possible implementation, upon receiving one of the first, second, or third information sent by the terminal device, the network-side device determines an encoder and / or decoder for inference or monitoring based on the information. The encoder and / or decoder determined by any one of the first, second, or third information is trained using the data set corresponding to the information.

[0241] For example, the second data set is CSI feedback data set 1, and the artificial intelligence model trained with CSI feedback data set 1 and the true-value CSI data set 2 corresponding to the CSI feedback data set is model 1. Model 1 includes encoder 1 and decoder 1. Then, the identifier of CSI feedback data set 1 can be used to determine at least one of model 1, encoder 1, or decoder 1, and the identifier of CSI feedback data set 1 and the identifier of true-value CSI data set 2 can be used to determine at least one of model 1, encoder 1, or decoder 1. For another example, the third data set is data set 1, and data set 1 includes a CSI feedback data set and a true-value CSI data set. The artificial intelligence model trained with data set 1 is model 2. Model 2 includes encoder 2 and decoder 2. Then, the identifier of data set 1 can be used to determine at least one of model 2, encoder 2, or decoder 2.

[0242] For example, please refer to the relevant content of step S704 above, which will not be repeated here.

[0243] S903: The terminal side device determines the encoder and / or decoder for inference or monitoring based on any one of the above-mentioned first information, second information or third information.

[0244] For example, please refer to the relevant content of step S902, which will not be repeated here.

[0245] In an embodiment of the present application, the sending end and the receiving end can achieve dual-end model pairing through the identifier of the data set (such as one of the first information, second information or third information mentioned above).

[0246] The above content elaborates on the method provided by the present application. In order to facilitate the implementation of the above scheme of the embodiment of the present application, the embodiment of the present application also provides corresponding devices or equipment.

[0247] The present application divides the functional modules of the network side device and the terminal side device according to the above-mentioned method embodiment. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in this application is schematic and is only a logical functional division. There may be other division methods in actual implementation. The communication device of the embodiment of the present application will be described in detail below with reference to Figures 10 to 12.

[0248] 10 , which is a schematic diagram of a communication device according to an embodiment of the present application, wherein the communication device may include a transceiver unit 10 and a processing unit 20 .

[0249] In some embodiments of the present application, the communication device may be the terminal-side device shown above, or a chip or circuit provided in the terminal-side device, or a network-side device, or a chip or circuit provided in the network-side device. That is, the communication device may be used to execute the steps or functions performed by the terminal-side device or the network-side device in the above method embodiments.

[0250] In one design, the transceiver unit 10 is used to: transmit first data, the first data includes M channel information feedbacks and N first identifiers, the N first identifiers are used to indicate N first data sets stored at the receiving end, the N first identifiers correspond one-to-one to the N first data sets, N and M are positive integers, each of the N first data sets includes one or more true-value channel information, the M channel information feedbacks correspond to M true-value channel information, the N first data sets include M true-value channel information, and each of the N first data sets includes at least one of the M true-value channel information.

[0251] In a possible implementation, N is 1, and the M pieces of true value channel information are part or all of the true value channel information in the first data set.

[0252] In one possible embodiment, the first data also includes at least one of the following: the format of the channel information feedback, the identifier of one or more second data sets to which the M channel information feedbacks belong, the number of the M channel information feedbacks, or first indication information, wherein the first indication information is used to indicate the correspondence between the M channel information feedbacks and the true channel information in the N first data sets.

[0253] In one possible embodiment, the processing unit 20 is used to: train a first model based on M channel information feedbacks and M true value channel information, where the first model is an encoder or decoder in an artificial intelligence model, the encoder is deployed on a terminal side device, and the decoder is deployed on a network side device.

[0254] In a possible implementation, the M pieces of true value channel information are predefined or pre-acquired.

[0255] In one possible embodiment, the transceiver unit 10 is used to: transmit one of the first information, the second information, or the third information, and any one of the first information, the second information, or the third information is used for inference or determination of the encoder and / or decoder for monitoring; wherein the first information includes N first identifiers and second information, the second information is the identifier of one or more second data sets to which the M channel information feedback belongs, and the third information is the identifier of the third data set, and the third data set is a data set including N first data sets and second data sets.

[0256] In the embodiment of the present application, the description of the first data, the first data set, the true value channel information, etc. can be referred to the introduction in the method embodiments shown in Figures 6 to 7 above, and will not be described in detail here.

[0257] It is understood that the specific description of the transceiver unit 10 and the processing unit 20 shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit 10 and the processing unit 20, reference can be made to the method embodiments shown in Figures 6 and 7 above, and will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects of the method embodiments shown in Figures 6 and 7 above, and for the sake of brevity, they will not be repeated here.

[0258] Reusing Figure 10, in some embodiments of the present application, the communication device can be the terminal-side device shown above, or a chip or circuit provided in the terminal-side device, or a network-side device, or a chip or circuit provided in the network-side device. That is, the communication device can be used to execute the steps or functions performed by the terminal-side device or the network-side device in the above method embodiments.

[0259] In one design, the transceiver unit 10 is used to: transmit a first data set and multiple second data sets corresponding to the first data set, the first data set includes one or more true-value channel information, the multiple second data sets include M channel information feedbacks, M is a positive integer; the one or more true-value channel information include true-value channel information corresponding to the M channel information feedbacks; the one or more true-value channel information include first true-value channel information, the first true-value channel information corresponds to first channel information feedback and second channel information feedback, and the first channel information feedback and the second channel information feedback respectively belong to two data sets in the multiple second data sets.

[0260] In a possible implementation, the transceiver unit 10 is configured to transmit first indication information, where the first indication information is used to indicate a correspondence between M channel information feedbacks and true value channel information in the first data set.

[0261] In one possible embodiment, the processing unit 20 is used to: train a first model based on M channel information feedbacks and true channel information corresponding to the M channel information feedbacks, where the first model is an encoder or decoder in an artificial intelligence model, the encoder is deployed on a terminal side device, and the decoder is deployed on a network side device.

[0262] In a possible implementation, the true value channel information corresponding to the M channel information feedbacks is predefined or pre-acquired.

[0263] In one possible implementation, the transceiver unit 10 is configured to: transmit one of the first information, the second information, or the third information, wherein any one of the first information, the second information, or the third information is used for inference or for determination of the encoder and / or decoder for monitoring;

[0264] The first information includes the identifier of the first data set and the second information, the second information is the identifier of multiple second data sets, the third information is the identifier of the third data set, and the third data set is a data set including the first data set and multiple second data sets.

[0265] In the embodiment of the present application, the description of the first data set, the second data set, the true value channel information, etc. can refer to the introduction in the method embodiment shown in Figure 8 above, and will not be described in detail here.

[0266] It is understood that the specific description of the transceiver unit 10 and the processing unit 20 shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit 10 and the processing unit 20, reference can be made to the method embodiment shown in Figure 8 above, and no further details will be given here. In addition, the technical effects of the embodiment of the present application refer to the technical effects of the method embodiment shown in Figure 8 above, and for the sake of brevity, no further details will be given here.

[0267] The above describes the network-side device and terminal-side device of the embodiments of the present application. The following describes possible product forms of the network-side device and terminal-side device. It should be understood that any product that has the functions of the terminal-side device or network-side device described in FIG10 above falls within the scope of protection of the embodiments of the present application. It should also be understood that the following description is merely illustrative and does not limit the product form of the communication device of the embodiments of the present application to this description.

[0268] In one possible implementation, in the communication device shown in FIG10 , the processing unit 20 may be a processing circuit, and the transceiver unit 10 may be a communication circuit. The processing circuit may be one or more processors, or all or part of the control or processing circuitry within one or more processors. When the communication device is a terminal device or network device, the communication circuit may be a transceiver circuit, which may be a transceiver. When the communication device is a chip or a chip system, the communication circuit may be an interface circuit. When the communication device is a server, the communication circuit may be an interface circuit or a transceiver circuit. The transceiver unit 10 may also be a transmitting unit and a receiving unit, where the transmitting unit may be a transmitting circuit and the receiving unit may be a receiving circuit, with the transmitting unit and receiving unit being integrated into a single device. In the embodiments of the present application, the processing circuit and the communication circuit may be coupled, etc., and the embodiments of the present application do not limit the connection method between the processing circuit and the communication circuit. During the execution of the above-described method, the process of sending information in the above-described method may be understood as the process of the processing circuit outputting the above-described information. When outputting the above-described information, the processing circuit outputs the above-described information to the communication circuit for transmission by the communication circuit. After being output by the processing circuit, the information may need to undergo further processing before reaching the communication circuit. Similarly, the process of receiving information in the above method can be understood as the process of the processing circuit receiving the input information. When the processing circuit receives the input information, the communication circuit receives the information and inputs it into the processing circuit. Furthermore, after the communication circuit receives the information, the information may need to undergo further processing before being input into the processing circuit. In one possible implementation, in the communication device shown in Figure 10, the processing unit 20 can be one or more processors, the transceiver unit 10 can be a transceiver, or the transceiver unit 10 can be a transmitting unit and a receiving unit, the transmitting unit can be a transmitter, the receiving unit can be a receiver, and the transmitting unit and receiving unit are integrated into a single device, such as a transceiver. In the embodiments of the present application, the processor and transceiver can be coupled, etc., and the connection method between the processor and transceiver is not limited in the embodiments of the present application. During the execution of the above method, the process of sending information in the above method can be understood as the process of the processor outputting the information. When outputting the information, the processor outputs the information to the transceiver for transmission by the transceiver. After being output by the processor, the information may undergo further processing before reaching the transceiver. Similarly, the information receiving process in the above method can be understood as the process of the processor receiving the input information. When the processor receives the input information, the transceiver receives the information and inputs it into the processor. Furthermore, after the transceiver receives the information, the information may undergo further processing before being input into the processor.

[0269] Referring to Figure 11, Figure 11 is another structural diagram of the communication device provided in an embodiment of the present application. As shown in Figure 11, the communication device provided in an embodiment of the present application can be used to implement the method described in the above method embodiment, and reference can be made to the description in the above method embodiment. The communication device can be a terminal side device, or a network side device, or a chip therein. Exemplarily, the communication device includes one or more processors 1001. The communication device may further include a memory 1003. Optionally, the communication device may further include a transceiver 1002. In one implementation, the communication device also includes an input and output device (not shown in Figure 11).

[0270] Processor 1001 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data. Memory 1003 is primarily used to store software programs and data. Transceiver 1002 may include control circuitry and an antenna. The control circuitry is primarily used to convert baseband signals into radio frequency signals and process radio frequency signals. The antenna is primarily used to transmit and receive radio frequency signals in the form of electromagnetic waves. Input / output devices, such as a touch screen, display, and keyboard, are primarily used to receive user input and output data to the user.

[0271] When the communication device is powered on, the processor 1001 can read the software program in the memory 1003, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be sent wirelessly, the processor 1001 performs baseband processing on the data to be sent and outputs the baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal and then transmits the radio frequency signal to the outside in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 1001. The processor 1001 converts the baseband signal into data and processes the data.

[0272] In another implementation, the RF circuit and antenna may be provided independently of the processor performing baseband processing. For example, in a distributed scenario, the RF circuit and antenna may be remotely arranged independent of the communication device.

[0273] The processor 1001 , the transceiver 1002 , and the memory 1003 may be connected via a communication bus.

[0274] Exemplarily, when the communication device is used to execute the steps, methods, or functions performed by the network-side device in the embodiment shown in FIG. 6 above, the transceiver 1002 can be used to execute step S601 in FIG. 6 , the processor 1001 can be used to execute S602 in FIG. 6 , and / or other processes for the technology described herein.

[0275] Exemplarily, when the communication device is used to execute the steps, methods or functions performed by the terminal side device in the embodiment shown in Figure 6 above, the transceiver 1002 can be used to execute step S601 in Figure 6, the processor 1001 can be used to execute S603 in Figure 6, and / or other processes for the technology described herein.

[0276] In any of the above implementations, the processor 1001 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or the transceiver circuit, interface, or interface circuit may be used for transmitting or delivering signals.

[0277] In any of the above implementations, the processor 1001 may store instructions, which may be computer programs. The computer programs, when executed on the processor 1001, may cause the communication device to perform the methods described in the above method embodiments. The computer programs may be embedded in the processor 1001, in which case the processor 1001 may be implemented by hardware.

[0278] In one implementation, the communication device may include a circuit that can implement the functions of sending, receiving, or communicating in the aforementioned method embodiment. The processor and transceiver described in this application can be implemented in an integrated circuit (IC), an analog IC, a radio frequency integrated circuit (RFIC), a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-channel metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0279] It is understood that the communication device shown in the embodiment of the present application may also have more components than those in Figure 11, and the embodiment of the present application is not limited to this. The method performed by the processor and transceiver shown above is only an example. For the specific steps performed by the processor and transceiver, please refer to the description of the method embodiment above.

[0280] In another possible implementation, the communication device provided in the embodiment of the present application may include one or more processors and memory. Wherein, the processor is used to execute a program stored in the memory, and when the program is executed, the above method embodiment is executed. Exemplarily, the processor and memory can also be integrated into one device, that is, the processor and memory can also be integrated together. For specific details about the processor and memory, please refer to the relevant content of the processor 1001 and memory 1003 in Figure 11.

[0281] In another possible implementation, the communication device shown in FIG11 may further include a processing unit, which may be one or more logic circuits, and the transceiver unit 10 may be an input / output interface, or may be referred to as a communication interface, or an interface circuit, or an interface, etc. Alternatively, the transceiver unit 10 may be a transmitting unit and a receiving unit, the transmitting unit may be an output interface, the receiving unit may be an input interface, and the transmitting unit and the receiving unit may be integrated into one unit, such as an input / output interface.

[0282] Referring to Figure 12, Figure 12 is another structural diagram of a communication device provided in an embodiment of the present application. As shown in Figure 12, the communication device shown in Figure 12 includes a logic circuit 901 and an interface 902. That is, the above-mentioned processing unit can be implemented with a logic circuit 901, and the transceiver unit 10 can be implemented with an interface 902. Among them, the logic circuit 901 can be a chip, a processing circuit, an integrated circuit or a system on chip (SoC) chip, etc., and the interface 902 can be a communication interface, an input and output interface, a pin, etc. Exemplarily, Figure 12 is shown as an example of a chip as the above-mentioned communication device, and the chip includes a logic circuit 901 and an interface 902.

[0283] In the embodiment of the present application, the logic circuit and the interface may also be coupled to each other. The embodiment of the present application does not limit the specific connection method between the logic circuit and the interface.

[0284] Exemplarily, when the communication device is used to execute the steps, methods, or functions executed by the terminal-side device in the method embodiment shown in FIG. 6 , the interface 902 is used to transmit the first data.

[0285] Exemplarily, when the communication device is used to execute the steps, methods, or functions executed by the network-side device in the method embodiment shown in FIG. 6 , the interface 902 is used to transmit the first data.

[0286] In the embodiment of the present application, the description of the first data, etc. can refer to the description of the method embodiment shown in Figure 6 above, and will not be described in detail here. It is understood that the specific description of the logic circuit 901 and the interface 902 can also refer to the description of the processing unit and the transceiver unit shown in Figure 10, and will not be repeated here.

[0287] It can be understood that the communication device shown in the embodiment of the present application can implement the method provided in the embodiment of the present application in the form of hardware, or can implement the method provided in the embodiment of the present application in the form of software, etc., and the embodiment of the present application is not limited to this.

[0288] For the specific implementation of each embodiment shown in FIG12 , reference may also be made to the above embodiments, which will not be described in detail here.

[0289] An embodiment of the present application also provides a communication system, which includes a network side device and a terminal side device. The network side device and the terminal side device can be used to execute the method in any of the aforementioned method embodiments (Figures 6 to 9).

[0290] In addition, the present application also provides a computer program, which is used to implement the operations and / or processing performed by the communication device (such as the above-mentioned network side device and terminal side device) in the method provided by the present application.

[0291] The present application also provides a computer-readable storage medium, which stores computer code. When the computer code runs on a computer, the computer executes the operations and / or processing performed by the communication device (such as the above-mentioned network side device and terminal side device) in the method provided by the present application.

[0292] The present application also provides a computer program product, which includes computer code or computer program. When the computer code or computer program runs on a computer, the operations and / or processing performed by the communication device (such as the above-mentioned network side device and terminal side device) in the method provided by the present application are executed.

[0293] 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 only schematic. For example, the division of the units is only 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0294] 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 the units may be selected according to actual needs to achieve the technical effects of the solutions provided in the embodiments of the present application.

[0295] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0296] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, including a number of 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 readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program code.

[0297] 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 this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method comprises: Transmitting first data, the first data including M channel information feedbacks and N first identifiers, the N first identifiers being used to indicate the N first data sets stored at the receiving end, the N first identifiers corresponding one-to-one to the N first data sets, N and M being positive integers, each of the N first data sets including one or more true-valued channel information, the M channel information feedbacks corresponding to the M true-valued channel information, the N first data sets including the M true-valued channel information, and each of the N first data sets including at least one of the M true-valued channel information.

2. The method according to claim 1, characterized in that The N is 1, and the M pieces of true value channel information are part or all of the true value channel information in the first data set.

3. The method according to claim 1 or 2, characterized in that The first data also includes at least one of the following: the format of the channel information feedback, the identifier of one or more second data sets to which the M channel information feedbacks belong, the number of the M channel information feedbacks, or first indication information, wherein the first indication information is used to indicate the correspondence between the M channel information feedbacks and the true channel information in the N first data sets.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Based on the M channel information feedback and the M true value channel information, a first model is trained, where the first model is an encoder or decoder in an artificial intelligence model, the encoder is deployed on a terminal side device, and the decoder is deployed on a network side device.

5. The method according to claim 4, characterized in that The M pieces of true value channel information are predefined or pre-acquired.

6. The method according to claim 4 or 5, characterized in that The method further comprises: transmitting one of first information, second information, or third information, wherein any of the first information, the second information, or the third information is used for inference or for determination of the encoder and / or the decoder for monitoring; The first information includes the N first identifiers and the second information, the second information is the identifier of one or more second data sets to which the M channel information feedbacks belong, the third information is the identifier of the third data set, and the third data set is a data set including the N first data sets and the second data set.

7. A communication method, characterized in that: The method comprises: Transmit a first data set and multiple second data sets corresponding to the first data set, wherein the first data set includes one or more true-valued channel information, and the multiple second data sets include M channel information feedbacks, where M is a positive integer; the one or more true-valued channel information include true-valued channel information corresponding to the M channel information feedbacks; the one or more true-valued channel information include first true-valued channel information, the first true-valued channel information corresponds to first channel information feedback and second channel information feedback, and the first channel information feedback and the second channel information feedback respectively belong to two data sets among the multiple second data sets.

8. The method according to claim 7, characterized in that The method further comprises: Transmitting first indication information, where the first indication information is used to indicate a correspondence between the M channel information feedbacks and true value channel information in the first data set.

9. The method according to claim 7 or 8, characterized in that The method further comprises: Based on the M channel information feedbacks and the true channel information corresponding to the M channel information feedbacks, a first model is trained. The first model is an encoder or decoder in an artificial intelligence model. The encoder is deployed on a terminal side device, and the decoder is deployed on a network side device.

10. The method according to claim 9, characterized in that The true value channel information corresponding to the M channel information feedbacks is predefined or pre-acquired.

11. The method according to claim 9 or 10, characterized in that The method further comprises: transmitting one of first information, second information, or third information, wherein any of the first information, the second information, or the third information is used for inference or for determination of the encoder and / or the decoder for monitoring; The first information includes the identifier of the first data set and the second information, the second information is the identifier of the multiple second data sets, the third information is the identifier of the third data set, and the third data set is a data set including the first data set and the multiple second data sets.

12. A communication method, characterized in that: The method comprises: Transmit one of the first information, the second information or the third information, wherein any one of the first information, the second information or the third information is used for inference or determination of an encoder or / and decoder for monitoring; wherein the first information includes an identifier of a first data set and the second information, the second information is an identifier of a second data set, the third information is an identifier of a third data set, and the third data set is a data set including the first data set and the second data set; the first data set includes multiple true value channel information, and the second data set includes multiple channel information feedbacks.

13. The method according to claim 12, characterized in that The transmitting one of the first information, the second information, or the third information includes: The network side device sends one of the first information, the second information, or the third information to the terminal side device; Alternatively, the terminal side device sends one of the first information, the second information or the third information to the network side device.

14. The method according to claim 12 or 13, characterized in that The dual-end model includes the encoder and / or the decoder, the encoder is deployed on the terminal side device, and the decoder is deployed on the network side device.

15. The method according to any one of claims 12 to 14, characterized in that The encoder and / or the decoder are determined by fourth information, where the fourth information is any one of the first information, the second information or the third information, and the encoder and / or the decoder are trained using a data set corresponding to the fourth information.

16. A communication device, characterized in that: Comprising a module or unit for executing the method according to any one of claims 1 to 6, or a module or unit for executing the method according to any one of claims 7 to 11, or a module or unit for executing the method according to any one of claims 12 to 15.

17. A communication device, characterized in that: The method comprises a processor, wherein the processor is used to implement the method according to any one of claims 1 to 6, 7 to 11, or 12 to 15 through logic circuits or executing code instructions.

18. A readable storage medium, characterized in that Used to store a program, the program being executed by one or more processors so that a device including the one or more processors performs the method according to any one of claims 1 to 6, 7 to 11, or 12 to 15.

19. A communication system, characterized in that: Comprising one or more of an apparatus for performing the method of any one of claims 1 to 6, an apparatus for performing the method of any one of claims 7 to 11, or an apparatus for performing the method of any one of claims 12 to 15.

Images