Communication method and communication apparatus

Abstract

Provided in the present application are a communication method and a communication apparatus, which are applied to the field of communications. The technical solution of the present application involves: using training data of a specific scenario to perform low-rank adaptation fine-tuning on a base model, so as to obtain a low-rank adaptation model corresponding to the base model. In this way, for different scenarios, a model adapted to a scenario can be obtained simply by using training data of the scenario to perform low-rank adaptation fine-tuning on a base model. By means of the technical solution provided in the present application, the training computation amount of a model corresponding to a scenario can be reduced, and transmission overheads of said model between devices can be reduced.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202411937820.3, filed with the State Intellectual Property Office of China on December 25, 2024, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods and communication devices. Background Technology

[0003] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, leading to increasingly diverse requirements. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology is being introduced into wireless communication networks to achieve network intelligence.

[0004] In one approach to applying AI technology in wireless communication networks, the base station trains a model locally based on historical data and then sends the trained model structure and weight parameters to the user equipment (UE). The terminal uses this model structure and weights for inference. Taking channel state information (CSI) feedback as an example, after the base station trains the encoder and decoder, it sends the encoder model to the UE. The UE compresses (optionally, also includes quantization) the CSI using the encoder and sends the compressed (optionally, also includes quantization) CSI to the base station. The base station then recovers the CSI using the decoder.

[0005] However, in scenarios where different CSI models are required for feedback in different scenarios, the above method has the following problems: the base station needs to train multiple models for multiple scenarios, and the base station and UE need to transmit these multiple models, which leads to high training costs for the base station and large model transmission overhead between the base station and UE. Summary of the Invention

[0006] This application provides a communication method and a communication device, which helps to reduce the model training cost of access network equipment and the model transmission overhead between access network equipment and terminals.

[0007] Firstly, this application provides a communication method that can be executed by a communication device. This communication device can be an access network device, or a device within the access network device (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), chip system, or processor), or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device. The following description uses an access network device as an example.

[0008] This communication method includes: sending a first model to a terminal; sending first information to the terminal, wherein the first information is used to instruct the training of a first low-rank adaptive model based on a first training dataset and a first model, and the first low-rank adaptive model is associated with the first model.

[0009] In this communication method, the first low-rank adaptation model is associated with the first model, which can be understood as follows: the first low-rank adaptation model is a low-rank adaptation model trained based on the first model. Because the first low-rank adaptation model is a low-rank adaptation model trained based on the first model, the functions achieved when the first low-rank adaptation model and the first model are used together are the same as (or similar to) those of the first model, but it can adapt to different scenarios.

[0010] Because the amount of training data required to train a low-rank adaptive model is relatively small, that is, the amount of training data required to train a second model (i.e., the first model plus the first low-rank adaptive model) that has the same (or similar) function as the first model is relatively small, the amount of training data required to obtain multiple models with the same function but adaptable to different scenarios can be reduced, thereby reducing the amount of computation in the training process.

[0011] In scenarios where training data is distributed by access network devices, this approach can also reduce the transmission overhead of the training data. Since the distributed training dataset is used to train a model, distributing the training dataset can also be understood as distributing the model; therefore, reducing the transmission overhead of the training data can also be understood as reducing the transmission overhead of the model.

[0012] In some possible implementations, the first model is used to perform at least one of the following processes on the CSI: prediction, compression, or quantization.

[0013] In some possible implementations, the first information includes: the first training dataset, the identifier of the first model, and the identifier of the first low-rank adaptive model.

[0014] In other words, the first training dataset is distributed from the access network device to the terminal. Since the first information also includes the identifier of the first model and the identifier of the first low-rank adaptation model, the access network device and the terminal can align the association between the first model and the first low-rank adaptation model, enabling the terminal to accurately train the first low-rank adaptation model using the corresponding first training dataset.

[0015] In some possible implementations, this communication method further includes sending second information to the terminal, the second information being used to indicate the performance metrics of the first low-rank adaptive model.

[0016] In this implementation, the terminal can be trained to obtain a first low-rank adaptive model that meets the requirements according to the instructions of the second information.

[0017] In some possible implementations, this communication method further includes receiving third information from the terminal, the third information being used to indicate whether the first low-rank adaptation model meets the performance metrics.

[0018] In this implementation, the terminal indicates to the access network device whether the first low-rank adaptation obtained during training meets the performance indicators. This helps the access network device perform relevant subsequent operations based on this information, ensuring communication performance. For example, re-distributing the training dataset.

[0019] In some possible implementations, this communication method further includes receiving fifth information from a terminal, the fifth information being used to indicate the processing result obtained based on the first model and the first low-rank adaptive model.

[0020] In some possible implementations, the fifth information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

[0021] In this implementation, while reporting the processing results based on the first model and the first low-rank adaptation model, the terminal also indicates that the processing results are based on the first model and the first low-rank adaptation model, which helps the access network device to perform corresponding processing. For example, in a scenario where the function of the first model includes compressed CSI, the fifth information reported by the terminal includes the identifier of the first model and the identifier of the first low-rank adaptation model, which helps the access network device to decompress the received CSI using the decompression model corresponding to the first model and the decompression low-rank adaptation model corresponding to the first low-rank adaptation model, so as to restore the CSI.

[0022] Secondly, this application provides a communication method that can be executed by a communication device. This communication device can be a terminal, or a device within the terminal (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or a logical node, logical module, or software capable of implementing all or part of the terminal's functions. The following description uses a terminal as an example.

[0023] This communication method includes: receiving a first model from an access network device; receiving first information from the access network device, the first information being used to instruct the training of a first low-rank adaptive model based on a first training dataset and a first model; and performing low-rank adaptation tuning on the first model according to the first information to obtain a first low-rank adaptive model associated with the first model.

[0024] In some possible implementations, the first information includes: the first training dataset, the identifier of the first model, and the identifier of the first low-rank adaptive model.

[0025] In some possible implementations, this communication method further includes receiving second information from an access network device, the second information being used to indicate the performance metrics of the first low-rank adaptation model.

[0026] In some possible implementations, this communication method further includes sending third information to the access network device, the third information being used to indicate whether the first low-rank adaptation model meets performance indicators.

[0027] In some possible implementations, this communication method further includes receiving fifth information from a terminal, the fifth information being used to indicate the processing result obtained based on the first model and the first low-rank adaptive model.

[0028] In some possible implementations, the fifth information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

[0029] In some possible implementations, the first model is used to perform at least one of the following processes on the CSI: prediction, compression, or quantization.

[0030] The technical effects of this communication method can be found in the relevant content of the first aspect, and will not be repeated here.

[0031] Thirdly, this application provides a communication method that can be executed by a communication device. This communication device can be an access network device, or a device within the access network device (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), a chip system, or a processor), or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device. The following description uses an access network device as an example.

[0032] This communication method includes: sending a first model to a terminal; and sending fourth information to the terminal, the fourth information being used to indicate a first low-rank adaptive model associated with the first model.

[0033] In this communication method, the first low-rank adaptation model is associated with the first model, which can be understood as follows: the first low-rank adaptation model is a low-rank adaptation model trained based on the first model. Because the first low-rank adaptation model is a low-rank adaptation model trained based on the first model, the functions achieved when the first low-rank adaptation model and the first model are used together are the same as (or similar to) those of the first model, but it can adapt to different scenarios.

[0034] Because training a low-rank adaptive model requires less training data—meaning training a second model (i.e., the first model plus the first low-rank adaptive model) with the same (or similar) functionality as the first model requires less training data—the amount of training data needed to obtain multiple models with the same functionality but adaptable to different scenarios can be reduced, thus decreasing the computational load during training. In scenarios where the model on the terminal side is distributed by the access network device, this also reduces the model's transmission overhead.

[0035] In some possible implementations, the first model is used to perform at least one of the following processes on the CSI: prediction, compression, or quantization.

[0036] In some possible implementations, the fourth information includes: the identifier of the first model, and the identifier of the first low-rank adaptive model.

[0037] In some possible implementations, this communication method further includes receiving fifth information from a terminal, the fifth information being used to indicate the processing result obtained based on the first model and the first low-rank adaptive model.

[0038] In some possible implementations, the fifth information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

[0039] In this implementation, while reporting the processing results based on the first model and the first low-rank adaptation model, the terminal also indicates that the processing results are based on the first model and the first low-rank adaptation model, which helps the access network device to perform corresponding processing. For example, in a scenario where the function of the first model includes compressed CSI, the fifth information reported by the terminal includes the identifier of the first model and the identifier of the first low-rank adaptation model, which helps the access network device to decompress the received CSI using the decompression model corresponding to the first model and the decompression low-rank adaptation model corresponding to the first low-rank adaptation model, so as to restore the CSI.

[0040] Fourthly, this application provides a communication method that can be executed by a communication device. This communication device can be a terminal, or a device within the terminal (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or a logical node, logical module, or software capable of implementing all or part of the terminal's functions. The following description uses a terminal as an example.

[0041] This communication method includes: receiving a first model from an access network device; and receiving fourth information from the access network device, the fourth information being used to indicate a first low-rank adaptive model associated with the first model.

[0042] In some possible implementations, the first model is used to perform at least one of the following processes on the CSI: prediction, compression, or quantization.

[0043] In some possible implementations, the fourth information includes: the identifier of the first model, and the identifier of the first low-rank adaptive model.

[0044] In some possible implementations, this communication method further includes sending a fifth message to the access network device, the fifth message being used to indicate the processing result based on the first model and the first low-rank adaptive model.

[0045] In some possible implementations, the fifth information includes: the identifier of the first model, the processing result, and the identifier of the first low-rank adaptive model.

[0046] The technical effects of this communication method can be found in the relevant content of the third aspect, and will not be repeated here.

[0047] Fifthly, this application provides a communication device. This communication device may be an access network device, or a device within the access network device (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), chip system, or processor), or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device.

[0048] This communication device may include modules that perform the methods / operations / steps / actions described in the first aspect or any of the possible implementations thereof. These modules may be hardware circuits, software, or a combination of hardware circuits and software.

[0049] In one design, the communication device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions in the method described in the first aspect above or any possible implementation thereof, while the processing module is used to perform the processing actions involved in the method described in the first aspect above or any possible implementation thereof.

[0050] Sixthly, this application provides a communication device. This communication device may be a terminal, or a device within a terminal (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or a logical node, logical module, or software capable of implementing all or part of the terminal's functions.

[0051] This communication device may include modules that perform the methods / operations / steps / actions described in the second aspect or any of the possible implementations thereof. These modules may be hardware circuits, software, or a combination of hardware circuits and software.

[0052] In one design, the communication device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions in the method described in the second aspect above or any possible implementation thereof, while the processing module is used to perform the processing actions involved in the method described in the second aspect above or any possible implementation thereof.

[0053] Seventhly, this application provides a communication device. This communication device may be an access network device, or a device within the access network device (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), chip system, or processor), or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device.

[0054] This communication device may include modules that perform the methods / operations / steps / actions described in the third aspect or any of the possible implementations thereof. These modules may be hardware circuits, software, or a combination of hardware circuits and software.

[0055] In one design, the communication device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions in the method described in the third aspect above or any possible implementation thereof, while the processing module is used to perform the processing actions involved in the method described in the third aspect above or any possible implementation thereof.

[0056] Eighthly, this application provides a communication device. This communication device may be a terminal, or a device within a terminal (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or a logical node, logical module, or software capable of implementing all or part of the terminal's functions.

[0057] This communication device may include modules that perform the methods / operations / steps / actions described in the fourth aspect or any of the possible implementations thereof. These modules may be hardware circuits, software, or a combination of hardware circuits and software.

[0058] In one design, the communication device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions in the method described in the fourth aspect above or any possible implementation thereof, while the processing module is used to perform the processing actions involved in the method described in the fourth aspect above or any possible implementation thereof.

[0059] Ninthly, this application provides a communication device including a processor, wherein instructions are executed by the processor to cause the method as described in the first aspect or any possible implementation thereof to be implemented.

[0060] Optionally, the communication device may further include a storage medium that stores the instructions executed by the processor.

[0061] In some implementations, the storage medium is integrated with the processor, for example, the storage medium is integrated into the processor.

[0062] In a tenth aspect, this application provides a communication device including a processor, wherein instructions are executed by the processor to cause the method as described in the second aspect or any possible implementation thereof to be implemented.

[0063] Optionally, the communication device may further include a storage medium that stores the instructions executed by the processor.

[0064] In some implementations, the storage medium is integrated with the processor, for example, the storage medium is integrated into the processor.

[0065] In one aspect, this application provides a communication device including a processor, wherein instructions are executed by the processor to cause the method as described in the third aspect or any possible implementation thereof to be implemented.

[0066] Optionally, the communication device may further include a storage medium that stores the instructions executed by the processor.

[0067] In some implementations, the storage medium is integrated with the processor, for example, the storage medium is integrated into the processor.

[0068] In a twelfth aspect, this application provides a communication device including a processor, wherein instructions are executed by the processor to cause the method as described in the fourth aspect or any possible implementation thereof to be implemented.

[0069] Optionally, the communication device may further include a storage medium that stores the instructions executed by the processor.

[0070] In some implementations, the storage medium is integrated with the processor, for example, the storage medium is integrated into the processor.

[0071] In a thirteenth aspect, this application provides a chip including processing circuitry for running programs or instructions to implement methods as described in the first aspect or any possible implementation thereof.

[0072] Optionally, the chip may further include a memory for storing programs or instructions.

[0073] Optionally, the chip may also include the transceiver circuit, or an input / output interface.

[0074] In a fourteenth aspect, this application provides a chip including processing circuitry for running programs or instructions to implement methods as described in the second aspect or any possible implementation thereof.

[0075] Optionally, the chip may further include a memory for storing programs or instructions.

[0076] Optionally, the chip may also include the transceiver circuit, or an input / output interface.

[0077] In a fifteenth aspect, this application provides a chip including processing circuitry for running programs or instructions to implement methods as described in the third aspect or any of its possible implementations.

[0078] Optionally, the chip may further include a memory for storing programs or instructions.

[0079] Optionally, the chip may also include the transceiver circuit, or an input / output interface.

[0080] In a sixteenth aspect, this application provides a chip including processing circuitry for running programs or instructions to implement methods as described in the fourth aspect or any possible implementation thereof.

[0081] Optionally, the chip may further include a memory for storing programs or instructions.

[0082] Optionally, the chip may also include the transceiver circuit, or an input / output interface.

[0083] In a seventeenth aspect, this application provides a computer-readable storage medium including instructions that, when executed by a processor, cause a method as described in the first aspect or any possible implementation thereof to be implemented.

[0084] In an eighteenth aspect, this application provides a computer-readable storage medium including instructions that, when executed by a processor, cause the method as described in the second aspect or any possible implementation thereof to be implemented.

[0085] In a nineteenth aspect, a computer-readable storage medium is provided, the computer-readable storage medium including instructions that, when executed by a processor, cause a method as described in the third aspect or any of its possible implementations to be implemented.

[0086] In a twentieth aspect, this application provides a computer-readable storage medium including instructions that, when executed by a processor, cause the method as described in the fourth aspect or any of its possible implementations to be implemented.

[0087] In a twentieth aspect, this application provides a computer program product comprising computer program code or instructions that, when executed, cause the method as described in the first aspect or any of its possible implementations to be implemented.

[0088] In a twentieth aspect, this application provides a computer program product comprising computer program code or instructions that, when executed, cause the method as described in the second aspect or any of its possible implementations to be implemented.

[0089] In a twentieth aspect, this application provides a computer program product comprising computer program code or instructions that, when executed, cause the method described in the third aspect or any of its possible implementations to be implemented.

[0090] In a twentieth aspect, this application provides a computer program product comprising computer program code or instructions that, when executed, cause the method as described in the fourth aspect or any of its possible implementations to be implemented.

[0091] In a twentieth aspect, this application provides a communication system for performing the methods described in the first aspect or any possible implementation thereof and for performing the methods described in the second aspect or a corresponding implementation thereof, or the communication system for performing the methods described in the third aspect or any possible implementation thereof and for performing the methods described in the fourth aspect or a corresponding implementation thereof.

[0092] It is understandable that the technical effects in any of the fifth to twenty-fifth aspects can be referenced from the technical effects in the corresponding aspect. Attached Figure Description

[0093] Figure 1 is a schematic diagram of a neuron structure according to an embodiment of this application;

[0094] Figure 2 is a schematic diagram of the FNN structure according to an embodiment of this application;

[0095] Figure 3 is a schematic diagram of a low-rank structure according to an embodiment of this application;

[0096] Figures 4 to 7 are schematic diagrams of communication systems according to various embodiments of this application;

[0097] Figure 8 is a schematic diagram of a chip system architecture according to an embodiment of this application;

[0098] Figures 9 to 13 are schematic flowcharts of communication methods according to various embodiments of this application;

[0099] Figures 14 and 15 are schematic diagrams of the structure of communication devices according to various embodiments of this application. Detailed Implementation

[0100] To better introduce the technical solution of this application, some relevant concepts and technologies involved in this application will be introduced below.

[0101] Machine learning (ML) is an important technological approach to achieving artificial intelligence (AI). Machine learning can be divided into supervised learning, unsupervised learning, and reinforcement learning.

[0102] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and expresses this learned mapping relationship using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear mappings and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0103] Unsupervised learning relies solely on collected sample values, using algorithms to discover inherent patterns within the samples. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample, which is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0104] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0105] Deep neural networks (DNNs) are a specific implementation of machine learning. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0106] The idea of ​​DNN originates from the neuronal structure of the brain. Figure 1 is a schematic diagram of the neuronal structure of one embodiment of this application. As shown in Figure 1, each neuron performs a weighted summation operation on its input values, and the weighted summation result generates the output through a nonlinear function. Specifically, assume that the input of the neuron is x = [x0,...,x...]. n The weights corresponding to the inputs are w = [w0,...,w...]. n The bias of the weighted summation is b. The nonlinear function can take many forms; one example is the max{0,x} maximum value function. The effect of a neuron's execution can be...

[0107] DNNs typically have a multi-layered structure, with each layer containing multiple neurons. The input layer processes the received values ​​through neurons and then passes them to the hidden layers. Similarly, the hidden layers then pass the computation results to the final output layer, producing the final output of the DNN.

[0108] DNNs typically have more than one hidden layer, and these hidden layers often directly affect the ability to extract information and fit functions. Increasing the number of hidden layers or widening the width of each layer can improve the function fitting ability of a DNN. The weights in each neuron are the parameters of the DNN network model. The model parameters are optimized through the training process, enabling the DNN network to extract data features and express mapping relationships. DNNs generally use supervised or unsupervised learning strategies to optimize model parameters.

[0109] Based on the network construction method, DNNs can be divided into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Figure 2 is a schematic diagram of an FNN structure according to an embodiment of this application. Its characteristic is that the neurons in adjacent layers are completely connected to each other, which makes FNNs usually require a large amount of storage space and result in high computational complexity.

[0110] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0111] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0112] The FNN, CNN, and RNN mentioned above are common neural network structures, all built upon neurons. As introduced above, each neuron performs a weighted summation operation on its input values, and the result is passed through a nonlinear function to produce the output. We call the weights of the weighted summation operation and the nonlinear function in the neural network the parameters of the neural network. Taking a neuron with max{0, x} as the nonlinear function as an example, we perform... The parameters of the operated neuron are weights w = [w0,...,w...]. nThe weighted summation bias is b, and the nonlinear function is max{0,x}. The parameters of all neurons in a neural network constitute the parameters of that neural network.

[0113] Low-rank adaptation (LoRA) is an incremental tuning method. It introduces a low-rank structure into the model's weight matrix and tunes this low-rank structure to adapt the model to new tasks or scenarios.

[0114] Figure 3 is a schematic diagram of a low-rank structure according to an embodiment of this application. As shown in Figure 3, the low-rank structure is composed of two concatenated matrices A and B, with dimensions d×r and r×d, respectively, where d is the input / output dimension and r << d. This results in a significantly smaller number of parameters in the low-rank structure compared to the pre-trained parameters in the same layer. In the low-rank structure, the input features are multiplied by these two matrices sequentially, and the output of the new structure is the sum of the original model's output and the low-rank structure's output. This allows for fine-tuning of the parameters in the low-rank structure using a small amount of scenario-specific data, making the entire model suitable for new scenarios. When facing various scenarios, multiple low-rank structures can be trained separately, and these low-rank structures, individually combined with the original model, can adapt to different scenarios.

[0115] A training dataset is a collection of training samples, each serving as an input to the neural network. It's used for model training. The training dataset is one of the most crucial parts of machine learning; the training process essentially involves learning certain features from the training dataset to minimize the difference between the neural network's output and the ideal target value. Typically, even with the same network structure, neural networks trained on different training datasets will have different weights and outputs. Therefore, the composition and selection of the training dataset, to a certain extent, determine the performance of the trained neural network.

[0116] When AI models are deployed in an over-the-air (OTA) architecture, whether for offline or online model updates / training, data from the actual network deployment is required to form the dataset needed for model updates / training. A high-quality training dataset helps wireless communication AI algorithm design achieve greater performance gains and improves the generalization ability and robustness of the final algorithm across various scenarios. Conversely, a flawed training dataset can easily lead to inaccurate gain evaluation, model overfitting, weak generalization ability, and poor scenario adaptability, among other problems.

[0117] The technical solution proposed in this application is described below.

[0118] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0119] In the description of the embodiments of this application, unless otherwise stated, "a plurality of" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0120] In the description of the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0121] In the description of the embodiments of this application, the terms "information", "signal", "message", "channel", and "signaling" may sometimes be used interchangeably. It should be noted that when their distinctions are not emphasized, their intended meanings are matched.

[0122] In the description of the embodiments of this application, the terms "of", "corresponding (relevant)" and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing their distinction, their intended meanings are matched.

[0123] In the description of the embodiments of this application, the order of the process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0124] In the description of the embodiments of this application, "preset," "predefined," or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminals and wireless access network devices), or by being pre-defined in a protocol. This application does not limit the specific implementation method. "Stored" can refer to storing in one or more memories. The one or more memories can be separate settings or integrated into an encoder or decoder, processor, or communication device. The one or more memories can also be partially separate settings and partially integrated into a decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0125] In the description of the embodiments of this application, "protocol" may refer to standard protocols in the field of communications, such as 3GPP LTE protocols (such as technical specification (TS) 36, i.e., the TS36 series of technical specifications), NR protocols (such as the TS38 series of technical specifications), and related protocols applied to future communication systems. This application does not limit this.

[0126] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation.

[0127] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0128] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0129] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal chip and other modules of the terminal, or between a base station chip and other modules of the base station.

[0130] It is understood that the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0131] The technical solutions provided in this application can be applied to various communication systems, such as: 5th 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 network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems 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. Furthermore, the terms "system" and "network" are interchangeable.

[0132] In a communication system, a network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device.

[0133] In the embodiments of this 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 apparatus.

[0134] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, 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 vehicles, 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 public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0135] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0136] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0137] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, 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 can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in future communication networks, or equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0138] 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 depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0139] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0140] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0141] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and 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 RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0142] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement one or more functions before and after layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more functions of inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU. For uplink transmission, the DU is configured to implement one or more functions before and after demapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and demapping), while other functions after demapping (e.g., digital BF or one or more functions of fast Fourier transform (FFT) / removing CP) are moved to the RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0143] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0144] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0145] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0146] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0147] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced.

[0148] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be, for example, one or more of the following: network devices, terminal devices, or core network elements, etc.

[0149] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0150] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0151] AI nodes can be AI network elements or AI modules.

[0152] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0153] 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 they can be deployed on the same node or device.

[0154] Figure 4 is a schematic diagram of a communication system according to an embodiment of this application. As shown in Figure 4, the communication system 100 may include at least one network device, such as network device 110 shown in Figure 4; the communication system 100 may also include at least one terminal device, such as terminal device 120 shown in Figure 4. Network device 110 and terminal device 120 can communicate via a wireless link. The communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0155] In practical applications, this communication system may include multiple network devices or multiple terminal devices. This application does not limit the number of network devices and terminal devices included in the communication system.

[0156] Figure 5 is a schematic diagram of a communication system according to another embodiment of this application. Compared to the communication system 100 shown in Figure 4, the communication system 200 shown in Figure 5 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models.

[0157] In some implementations, network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by terminal device 120. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to terminal device 120. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on terminal device 120. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on terminal device 120.

[0158] It is understood that Figure 5 only illustrates the example of AI network element 140 being directly connected to network device 110. In other scenarios, AI network element 140 can also be connected to terminal device 120. Alternatively, AI network element 140 can be connected to both network device 110 and terminal device 120 simultaneously. Alternatively, AI network element 140 can also be connected to network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between AI network element and other network elements.

[0159] In some implementations, the AI ​​network element 140 can be set as a module in network devices and / or terminal devices, for example, in network device 110 or terminal device 120 as shown in Figure 4.

[0160] It should be noted that Figures 4 and 5 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, or core network devices, which are not shown in Figures 4 and 5.

[0161] Figure 6 is a schematic diagram of a communication system according to another embodiment of this application. As shown in Figure 6, network elements in the communication system are connected through interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network node (RAN node) network equipment, terminals, or one or more devices in operation administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 6 for clarity).

[0162] Network devices can function as a single RAN node or comprise multiple RAN nodes, such as CUs and DUs. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured within the CU-CP and / or CU-UP.

[0163] Figure 7 is a schematic diagram of a communication system according to another embodiment of this application. As shown in Figure 7, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 6, used to implement AI-related functions.

[0164] RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0165] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from network devices (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. Optionally, the NRT RIC can deliver inference results to network devices and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the NRT RIC delivers inference results to the DU, and the DU sends them to the RU.

[0166] Non-real-time RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from network devices (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the network devices and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers the inference result to a DU, which then forwards it to an RU.

[0167] For example, near real-time RICs are set up in network devices (e.g., CU, DU), while non-real-time RICs are set up in OAM, cloud servers, core network devices, or other network devices. RICs can be trained by obtaining subsets from multiple end devices from network devices (e.g., CU, CU-CP, CU-UP, DU, and / or RU), recombining them into a training dataset #2, and training on the training dataset #2.

[0168] For example, near real-time RIC and non-real-time RIC can also be set up separately as a network element, and the network device can be a near real-time RIC or a non-real-time RIC.

[0169] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Optionally, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in network devices (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0170] Figure 8 is a schematic diagram of a chip system architecture according to an embodiment of this application. This chip system architecture can be used in access network devices and / or terminal devices. Input / output control is used to manage the input and output signals of the device; for example, input / output control can be represented as a modem, keyboard, mouse, touchscreen, etc. Input / output control may also be part of a processor. Communication control is used to manage the device's reception and transmission of signals; communication control may also be part of a processor. Receiver / transmitter is used to communicate with other devices; the receiver / transmitter may include a modem for modulating information or demodulating modulated information. Antenna is used to transmit or 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 (NNs).

[0171] Figure 9 is a schematic flowchart of a communication method according to an embodiment of this application. This communication method includes steps S910 and S920. The communication method is executed by an access network device and a terminal. As an example, the access network device is any of the aforementioned communication systems. As an example, the terminal is any of the aforementioned communication systems.

[0172] It is understood that the access network device in the embodiments of this application can be replaced by a device within the access network device (e.g., a module, a communication module, a circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or it can be a logical node, logical module, or software that can implement all or part of the functions of the access network device.

[0173] It is understood that the terminal in the embodiments of this application can be replaced by a device within the terminal (e.g., a module, a communication module, a circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or it can be a logical node, logical module, or software that can implement all or part of the terminal functions.

[0174] In S910, the access network device sends the first model to the terminal. Correspondingly, the terminal receives the first model.

[0175] As an example, the first model is a DNN model.

[0176] As an example, the first model is used to perform at least one of the following processes on the CSI: prediction, compression, or quantization.

[0177] For example, the first model is used to compress CSI; another example is that the first model is used to compress and quantize CSI; yet another example is that the first model is used to predict CSI, and so on.

[0178] When the first model is used to perform multiple processes on CSI, it is understood that the embodiments of this application do not limit the order in which the first model performs at least one of the above-mentioned processes on CSI.

[0179] The following content of this embodiment will use the first model for CSI compression as an example. The implementation of the first model for other processing can be found in the relevant content on the first model for CSI compression, which will not be repeated here.

[0180] As an example, the access network device sends a first model to the terminal, including: the access network device sending the structure and parameters of the first model to the terminal.

[0181] As an example, the access network device sends a first model to the terminal, including: the access network device sending a training dataset of the first model to the terminal, and the terminal training the first model based on the training dataset.

[0182] As an example, the access network device also sends an identifier of the first model to the terminal. In this way, when the terminal has multiple models, it can distinguish the first model from other models based on the identifier of the first model.

[0183] S920, the access network device sends first information to the terminal, the first information being used to instruct the training of a first low-rank adaptive model based on a first training dataset and a first model, the first low-rank adaptive model being associated with the first model. Accordingly, the terminal receives the first information.

[0184] In this embodiment, the first low-rank adaptation model refers to the low-rank adaptation structure obtained by performing low-rank adaptation optimization on the first model based on the first training dataset.

[0185] The association between the first low-rank adaptive model and the first model can be understood as follows: the first low-rank adaptive model is a low-rank adaptive structure obtained by low-rank adaptation optimization of the first model.

[0186] The first information is used to indicate the training of the first low-rank adaptive model based on the first training dataset and the first model. It can be understood as: the first information indicates that the first model is tuned for low-rank adaptation based on the first training dataset, and the resulting low-rank adaptive structure is called the first low-rank adaptive model.

[0187] The first model in this embodiment can be called the basic model.

[0188] In this embodiment, training a first low-rank adaptive model based on a first training dataset and a first model can be understood as: fine-tuning the first model using the first training dataset using LoRA. The first training dataset can be referred to as a fine-tuning dataset for a specific scenario, or simply a fine-tuning dataset.

[0189] As an example, the first information carries at least one of the following: a first training dataset, an identifier of a first model, or an identifier of a first low-rank adaptive model.

[0190] The first information carries the identifier of the first model so that the terminal can know which model the first training dataset is used to perform low-rank adaptation tuning; the first information carries the identifier of the first low-rank adaptation model so that the terminal can know what the identifier of the low-rank adaptation model obtained by performing low-rank adaptation tuning on the first model based on the first training dataset is, thereby facilitating accurate indication of the first low-rank adaptation model between the access network device and the terminal.

[0191] In some implementations, the first information does not carry an identifier for the first low-rank adaptation model. After the terminal trains and obtains the first low-rank adaptation model, it assigns an identifier to the first low-rank adaptation model and informs the access network device.

[0192] As an example, the first training dataset is training data corresponding to a specific scenario. For example, this specific scenario may include one or more scenarios such as high-speed movement, occlusion, and multiple scatterers.

[0193] Taking the first model for CSI compression as an example, the first training dataset contains CSIs collected under a specific scenario. Thus, compressing the CSIs under this specific scenario based on the first model and the first low-rank adaptive model yields better compression performance than compressing the CSIs under this specific scenario based solely on the first model, because the first low-rank adaptive model is trained on the CSIs under this specific scenario. This results in a higher compression ratio and reduces the transmission overhead of the terminal uploading CSIs to the access network device.

[0194] Taking the first model for CSI compression as an example, to adapt to different scenarios, some implementations train different CSI compression models for different scenarios. For instance, a full-scale model is trained using CSI collected in the first scenario, and another full-scale model is trained using CSI collected in the second scenario. The access network device then distributes these two full-scale models to the terminal. The terminal uses the first full-scale model to compress the CSI in the first scenario and the second full-scale model to compress the CSI in the second scenario. Here, a full-scale model refers to a model that can achieve CSI compression when used alone.

[0195] In this embodiment, taking two scenarios as examples, the method of low-rank adaptation tuning of the first model based on the training dataset of a specific scenario requires training at least one full model and one low-rank adaptation model; while the aforementioned method of training different full models for different scenarios requires training at least two full models. Therefore, it can be seen that the method of low-rank adaptation tuning of the first model based on the training dataset of a specific scenario in this application can reduce the computational load of the model training equipment and reduce training costs.

[0196] On the other hand, taking two scenarios as examples, the method of low-rank adaptive tuning of the first model based on the training dataset of a specific scenario only requires the access network device to send at least one full model (or the training dataset corresponding to one full model) and one fine-tuning dataset corresponding to the scenario to the terminal. However, the aforementioned method of training different full models for different scenarios requires the access network device to send at least two full models or the training datasets corresponding to two full models to the terminal. Therefore, it can be seen that the method of low-rank adaptive tuning of the first model based on the training dataset of a specific scenario in this application can reduce the model transmission overhead between the access network device and the terminal.

[0197] In some implementations, the access network device also sends second information to the terminal, which indicates the performance metrics of the first low-rank adaptive model. Accordingly, the terminal receives the second information. Furthermore, when training the first low-rank adaptive model based on the first information, the terminal can determine whether the performance of the trained first low-rank adaptive model meets the requirements.

[0198] In some implementations, the second information can be understood as being used to determine or detect whether the first low-rank adaptive model meets the performance metrics.

[0199] As an example, the second information includes at least one of the following: a validation dataset, i.e., a dataset used to validate the accuracy of the first low-rank adaptation model; the accuracy metric or accuracy requirement of the first low-rank adaptation model; or, the maximum number of training iterations for the first low-rank adaptation model.

[0200] It is understandable that in some implementations, the performance metrics of the first low-rank adaptation model are predefined in the terminal or predetermined by the terminal based on the protocol.

[0201] Using the second information to indicate performance metrics, compared to predefined performance metrics in the terminal, helps to train the first low-rank adaptation model according to the needs of the access network equipment; using predefined performance metrics in the terminal, compared to using the second information to indicate performance metrics, helps to reduce the transmission overhead between the access network equipment and the terminal.

[0202] In some implementations, as shown in Figure 10, the communication method of this application embodiment further includes: S930, the terminal uses the first training dataset to perform low-rank adaptation tuning on the first model to obtain the first low-rank adaptation model.

[0203] It is understandable that after the terminal obtains the first low-rank adaptation model, it can store the first low-rank adaptation model, as well as the mapping relationship between the first low-rank adaptation model, the first model, and the specific scenario.

[0204] In some implementations, as shown in FIG10, the communication method of this application embodiment further includes: S940, the terminal sends third information to the access network device, the third information being used to indicate whether the first low-rank adaptation model meets the performance indicators. Accordingly, the access network device receives the third information.

[0205] In some implementations, after receiving the third information, the access network device performs corresponding processing based on the third information. For example, it resends the training dataset of the low-rank adaptive model used to train the first model in that specific scenario to the terminal, so that the terminal can obtain the first low-rank adaptive model that meets the performance indicators.

[0206] In some implementations, the third information is used to indicate whether the first low-rank adaptation model meets performance metrics, including: the third information indicating the performance of the first low-rank adaptation model. In this case, the access network device determines whether the first low-rank adaptation model meets performance metrics based on the performance metrics and the performance indicated by the third information.

[0207] Optionally, the access network device can determine the re-distributed training dataset based on the difference between the current performance and the performance index of the first low-rank adaptive model, so that the low-rank adaptive model trained on the re-distributed training dataset can meet the performance index, thereby improving the efficiency of making the trained low-rank adaptive model meet the performance index.

[0208] In some implementations, the third information can be understood as an indication of the training results of the first low-rank adaptation model.

[0209] In some implementations, the communication method of this application embodiment further includes: the terminal using a first model and a first low-rank adaptation model to process data collected in a specific scene to obtain a processing result. It can be understood that the specific scene here is the same as the scene corresponding to the training dataset used to train the first low-rank adaptation model.

[0210] Taking the first model for compressing CSI as an example, as shown in Figure 10, the communication method of this application embodiment further includes: S950 and S960.

[0211] In S950, the access network equipment sends CSI-RS to the terminal. The terminal then measures the CSI-RS to obtain the CSI.

[0212] S960, the terminal compresses the CSI based on the scenario of the measured CSI-RS as the scenario corresponding to the first training dataset, and uses the first model and the first low-rank adaptation model to obtain compressed CSI.

[0213] For example, the terminal selects a first low-rank adaptive model associated with the scenario of measuring CSI-RS to compress the CSI.

[0214] It is understandable that using the first model and the first low-rank adaptive model to compress CSI includes: combining the first model and the first low-rank adaptive model set to compress CSI.

[0215] In some implementations, the communication method of this application embodiment further includes: the terminal sending fifth information to the access network device, the fifth information indicating the processing result obtained based on the first model and the first low-rank adaptive model. Accordingly, the access network device receives the fifth information and performs corresponding processing.

[0216] In some implementations, the fifth piece of information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model. Specifically, including the processing result in the fifth piece of information allows the access network device to directly obtain the processing result; including the identifier of the first model in the fifth piece of information allows the access network device to know which model produced the processing result; and including the identifier of the first low-rank adaptive model in the fifth piece of information allows the access network device to know which scenario the processing result belongs to based on the mapping relationship between the first low-rank adaptive model and the scenario, thereby facilitating subsequent corresponding operations.

[0217] Taking the first model for compressing CSI as an example, as shown in Figure 10, the communication method of this application embodiment further includes: S970 and S980.

[0218] S970, the terminal sends the fifth information to the access network device, the fifth information indicating compressed CSI. Accordingly, the access network device receives the fifth information.

[0219] S980, the access network device uses the second model corresponding to the first model and the second low-rank adaptive model corresponding to the first low-rank adaptive model to decompress the compressed CSI. The second model is used to decompress the CSI, and the second low-rank adaptive model is a low-rank adaptive structure obtained by low-rank adaptation optimization of the second model using training data from a specific scenario. This specific scenario has the same characteristic scenario associated with the first low-rank adaptive model.

[0220] This is understandable, because the first training dataset is indeed a training dataset corresponding to a specific scenario. That is, there is a correlation between the first training dataset and the specific scenario, so the specific scenario can be known based on the first training dataset.

[0221] It is understandable that in some implementations, the first and second information are carried in the same message to improve the training efficiency of the first low-rank adaptation model.

[0222] Figure 11 is a schematic flowchart of a communication method according to an embodiment of this application. This communication method includes steps S1110 and S1120. The communication method is executed by an access network device and a terminal. As an example, the access network device is any of the aforementioned communication systems. As an example, the terminal is any of the aforementioned communication systems.

[0223] It is understood that the access network device in the embodiments of this application can be replaced by a device within the access network device (e.g., a module, a communication module, a circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or it can be a logical node, logical module, or software that can implement all or part of the functions of the access network device.

[0224] It is understood that the terminal in the embodiments of this application can be replaced by a device within the terminal (e.g., a module, a communication module, a circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), a chip system, or a processor), or it can be a logical node, logical module, or software that can implement all or part of the terminal functions.

[0225] S1110, the access network device sends the first model to the terminal. Correspondingly, the terminal receives the first model.

[0226] This step can be referred to in S910, and will not be repeated here.

[0227] S1120, the access network device sends fourth information to the terminal, the fourth information indicating the first low-rank adaptive model associated with the first model. Accordingly, the terminal receives the fourth information.

[0228] As an example, the access network device trains a first low-rank adaptive model based on a first training dataset and a first model.

[0229] The method by which the access network device trains the first low-rank adaptive model based on the first training dataset and the first model can be referred to in S920, whereby the terminal trains the first low-rank adaptive model based on the first training dataset and the first model. It will not be repeated here.

[0230] In this embodiment, the fourth information indicates the first low-rank adaptation model, including: the fourth information contains the parameters of the first low-rank adaptation model.

[0231] As an example, the parameters of the first low-rank adaptive model include: model structure, neuron weights, activation parameters, etc.

[0232] In some implementations, the fourth information also includes: the identifier of the first model, and the identifier of the first low-rank adaptive model.

[0233] The fourth information contains the identifiers of the first model and the first low-rank adaptive model. For details, please refer to the information in S920 that the first information carries the identifiers of the first model and the first low-rank adaptive model. It will not be repeated here.

[0234] In some implementations, the fourth information also carries indication information for a specific scenario corresponding to the first low-rank adaptation model.

[0235] After receiving the fourth information, the terminal stores the first low-rank adaptation model, as well as the mapping relationship between the first low-rank adaptation model, the first model, and the specific scenario.

[0236] The technical effects of the embodiments in this application are similar to those of the embodiments shown in FIG9, and will not be repeated here. Furthermore, in the embodiments of this application, the access network device directly sends the trained first low-rank adaptation model to the terminal. Compared to the method of training by the terminal in the embodiment shown in FIG9, this reduces the need for terminal devices and saves terminal resources; in scenarios where terminal resources are limited, it can improve the training efficiency of the first low-rank adaptation model.

[0237] In some implementations, the communication method of this application embodiment further includes: the terminal using a first model and a first low-rank adaptation model to process data collected in a specific scene to obtain a processing result. It can be understood that the specific scene here is the same as the scene corresponding to the training dataset used to train the first low-rank adaptation model.

[0238] Taking the first model for compressing CSI as an example, as shown in Figure 12, the communication method of this application embodiment further includes: S1130 and S1140.

[0239] S1130, the access network device sends CSI-RS to the terminal. The terminal then measures the CSI-RS to obtain the CSI.

[0240] This step can be referenced from S950.

[0241] S1140, the terminal compresses the CSI based on the scenario of the measured CSI-RS as the scenario corresponding to the first training dataset, using the first model and the first low-rank adaptation model to obtain compressed CSI.

[0242] This step can be referenced from S960.

[0243] In some implementations, the communication method of this application embodiment further includes: the terminal sending fifth information to the access network device, the fifth information indicating the processing result obtained based on the first model and the first low-rank adaptive model. Accordingly, the access network device receives the fifth information and performs corresponding processing.

[0244] Taking the first model for compressing CSI as an example, as shown in Figure 12, the communication method of this application embodiment further includes: S1150 and S1160.

[0245] S1150, the terminal sends the fifth information to the access network device, the fifth information indicating compressed CSI. Accordingly, the access network device receives the fifth information.

[0246] This step can be referenced from S970.

[0247] S1160, the access network device uses the second model corresponding to the first model and the second low-rank adaptive model corresponding to the first low-rank adaptive model to decompress the compressed CSI.

[0248] This step can be referenced from S980.

[0249] It is understood that in the above method embodiments, the operations performed by the terminal can also be performed by other devices, such as by the host or cloud server of the over-the-top (OTT) system.

[0250] It is understood that in the above method embodiments, the operations performed by the access network device can also be performed by other devices, such as devices collectively referred to as intelligent network elements, such as near real-time RICs (near real-time RICs are set in RAN nodes, for example, in CU / DU).

[0251] The following description, using the example shown in Figure 10 where the terminal device's operation is performed by an OTT and the access network device's operation is performed by an intelligent network element, is presented in conjunction with Figure 13.

[0252] S1301, the intelligent network element sends the first model to the access network device. Correspondingly, the access network device receives the first model.

[0253] The details of this step can be found in S910.

[0254] S1302, the access network device sends the first model to the terminal. Correspondingly, the terminal receives the first model.

[0255] It is understandable that the access network device forwards or transmits the first model to the terminal.

[0256] S1303, the terminal sends the first model to the OTT. Correspondingly, the OTT receives the first model.

[0257] S1304, the intelligent network element sends first information to the access network device, the first information being used to instruct the training of a first low-rank adaptive model based on a first training dataset and a first model. Correspondingly, the access network device receives the first information.

[0258] This step can be referenced from S920.

[0259] S1305, the access network device sends the first information to the terminal. Correspondingly, the terminal receives the first information.

[0260] It is understandable that the access network device forwards or transmits the first information to the terminal.

[0261] S1306, the terminal sends the first information to the OTT. Correspondingly, the OTT receives the first information.

[0262] S1307, OTT uses the first training dataset to perform low-rank adaptation tuning on the first model, resulting in the first low-rank adaptation model.

[0263] S1308, the OTT sends third information to the terminal, which indicates whether the first low-rank adaptation model meets the performance indicators. Accordingly, the terminal receives the third information.

[0264] S1309, the terminal sends third information to the access network device. Correspondingly, the access network device receives the third information.

[0265] S1310, the access network device sends third information to the intelligent network element. Correspondingly, the intelligent network element receives the third information.

[0266] S1311, the access network device sends CSI-RS to the terminal. The terminal then measures the CSI-RS to obtain the CSI.

[0267] S1312, the terminal sends a CSI to the OTT. Correspondingly, the OTT receives the CSI.

[0268] S1313, OTT uses the first model and the first low-rank adaptive model to compress CSI, resulting in compressed CSI.

[0269] S1314, the OTT sends the fifth information to the terminal, which indicates compressed CSI. Correspondingly, the access network device receives the fifth information.

[0270] S1315, the terminal sends the fifth information to the access network device. Correspondingly, the access network device receives the fifth information.

[0271] S1316, the access network device sends the fifth information to the intelligent network element. Correspondingly, the intelligent network element receives the fifth information.

[0272] S1317, the intelligent network element uses the second model corresponding to the first model and the second low-rank adaptive model corresponding to the first low-rank adaptive model to decompress the compressed CSI.

[0273] Figures 14 and 15 are schematic diagrams of the communication devices according to embodiments of this application. These communication devices can be used to implement the functions of the terminal or access network equipment in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0274] As an example, this communication device may be an access network device, or it may be a device within an access network device (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), chip system or processor), or it may be a logical node, logical module or software that can implement all or part of the functions of the access network device.

[0275] As an example, this communication device may be a terminal, or a device within the terminal (e.g., a module, communication module, circuit or chip responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), chip system or processor), or a logical node, logical module or software that can implement all or part of the terminal functions.

[0276] As shown in Figure 14, the communication device 1400 includes a processing unit 1410 and a transceiver unit 1420. The communication device 1400 is used to implement the functions of a terminal or access network device in any of the above method embodiments.

[0277] As an example, when the communication device 1400 is used for the function of the access network device in any of the foregoing method embodiments, the processing unit 1410 is used to obtain one or more of the first model, the second model, the first training dataset, the second low-rank adaptation model, and the performance index; the transceiver unit 1420 is used to send the first information, the second information, or the fourth information, and to receive the third information and the fifth information.

[0278] As an example, when the communication device 1400 is used to implement the terminal function in any of the aforementioned method embodiments, the transceiver unit 1420 is used to receive first information, second information, or fourth information, and to send third information and fifth information; the processing unit 1410 is used to obtain a first low-rank adaptation model and process the data based on the first low-rank adaptation model and the first model.

[0279] For a more detailed description of the operations performed by the processing unit 1410 and the transceiver unit 1420, please refer to the relevant descriptions in the foregoing method embodiments.

[0280] As shown in Figure 15, the communication device 1500 includes a processor 1510 and an interface circuit 1520. The processor 1510 and the interface circuit 1520 are coupled to each other. It is understood that the interface circuit 1520 can be a transceiver or an input / output interface. Optionally, the communication device 1500 may also include a memory 1530 for storing instructions executed by the processor 1510, or storing input data required by the processor 1510 to execute instructions, or storing data generated after the processor 1510 executes instructions. Sometimes, the interface circuit 1520 can also be understood as part of the processor 1510, in which case the communication device 1500 includes the processor 1510.

[0281] As an example, when the communication device 1500 is used to implement any of the aforementioned methods, the processor 1510 is used to implement the functions of the processing unit 1410, and the interface circuit 1520 is used to implement the functions of the transceiver unit 1420.

[0282] As an example, when the aforementioned communication device is a chip used in a communication equipment, the chip receiving information can be understood as the information being first received by other modules (such as an RF module or antenna) in the communication equipment, and then sent to the chip by these modules. Similarly, the chip sending information can be understood as the information being first sent to other modules (such as an RF module or antenna) in the communication equipment, and then sent by these modules.

[0283] Some embodiments of this application also provide a computer program product that, when run on a processor, can implement the methods implemented by the terminal in any of the above embodiments.

[0284] Some embodiments of this application also provide a computer program product that, when run on a processor, can implement the methods implemented by the access network device in any of the above embodiments.

[0285] In some embodiments of this application, a computer-readable storage medium is also provided, which contains computer instructions that, when executed on a processor, can implement the methods implemented by the terminal in any of the above embodiments.

[0286] In some embodiments of this application, a computer-readable storage medium is also provided, which contains computer instructions that, when executed on a processor, can implement the methods implemented by the access network device in any of the above embodiments.

[0287] In some embodiments of this application, a communication system is also provided, which can implement the methods implemented by the terminal and access network equipment in any of the above method embodiments.

[0288] It is understood that the processor in the embodiments of this application can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0289] In this embodiment of the application, the processor may include one or more of the following: a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), an artificial intelligence processor (AI processor), or a neural processing unit (NPU).

[0290] In this application embodiment, the memory may include, but is not limited to, cache, read-only memory (ROM), random access memory (RAM), synchronous dynamic random access memory (SDRAM), hard disk drive (HDD) or solid-state drive (SSD), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), etc. Memory is any other medium capable of carrying or storing desired program code having an instruction or data structure form and accessible by a computer, but is not limited thereto. The memory in this application embodiment may also be a circuit or any other device capable of implementing storage functions for storing computer programs or instructions, and / or data.

[0291] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, optical discs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and the storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the ASIC can reside in a base station or terminal. The processor and the storage medium can also exist as discrete components in the base station or terminal.

[0292] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0293] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

Claims

1. A communication method, characterized in that, The method includes: Send the first model to the terminal; Send a first message to the terminal, the first message being used to instruct the training of a first low-rank adaptive model based on a first training dataset and the first model, the first low-rank adaptive model being associated with the first model.

2. The method according to claim 1, characterized in that, The first model is used to perform at least one of the following processes on the channel state information: prediction, compression, or quantization.

3. The method according to claim 1 or 2, characterized in that, The first information includes at least one of the following: the first training dataset, the identifier of the first model, and the identifier of the first low-rank adaptive model.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Send a second message to the terminal, the second message being used to indicate the performance metrics of the first low-rank adaptive model.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: The system receives third information from the terminal, which indicates whether the first low-rank adaptation model meets the performance metrics.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes receiving fifth information from the terminal, the fifth information being used to indicate the processing result obtained based on the first model and the first low-rank adaptation model.

7. The method according to claim 6, characterized in that, The fifth piece of information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

8. A communication method, characterized in that, The method includes: Send the first model to the terminal; A fourth message is sent to the terminal, the fourth message being used to indicate a first low-rank adaptive model associated with the first model.

9. The method according to claim 8, characterized in that, The first model is used to perform at least one of the following processes on the channel state information: prediction, compression, or quantization.

10. The method according to claim 8 or 9, characterized in that, The fourth information includes: the identifier of the first model, and the identifier of the first low-rank adaptive model.

11. The method according to any one of claims 8 to 10, characterized in that, The method further includes: The terminal receives fifth information, which indicates the processing result obtained based on the first model and the first low-rank adaptive model.

12. The method according to claim 11, characterized in that, The fifth piece of information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

13. A communication method, characterized in that, The method includes: Receive the first model from the access network device; Receive first information from the access network device, the first information being used to instruct the training of a first low-rank adaptive model based on the first training dataset and the first model, the first low-rank adaptive model being associated with the first model; Based on the first information, the first model is optimized for low-rank adaptation to obtain a model that is compatible with the first low-rank adaptation model.

14. The method according to claim 13, characterized in that, The first information includes: the first training dataset, the identifier of the first model, and the identifier of the first low-rank adaptive model.

15. The method according to claim 13 or 14, characterized in that, The method further includes: The system receives second information from the access network device, the second information being used to indicate the performance metrics of the first low-rank adaptation model.

16. The method according to any one of claims 13 to 15, characterized in that, The method further includes: A third message is sent to the access network device, the third message being used to indicate whether the first low-rank adaptation model meets the performance indicators.

17. The method according to any one of claims 13 to 16, further comprising: Receive fifth information from the terminal, which indicates the processing result obtained based on the first model and the first low-rank adaptive model.

18. The method according to claim 17, characterized in that, The fifth piece of information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

19. The method according to any one of claims 13 to 18, characterized in that, The first model is used to perform at least one of the following processes on the channel state information: prediction, compression, or quantization.

20. A communication method, characterized in that, The method includes: Receive the first model from the access network device; The system receives fourth information from the access network device, the fourth information indicating a first low-rank adaptive model associated with the first model.

21. The method according to claim 20, characterized in that, The fourth information includes: the identifier of the first model, and the identifier of the first low-rank adaptive model.

22. The method according to claim 20 or 21, characterized in that, The method further includes: A fifth message is sent to the access network device, the fifth message indicating the processing result obtained based on the first model and the first low-rank adaptive model.

23. The method according to claim 22, characterized in that, The fifth piece of information includes: the identifier of the first model, the processing result obtained based on the first model and the first low-rank adaptive model, and the identifier of the first low-rank adaptive model.

24. The method according to any one of claims 20 to 23, characterized in that, The first model is used to perform at least one of the following processes on the channel state information (CSI): prediction, compression, or quantization.

25. A communication device, characterized in that, include: A processor coupled to a memory for storing a computer program, wherein when the processor invokes the computer program, the communication device performs the method of any one of claims 1 to 24.

26. A computer-readable storage medium, characterized in that, Used to store a computer program, the computer program including instructions for implementing the method as described in any one of claims 1 to 24.

27. A computer program product, the computer program product comprising instructions, characterized in that, When the instructions are executed on a computer, the computer causes the computer to perform the method as described in any one of claims 1 to 24.

28. A chip or chip system, characterized in that, The chip or chip system includes a processor coupled to a memory for storing programs or instructions that, when executed by the processor, cause the processor to implement the method as described in any one of claims 1 to 24.

Images