Model training method and device, communication equipment and computer readable storage medium

Abstract

The invention discloses a model training method and device and communication equipment, and the method comprises the steps that network equipment trains a first model based on a first data set, the first model comprises a first part and a second part, a second data set is sent to terminal equipment, the first data set comprises M first samples, and M is a positive integer; the second data set comprises N second samples, the N second samples are obtained by processing the N first samples through the first part of the first model, and M and N are positive integers; wherein the second data set is used for the terminal device to train a second model, and the trained second model and a second part of the first model are used for CSI reporting.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a model training method and apparatus, communication equipment, and computer-readable storage medium. Background Art

[0002] Introducing artificial intelligence (AI) in the radio access network (RAN) can improve the performance of the wireless air interface. A typical application is AI-based channel state information (CSI) feedback.

[0003] AI-based CSI feedback can be implemented using an AI model (can be referred to as a model for short). In some scenarios, a pair of AI models need to be deployed on the terminal device side and the network device side, respectively, which is called a two-sided AI model. The terminal device and the network device implement CSI feedback through their respective AI models. At present, there is a lack of a complete technical solution for how to train a pair of AI models for CSI feedback. Summary of the invention

[0004] Embodiments of the present application provide a model training method and apparatus, communication equipment, chip, and computer-readable storage medium.

[0005] The model training method provided in the embodiment of the present application includes:

[0006] The network device trains a first model based on a first data set, the first model includes a first part and a second part, and sends a second data set to a terminal device, the first data set includes M first samples, the second data set includes N second samples, the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers;

[0007] The second data set is used for training a second model for the terminal device, and the trained second model and the second part of the first model are used for CSI reporting.

[0008] The model training method provided in the embodiment of the present application includes:

[0009] The terminal device trains a third model based on the fifth data set, the third model includes a first part and a second part, and sends a sixth data set to the network device, the fifth data set includes M first samples, the sixth data set includes N first samples and N second samples, the N second samples are obtained by processing the N first samples by the first part of the third model, and M and N are positive integers;

[0010] The sixth data set is used by the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

[0011] The model training device provided in the embodiment of the present application is applied to a network device, and the device includes:

[0012] A training unit, configured to train a first model based on a first data set, wherein the first model includes a first part and a second part;

[0013] a sending unit, configured to send a second data set to a terminal device, wherein the first data set includes M first samples, and the second data set includes N second samples, wherein the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers;

[0014] The second data set is used for training a second model for the terminal device, and the trained second model and the second part of the first model are used for CSI reporting.

[0015] The model training device provided in the embodiment of the present application is applied to a terminal device, and the device includes:

[0016] A training unit, configured to train a third model based on a fifth data set, wherein the third model includes a first part and a second part;

[0017] a sending unit, configured to send a sixth data set to a network device, wherein the fifth data set includes M first samples, and the sixth data set includes N first samples and N second samples, wherein the N second samples are obtained by processing the N first samples by the first part of the third model, and M and N are positive integers;

[0018] The sixth data set is used by the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

[0019] The communication device provided in an embodiment of the present application includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute any one of the above-mentioned model training methods.

[0020] The chip provided in the embodiment of the present application includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes any one of the above methods.

[0021] The computer-readable storage medium provided in the embodiments of the present application is used to store a computer program, and the computer program enables a computer to execute any one of the above methods.

[0022] In the above technical solution of the embodiment of the present application, the network device initiates model training, specifically, the network device trains the first model based on the first data set, and the network device sends the second data set to the terminal device, so that the terminal device trains the second model based on the second data set, and the trained second model and the second part of the first model (which can be understood as a pair of AI models) are used for CSI reporting, thus clarifying the training method of a pair of AI models for CSI reporting. Alternatively, the terminal device initiates model training, specifically, the terminal device trains the third model based on the fifth data set, and the terminal device sends the sixth data set to the network device, so that the network device trains the fourth model based on the sixth data set, and the trained fourth model and the first part of the third model (which can be understood as a pair of AI models) are used for CSI reporting, thus clarifying the training method of a pair of AI models for CSI reporting. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of an application scenario of an embodiment of the present application;

[0024] Figure 2 This is a schematic diagram of AI-based CSI feedback;

[0025] Figure 3 This is a schematic diagram of independently training an AI model;

[0026] Figure 4 This is a flow chart of the model training method provided in the embodiment of the present application. Figure 1 ;

[0027] Figure 5 This is a flow chart of the model training method provided in the embodiment of the present application. Figure 2 ;

[0028] Figure 6 This is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. Figure 1 ;

[0029] Figure 7 This is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. Figure 2 ;

[0030] Figure 8 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0031] Fig. 9 It is a schematic structural diagram of the chip of an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] Figure 1 It is a schematic diagram of an application scenario of an embodiment of the present application.

[0034] like Figure 1 As shown, the communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0035] It should be understood that the embodiments of the present application are only exemplified by the communication system 100, but the embodiments of the present application are not limited thereto. That is to say, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: 5G communication system (also known as New Radio (NR) communication system), or future communication systems, etc.

[0036] exist Figure 1 In the communication system 100 shown, the network device 120 may be an access network device that communicates with the terminal device 110. The access network device may provide communication coverage for a specific geographical area, and may communicate with the terminal device 110 (eg, UE) located in the coverage area.

[0037] The network device 120 may be a base station (gNB) in an NR system, or a network device in a future evolved public land mobile network (PLMN), etc.

[0038] The terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wireless connection.

[0039] For example, the terminal device 110 may refer to an access terminal, a user equipment (UE), a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user device. The access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolution network, etc.

[0040] Figure 1 One base station and two terminal devices are shown exemplarily. Optionally, the wireless communication system 100 may include multiple base station devices and each base station may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0041] It should be noted that Figure 1It is only to illustrate the system to which the present application is applicable in the form of an example. Of course, the method shown in the embodiment of the present application can also be applied to other systems. In addition, the terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. It should also be understood that the "indication" mentioned in the embodiment of the present application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, B can be obtained through C; it can also mean that there is an association relationship between A and B. It should also be understood that the "correspondence" mentioned in the embodiment of the present application can mean that there is a direct or indirect correspondence relationship between the two, or it can mean that there is an association relationship between the two, or it can mean that there is an indication and being indicated, configuration and being configured, etc. It should also be understood that the "predefined" or "predefined rules" mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices), and the present application does not limit its specific implementation method. For example, predefined may refer to the definition in the protocol. It should also be understood that in the embodiments of the present application, the "protocol" may refer to a standard protocol in the field of communications, such as the NR protocol and related protocols used in future communication systems, which is not limited in the present application.

[0042] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0043] Traditional CSI feedback based on codebooks (such as Type-I / Type-II / e-Type-II codebooks) has problems such as limited feedback accuracy or large feedback overhead. AI-based CSI feedback can effectively solve these problems of traditional solutions. The AI-based CSI feedback process is as follows: the terminal device inputs the channel information obtained by CSI measurement into the model on the terminal device side, processes the channel information through the model to obtain CSI quantization bits; the terminal device sends the CSI quantization bits to the network device. After receiving the CSI quantization bits, the network device inputs the CSI quantization bits into the model on the network device side, and recovers the corresponding channel information from the CSI quantization bits through the model. Among them, the channel information includes eigenvectors, beam information, delay information, etc.

[0044] Figure 2 The schematic diagram of AI-based CSI feedback is shown, and feature vector feedback is used as an example for explanation. The AI ​​model deployed on the terminal device side includes an encoding (encoder) module and a quantization (Quantization) module, and the AI ​​model deployed on the network device side includes a dequantization (Dequantization) module and a decoding (Decoder) module. The AI-based feature vector feedback process is as follows: the encoding module and the quantization module on the terminal device side compress and quantize the feature vectors of k (k ≥ 1) subbands respectively, and feed back the quantized bits (i.e., the quantized bits of the feature vector) to the network device. After the network device receives the bits fed back by the terminal device, it dequantizes and decompresses them through the dequantization module and the decoding module respectively, thereby recovering the feature vectors of the k subbands.

[0045] In the above AI-based CSI feedback process, a pair of AI models need to be deployed on the terminal device side and the network device side respectively, which can be called a two-sided AI model. In actual model deployment, there are three ways to implement the training of a pair of AI models.

[0046] (1) The network device side trains a pair of AI models (including CSI generation part and CSI recovery part) and sends the CSI generation part to the terminal device. This method can be called the training method initiated by the network device. Alternatively, the terminal device side trains a pair of AI models (including CSI generation part and CSI recovery part) and sends the CSI recovery part to the network device. This method can be called the training method initiated by the terminal device.

[0047] (2) The network device side and the terminal device side jointly train a pair of AI models (including a CSI generation part and a CSI recovery part), where the CSI generation part is deployed on the terminal device side and the CSI recovery part is deployed on the network device side.

[0048] (3) The network device side and the terminal device side each train their own AI models. The terminal device side trains the CSI generation part, and the network device side trains the CSI recovery part. The CSI generation part is deployed on the terminal device side, and the CSI recovery part is deployed on the network device side.

[0049] It should be noted that the CSI generation part above represents the AI ​​model on the terminal device side of a pair of AI models, which may actually include an encoder module and a quantization module. The CSI recovery part above represents the AI ​​model on the network device side of a pair of AI models, which may actually include a dequantization module and a decoder module.

[0050] In the above method (1), it is necessary to transmit the model between the network device and the terminal device. The model transmitted by the network device to the terminal device may not match the model supported by the terminal device, or the model transmitted by the terminal device to the network device may not match the model supported by the network device.

[0051] In the above method (2), a forward propagation process and a backward propagation process need to be performed between the network device and the terminal device, resulting in a large air interface overhead.

[0052] In the above method (3), it is necessary to ensure that the models trained on the network device side and the terminal device side can be used together and meet the performance requirements.

[0053] In some technical solutions, improvements can be made based on the above method (3). Taking the training method initiated by the network device as an example, a potential training method is: after the network device trains the CSI generation part 1 and the CSI recovery part (i.e., a pair of AI models) based on the data set A, the data set B is sent to the terminal device. The data set B includes N (N≥1) first samples and N second samples obtained after the N first samples are processed by the CSI generation part. The terminal device trains the CSI generation part 2 based on the received data set B to ensure that it can be used in conjunction with the CSI recovery part on the network device side. Figure 3 , the process of training their own AI models on the network device side and the terminal device side is as follows:

[0054] ① Train the CSI generation part 1 and the CSI recovery part (i.e., a pair of AI models) on the network equipment side, where the input of the CSI generation part 1 is Vin (i.e., data set A), the output of the CSI generation part 1 is Vq, the input of the CSI recovery part is Vq, and the output of the CSI recovery part is Vout.

[0055] ② The network device sends data set B (including N first samples and N second samples after the N first samples pass through the CSI generation part on the network device side) to the terminal device.

[0056] ③ The terminal device trains CSI generation part 2, wherein the input of CSI generation part 2 is Vin, the output of CSI generation part 2 is Vq, and the terminal device trains CSI generation part 2 based on data set B.

[0057] ④ Combine the CSI recovery part obtained by training on the network device side and the CSI generation part 2 obtained by training on the terminal device side as a pair of AI models for CSI feedback.

[0058] Assuming that the CSI recovery part on the network device side adopts the transformer model structure, the simulation results on the terminal device side under different sample numbers of data sets B and using different model structures are shown in the following Table 1. Here, the square of generalized cosine similarity (SGCS) of channel information is used as the simulation result for illustration. Among them, Case 1 is a case of joint training, that is, the network device trains a pair of AI models (including CSI generation part 1 and CSI recovery part); Case 2 is a case of independent training, that is, the terminal device side trains CSI generation part 2 (using the Transformer model structure), and the network device side trains the CSI recovery part (using the Transformer model structure); Case 3 is another case of independent training, that is, the terminal device side trains CSI generation part 3 (using the EVCsiNet model structure), and the network device side trains the CSI recovery part (using the Transformer model structure); Case 4 is another case of independent training, that is, the terminal device side trains CSI generation part 4 (using the MLP-Mixer model structure), and the network device side trains the CSI recovery part (using the Transformer model structure).

[0059]

[0060] Table 1

[0061] It should be noted that in Table 1, for the sake of simplicity, the CSI generation part is described as encoder, and the CSI recovery part is described as decoder. In Case 1, encoder1 and decoder are models trained on the network device side based on training data set A and using the transformer model structure. In Case 2, encoder2 is a model trained on the terminal device side based on data set B and using the Transfomer model structure. In Case 3, encoder3 is a model trained on the terminal device side based on data set B and using the EVCsiNet model structure. In Case 4, encoder4 is a model trained on the terminal device side based on data set B and using the MLP-Mixer model structure. Among them, Case 2, Case 3, and Case 4 all assume that the terminal device side and the network device side use the same quantization / dequantization method.

[0062] From the above simulation results, in order to realize model training, the terminal device needs to obtain data set B. Furthermore, the terminal device also needs to obtain information about the quantization method and basic model structure adopted by the network device.

[0063] In some technical solutions, training can also be initiated by the terminal device. The way in which the terminal device initiates training is similar to the way in which the network device initiates training. A potential training method is: after the terminal device trains the CSI generation part and the CSI recovery part 1 (i.e., a pair of AI models) based on the data set A, it sends the data set B to the network device. The data set B includes M (M≥1) first samples and M second samples obtained after the M second samples are processed by the CSI generation part. The network device trains the CSI recovery part 2 based on the received data set B to ensure that it can be used in conjunction with the CSI generation part on the terminal device side.

[0064] In addition, after the CSI generation part and the CSI recovery part are trained and deployed on the terminal device and network device side respectively, when the scenario or configuration of the terminal device or network device changes, such as the terminal device switches to another cell, or the number of transmit antennas or subbands configured in the network device changes, the originally deployed model may not be suitable for the new scenario. Therefore, the originally deployed model needs to be updated or fine-tuned.

[0065] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0066] It should be noted that the "CSI reporting" described in the embodiments of the present application may also be described as "CSI feedback". Specifically, the "CSI feedback" refers to AI-based CSI feedback. The process of AI-based CSI feedback may refer to the aforementioned related description.

[0067] Figure 4 This is a flow chart of the model training method provided in the embodiment of the present application. Figure 1 ,like Figure 4 As shown, the model training method includes:

[0068] Step 401: The network device trains a first model based on a first data set, where the first model includes a first part and a second part, and sends a second data set to a terminal device, where the first data set includes M first samples, and the second data set includes N second samples, where the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers; wherein the second data set is used for the terminal device to train a second model, and the trained second model and the second part of the first model are used for CSI reporting.

[0069] In the embodiment of the present application, the network device side is responsible for training the first model, and the terminal device side is responsible for training the second model. The first model includes a first part and a second part, and the trained second model and the second part of the first model are used for CSI reporting. The second part of the first model and the second model can be understood as a pair of AI models for CSI reporting, that is, a two-sided AI model.

[0070] In some implementations, the first part of the first model is a CSI generation part (CSI generation part), and the second part of the first model is a CSI reconstruction part (CSI reconstruction part).

[0071] In some embodiments, the second model is a CSI generation part. In order to distinguish the CSI generation part in the first model from the CSI generation part in the second model, the CSI generation part in the first model can be called CSI generation part 1, and the CSI generation part in the second model can be called CSI generation part 2.

[0072] It should be noted that the CSI generation part 2 represents the AI ​​model on the terminal device side in a pair of AI models, which may actually include a coding module and a quantization module. The CSI recovery part represents the AI ​​model on the network device side in a pair of AI models, which may actually include a dequantization module and a decoding module. The functions of the coding module, quantization module, dequantization module and decoding module can refer to the above-mentioned related description.

[0073] In the embodiment of the present application, the network device trains the first model based on the first data set, and the terminal device trains the second model based on the second data set. The first data set can also be described as data set A, and the second data set can also be described as data set B, which is not limited in the present application.

[0074] In the embodiment of the present application, the first data set includes M first samples, where M is a positive integer, and the first sample is a channel information sample (also referred to as a channel sample). The terminal device performs CSI measurement to obtain channel information, and reports the measured channel information to the network device, so that the network device can obtain the channel information and use the channel information as a sample for training the first model (i.e., a channel information sample).

[0075] In some implementations, the network device may obtain M first samples from one terminal device, that is, the M first samples are obtained by performing CSI measurement on one terminal device. In other implementations, the network device may obtain M first samples from multiple terminal devices, that is, the M first samples are obtained by performing CSI measurement on multiple terminal devices.

[0076] After the network device obtains the M first samples, it trains the first model based on the M first samples, that is, trains the first part and the second part of the first model. For example, the network device trains the CSI generation part 1 and the CSI recovery part based on the M first samples.

[0077] In the embodiment of the present application, the second data set includes N second samples, where N is a positive integer, and the N second samples are obtained by processing the N first samples through the first part of the first model. Here, the N second samples are obtained by processing the N first samples through the first part of the first model, which specifically means that the N second samples are obtained by processing the N first samples through the first part of the trained first model.

[0078] In some embodiments, the N first samples are identical to the M first samples. In other embodiments, the N first samples are partially identical to the M first samples. In other embodiments, the N first samples are completely different from the M first samples.

[0079] The network device inputs N first samples into the first model, and obtains N second samples after the first part of the first model is processed. The second sample is a quantized bit sample corresponding to the channel information. The N second samples constitute a second data set, and the network device sends the second data set to the terminal device for the terminal device to train the second model. The format of the second data set is described below.

[0080] Solution 1

[0081] In some embodiments, the second data set includes N first samples and N second samples, where the N second samples are obtained by processing the N first samples with the first part of the first model.

[0082] Here, the second data set has a first format; in the first format, the second data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indexes.

[0083] For example, the arrangement of the N groups of data in the second data set may be {datasample1, datasample1 ′ ,datasample2,datasample2 ′ ,datasample3,datasample3 ′ ,…,datasampleN,datasampleN ′}, where datasample1, datasample1 ′ For the first set of data, datasample2, datasample2′ is the second set of data, and so on. datasample1 represents the first sample with sample index 1, datasample1 ′ represents the second sample obtained by processing datasample1 with the first part of the first model, datasample2 represents the first sample with sample index 2, datasample2 ′ Represents the second sample obtained by processing datasample2 with the first part of the first model, and so on.

[0084] For example, the arrangement of the N groups of data in the second data set may be {data1, data2, data3, ..., dataN}, where data1 = {datasample1, datasample1 ′}, data2={datasample2, datasample2 ′}, and so on. data1 is the first set of data, data2 is the second set of data, and so on. datasample1 represents the first sample with sample index 1, datasample1 ′ represents the second sample obtained by processing datasample1 with the first part of the first model, datasample2 represents the first sample with sample index 2, datasample2 ′ Represents the second sample obtained by processing datasample2 with the first part of the first model, and so on.

[0085] For Option 1, it can be applied to at least the following situations:

[0086] 1) The M first samples are measured by the above terminal device and other terminal devices, and the N first samples are all or part of the M first samples.

[0087] 2) The M first samples are all measured by the above-mentioned terminal device, and the N first samples are all or part of the M first samples.

[0088] 3) The M first samples are measured by the above terminal device and other terminal devices, and the N first samples are completely different from or partially different from the M first samples.

[0089] 4) The M first samples are all measured by the above-mentioned terminal device, and the N first samples are completely different from or partially different from the M first samples.

[0090] 5) N first samples are measured by the above terminal device and other terminal devices.

[0091] 6) N first samples are measured by the above terminal device.

[0092] Solution 2

[0093] In some embodiments, the second data set includes N second samples, where the N second samples are obtained by processing the N first samples with the first part of the first model.

[0094] Here, the second data set has a second format; in the second format, the second data set includes N second samples, and the N second samples are arranged according to sample indices.

[0095] For example, the arrangement of the N second samples in the second data set may be {datasample1 ′ ,datasample2 ′ ,datasample3 ′ ,…,datasampleN ′}, where datasample1 ′ represents the second sample obtained by processing datasample1 with the first part of the first model, datasample2 ′ represents the second sample obtained by processing datasample2 with the first part of the first model, and so on. datasample1 represents the first sample with sample index 1, datasample2 represents the first sample with sample index 2, and so on.

[0096] For Option 2, it can be applied to at least the following situations:

[0097] 1) The M first samples are all measured by the above-mentioned terminal device, and the N first samples are all or part of the M first samples.

[0098] 2) N first samples are obtained by measuring the above terminal device.

[0099] In some implementations, when the M first samples are all measured by the terminal device, and the N first samples are part of the M first samples, the network device sends first information to the terminal device, and the first information is used to indicate the sample index of the N second samples. Here, since the second sample corresponds to the first sample, the sample index of the second sample can be consistent with the sample index of the corresponding first sample. In this way, the terminal device can determine which samples of the M first samples the N first samples corresponding to the N second samples are based on the first information.

[0100] In some implementations, after the network device obtains the M first samples measured by the terminal device, considering that there are samples of low quality among the M first samples, only N first samples among the M first samples are used, and the second data set only includes N second samples corresponding to the N first samples. Here, there may be multiple criteria for determining samples of low quality, such as if some data statistical features of some samples are significantly different from the data statistical features of the majority of other samples, or if the data statistical features of some samples do not meet the requirements defined by the network device, then these samples may be considered as samples of low quality.

[0101] In some embodiments, the first information includes a first sample index list, and the first sample index list includes sample indices of N second samples.

[0102] Exemplarily, the value of the sample index in the first sample index list may be a relative index value in the M first samples, which may be obtained by bits to represent the value of the sample index, that is, the sample index occupies For example, if the N first samples are the 1st, 3rd, and 5th samples of the M first samples, then the first sample index list is {Index#1, Index#3, Index#5}, where Index#1 represents the sample index value of 1, Index#3 represents the sample index value of 3, and Index#5 represents the sample index value of 5.

[0103] In some other embodiments, the first information includes a first bitmap, each bit in the first bitmap corresponds to a sample index, and the value of the bit is used to indicate whether a second sample corresponding to the sample index corresponding to the bit is included in the second data set.

[0104] Exemplarily, the first bitmap is a bitmap of length M, in which, in order from low to high, the i-th (1≤i≤M) bit corresponds to the i-th sample in the M first samples, the value of the i-th bit is 1, indicating that the second sample corresponding to the i-th sample in the M first samples is included in the above-mentioned second data set, and the value of the i-th bit is 0, indicating that the second sample corresponding to the i-th sample in the M first samples is not included in the above-mentioned second data set.

[0105] Solution 3

[0106] In some embodiments, the second data set has a third format; in the third format, the second data set includes N groups of data, each group of the N groups of data includes a second sample, and each group of data in some of the N groups of data also includes a first sample corresponding to the second sample; wherein the N groups of data are arranged according to sample indexes.

[0107] Here, Solution 3 can be understood as a combination of Solution 1 and Solution 2, that is, in Solution 3, part of the data in the second data set has the first format, and another part of the data has the second format.

[0108] For example, the arrangement of the N groups of data in the second data set may be {data1, data2, data3, ..., dataN}, where data1 is the first group of data, data2 is the second group of data, and so on. Some of the N data include the first sample and the corresponding second sample. For example, data1 = {datasample1, datasample1 ′}, datasample1 represents the first sample with sample index 1, datasample1 ′ represents the second sample obtained by processing datasample1 by the first part of the first model. In addition, some of the N data include the second sample. For example, data2 = {datasample2 ′}, datasample2 ′ Represents the second sample obtained by processing datasample2 with the first part of the first model.

[0109] For Solution 3, if a sample among the N first samples is not measured by the terminal device, the second data set needs to include the sample and a second sample obtained by processing the sample by the first part of the first model. If a sample among the N first samples is measured by the terminal device, the second data set may only include the second sample obtained by processing the sample by the first part of the first model.

[0110] For Option 3, it can be applied to at least the following situations:

[0111] The N first samples are obtained by measuring the above terminal device and other terminal devices.

[0112] In some embodiments, P first samples among N first samples correspond to P second samples in the second data set, where P is an integer less than N, and when the second data set does not include the P first samples (e.g., when the P first samples are measured by the above-mentioned terminal device, the second data set may not include the P first samples), the network device sends second information to the terminal device, and the second information is used to indicate the sample index of the P second samples. Here, since the second sample corresponds to the first sample, the sample index of the second sample may be consistent with the sample index of the corresponding first sample. In this way, the terminal device can determine which samples among the N first samples the P first samples corresponding to the P second samples are based on the second information.

[0113] In some embodiments, the second information includes a second sample index list, where the second sample index list includes sample indices of P second samples.

[0114] Exemplarily, the value of the sample index in the second sample index list may be a relative index value in the N first samples, which may be obtained by bits to represent the value of the sample index, that is, the sample index occupies For example, if the P first samples are the 1st, 3rd, and 5th samples of the N first samples, then the second sample index list is {Index#1, Index#3, Index#5}, where Index#1 represents the sample index value of 1, Index#3 represents the sample index value of 3, and Index#5 represents the sample index value of 5.

[0115] In some other embodiments, the second information includes a second bitmap, each bit in the second bitmap corresponds to a sample index, and the value of the bit is used to indicate whether the second sample corresponding to the sample index corresponding to the bit is included in the second data set.

[0116] Exemplarily, the second bitmap is a bitmap of length N, in which, in order from low to high, the i-th (1≤i≤N) bit corresponds to the i-th sample in N first samples, the value of the i-th bit is 1, indicating that the second sample corresponding to the i-th sample in the N first samples is included in the above-mentioned second data set, and the value of the i-th bit is 0, indicating that the second sample corresponding to the i-th sample in the N first samples is not included in the above-mentioned second data set.

[0117] In some implementations, the network device sends third information to the terminal device, where the third information is used to indicate the quantization granularity of the quantization module in the first model.

[0118] In some implementations, the network device receives fourth information sent by the terminal device, and the fourth information is used to indicate the second model supported by the terminal device and / or the configuration information supported by the second model, and the configuration information includes at least one of the following: the number of antennas, the number of subbands, and the number of payloads required for CSI reporting. The network device can select an appropriate second data set based on the fourth information and send it to the terminal device. Here, the terminal device can report the second model supported by itself and / or the configuration information supported by the second model to the network device through UE capabilities.

[0119] Through the above scheme, it is possible to implement that the network device trains the first model based on the first data set, and the terminal device trains the second model based on the second data set, and the trained second model and the second part of the first model are used for CSI reporting. The second part of the first model and the second model can be understood as a pair of AI models for CSI reporting, that is, a bilateral AI model. After the bilateral AI model is deployed, when the configuration of the network device or the environment in which the terminal device is located changes, the network device and / or the terminal device detects that the performance of their respective models cannot meet the requirements, and a model update process can be initiated. The model update process is described below.

[0120] In some embodiments, the network device trains a first model based on a third data set, and sends a fourth data set to the terminal device, the third data set includes M' first samples, the fourth data set includes N' second samples, the N' second samples are N' first samples processed by the first part of the first model, and M' and N' are positive integers; wherein the fourth data set is used by the terminal device to determine the second model.

[0121] Here, the third data set can be understood as an updated data set of the first data set, and the fourth data set can be understood as an updated data set of the second data set. The third data set can also be described as data set A ′ , the fourth data set can also be described as data set B ′ , this application does not limit this.

[0122] Here, the specific implementation method of "the network device trains the first model based on the third data set and sends the fourth data set to the terminal device" is similar to the specific implementation method of "the network device trains the first model based on the first data set and sends the second data set to the terminal device", and can refer to the above description.

[0123] After the network device trains the first model based on the first data set, when the third data set is obtained, the network device can train again based on the third data set on the basis of the first model trained last time, thereby achieving the purpose of updating the first model. Similarly, after the terminal device trains the second model based on the second data set, when the fourth data set is obtained, the terminal device can train again based on the fourth data set on the basis of the second model trained last time (or fine-tune the model or update the model parameters), thereby achieving the purpose of updating the second model.

[0124] In some embodiments, the fourth data set in the above solution has an association relationship with at least one of the following: the second data set, the second model. The association relationship is characterized by at least one of the following:

[0125] The subordinate data set identifier of the fourth data set is equal to the identifier of the second data set;

[0126] The identifier of the fourth data set is equal to the identifier of the second data set;

[0127] The subordinate model identifier of the fourth data set is equal to the identifier of the second model.

[0128] In some implementations, the quantization granularity of the quantization module in the first model associated with the fourth data set in the above solution is equal to the quantization granularity of the quantization module in the first model associated with the second data set.

[0129] In the above scheme, the transmission method of the second data set can be but is not limited to: the network device sends the second data set to the terminal device through a semi-persistent scheduling (SPS) method. In specific implementation, the network device sends a first radio resource control (RRC) signaling to the terminal device, the first RRC signaling includes an SPS configuration, and the SPS configuration includes an identifier of the second data set; the network device sends a first activation signaling to the terminal device, the first activation signaling is used to activate the SPS configuration, and the SPS configuration is used for the terminal device to receive the second data set in an SPS manner.

[0130] In some implementations, the first activation signaling may be a Media Access Control-Control Element (MAC-CE).

[0131] In some embodiments, after activating the SPS configuration through the first activation signaling (which can also be understood as activating an SPS transmission), the network device can transmit one or more data sets, and can include the identifier of the second data set (such as the index of the second data set) in the SPS configuration to establish an association relationship between the SPS configuration and the second data set, so that the terminal device can know that the SPS configuration is used to transmit the second data set. After completing the transmission of the second data set, the SPS configuration can be deactivated through the first activation signaling.

[0132] It should be noted that the SPS mode belongs to a semi-static transmission mode. In order to distinguish the SPS transmission corresponding to the second data set from the ordinary SPS transmission, a new radio network temporary identifier (RNTI), such as D-RNTI, can be defined for the SPS transmission corresponding to the second data set, and the new RNTI is used to indicate that the SPS transmission is used to transmit the second data set.

[0133] During the model update process, the network device needs to send a fourth data set to the terminal device. The transmission method of the fourth data set is similar to the transmission method of the second data set. The transmission of the fourth data set can be implemented by referring to the transmission method of the second data set.

[0134] In the technical solution of the embodiment of the present application, the network device initiates model training. Specifically, the network device trains a first model based on a first data set, and the network device sends a second data set to a terminal device, so that the terminal device trains a second model based on the second data set. The trained second model and the second part of the first model (which can be understood as a pair of AI models) are used for CSI reporting. In this way, the training method of a pair of AI models used for CSI reporting is clarified.

[0135] Figure 5 This is a flow chart of the model training method provided in the embodiment of the present application. Figure 2 ,like Figure 5 As shown, the model training method includes:

[0136] Step 501: The terminal device trains a third model based on the fifth data set, the third model includes a first part and a second part, and sends a sixth data set to the network device, the fifth data set includes M first samples, the sixth data set includes N first samples and N second samples, the N second samples are N first samples processed by the first part of the third model, and M and N are positive integers; wherein the sixth data set is used for the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

[0137] In the embodiment of the present application, the terminal device side is responsible for training the third model, and the network device side is responsible for training the fourth model. The third model includes a first part and a second part, and the first part and the fourth model of the trained third model are used for CSI reporting. The first part and the fourth model of the third model can be understood as a pair of AI models for CSI reporting, that is, a bilateral AI model.

[0138] In some implementations, the first part of the third model is a CSI generation part (CSI generation part), and the second part of the third model is a CSI reconstruction part (CSI reconstruction part).

[0139] In some embodiments, the fourth model is a CSI recovery part. In order to distinguish the CSI recovery part in the third model from the CSI recovery part in the fourth model, the CSI recovery part in the third model may be referred to as CSI recovery part 1, and the CSI recovery part in the fourth model may be referred to as CSI recovery part 2.

[0140] It should be noted that the CSI generation part represents the AI ​​model on the terminal device side in a pair of AI models, which may actually include a coding module and a quantization module. The CSI recovery part 2 represents the AI ​​model on the network device side in a pair of AI models, which may actually include a dequantization module and a decoding module. The functions of the coding module, quantization module, dequantization module and decoding module can refer to the above-mentioned related description.

[0141] In the embodiment of the present application, the terminal device trains the third model based on the fifth data set, and the network device trains the fourth model based on the sixth data set. The third data set can also be described as data set A, and the sixth data set can also be described as data set B, which is not limited in the present application.

[0142] In the embodiment of the present application, the fifth data set includes M first samples, where M is a positive integer, and the first samples are channel information samples (also referred to as channel samples). The terminal device performs CSI measurement to obtain channel information, and uses the channel information as a sample for training the third model (i.e., channel information sample).

[0143] After the terminal device obtains the M first samples, it trains the third model based on the M first samples, that is, trains the first part and the second part of the third model. For example, the terminal device trains the CSI generation part and the CSI recovery part 1 based on the M first samples.

[0144] In the embodiment of the present application, the sixth data set includes N first samples and N second samples, the N second samples are obtained by processing the N first samples by the first part of the third model, and N is a positive integer.

[0145] In some embodiments, the N first samples are identical to the M first samples. In other embodiments, the N first samples are partially identical to the M first samples. In other embodiments, the N first samples are completely different from the M first samples.

[0146] The terminal device inputs the N first samples into the third model, and obtains N second samples after the first part of the third model is processed. The second sample is a quantized bit sample corresponding to the channel information. The N first samples and the N second samples constitute a sixth data set, and the terminal device sends the sixth data set to the network device for the network device to train the fourth model. The format of the sixth data set is described below.

[0147] In some embodiments, the sixth data set has a fourth format; in the fourth format, the sixth data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indexes.

[0148] For example, the arrangement of the N groups of data in the sixth data set may be {datasample1, datasample1 ′ ,datasample2,datasample2 ′ ,datasample3,datasample3 ′ ,…,datasampleN,datasampleN ′}, where datasample1, datasample1 ′ For the first set of data, datasample2, datasample2 ′ is the second set of data, and so on. datasample1 represents the first sample with sample index 1, datasample1 ′ represents the second sample obtained by processing datasample1 with the first part of the third model, datasample2 represents the first sample with sample index 2, datasample2 ′ Represents the second sample obtained by processing datasample2 with the first part of the third model, and so on.

[0149] For example, the arrangement of the N groups of data in the second data set may be {data1, data2, data3, ..., dataN}, where data1 = {datasample1, datasample1 ′}, data2={datasample2, datasample2′}, and so on. data1 is the first set of data, data2 is the second set of data, and so on. datasample1 represents the first sample with sample index 1, datasample1 ′ represents the second sample obtained by processing datasample1 with the first part of the third model, datasample2 represents the first sample with sample index 2, datasample2 ′ Represents the second sample obtained by processing datasample2 with the first part of the third model, and so on.

[0150] In some implementations, the terminal device sends fifth information to the network device, where the fifth information is used to indicate a quantization granularity of a quantization module in the third model.

[0151] In some embodiments, the terminal device receives sixth information sent by the network device, and the sixth information is used to indicate the configuration information supported by the fourth model and / or the fourth model supported by the network device, and the configuration information includes at least one of the following: the number of antennas, the number of subbands, and the number of payloads required for CSI reporting.

[0152] Through the above scheme, it is possible to implement that the terminal device trains the third model based on the fifth data set, and the network device trains the fourth model based on the sixth data set, and the trained fourth model and the second part of the third model are used for CSI reporting. The second part of the third model and the fourth model can be understood as a pair of AI models for CSI reporting, that is, a bilateral AI model. After the bilateral AI model is deployed, when the configuration of the network device or the environment in which the terminal device is located changes, the network device and / or the terminal device detects that the performance of their respective models cannot meet the requirements, and a model update process can be initiated. The model update process is described below.

[0153] In some embodiments, the terminal device trains a third model based on the seventh data set, and sends the eighth data set to the network device, the seventh data set includes M' first samples, the eighth data set includes N' first samples and N' second samples, the N' second samples are obtained by processing the N' first samples by the first part of the third model, and M' and N' are positive integers; wherein the eighth data set is used by the network device to determine the fourth model.

[0154] Here, the seventh data set can be understood as an updated data set of the fifth data set, and the eighth data set can be understood as an updated data set of the sixth data set. The seventh data set can also be described as data set A ′ , the eighth data set can also be described as data set B ′ , this application does not limit this.

[0155] Here, the specific implementation method of "the terminal device trains the third model based on the seventh data set and sends the eighth data set to the network device" is similar to the specific implementation method of "the terminal device trains the third model based on the fifth data set and sends the sixth data set to the network device", and can refer to the above description.

[0156] After the terminal device trains the third model based on the fifth data set, when the seventh data set is obtained, the terminal device can train again based on the seventh data set on the basis of the third model after the last training, thereby achieving the purpose of updating the third model. Similarly, after the network device trains the fourth model based on the sixth data set, when the eighth data set is obtained, the terminal device can train again based on the eighth data set on the basis of the fourth model after the last training (or fine-tune the model or update the model parameters), thereby achieving the purpose of updating the fourth model.

[0157] In some embodiments, the eighth data set in the above solution has an association relationship with at least one of the following: the sixth data set, the fourth model. The association relationship is characterized by at least one of the following:

[0158] The subordinate data set identifier of the eighth data set is equal to the identifier of the sixth data set;

[0159] The identifier of the eighth data set is equal to the identifier of the sixth data set;

[0160] The subordinate model identifier of the eighth data set is equal to the identifier of the fourth model.

[0161] In some implementations, the quantization granularity of the quantization module in the third model associated with the eighth data set in the above solution is equal to the quantization granularity of the quantization module in the third model associated with the sixth data set.

[0162] In the above scheme, the transmission method of the sixth data set can be but is not limited to: the terminal device sends the sixth data set to the network device through a configured grant (Configured Grant, CG). In specific implementation, the terminal device receives a second RRC signaling sent by the network device, the second RRC signaling includes a CG-PUSCH configuration, and the CG-PUSCH configuration includes an identifier of the sixth data set; the terminal device receives a second activation signaling sent by the network device, the second activation signaling is used to activate the CG-PUSCH configuration, and the CG-PUSCH configuration is used for the terminal device to send the sixth data set in a CG manner.

[0163] In some implementations, the second activation signaling may be downlink control information (Downlink Control Information, DCI).

[0164] In some embodiments, after activating the CG-PUSCH configuration through the second activation signaling (which can also be understood as activating a CG-PUSCH transmission), the terminal device can transmit one or more data sets, and can include the identifier of the sixth data set (such as the index of the sixth data set) in the CG-PUSCH configuration to establish an association relationship between the CG-PUSCH configuration and the sixth data set, so that the terminal device can know that the CG-PUSCH configuration is used to transmit the sixth data set. After completing the transmission of the sixth data set, the CG-PUSCH configuration can be deactivated through the first activation signaling.

[0165] It should be noted that the CG-PUSCH mode belongs to a semi-static transmission mode. In order to distinguish the CG-PUSCH transmission corresponding to the sixth data set from the ordinary CG-PUSCH transmission, a new RNTI, such as D-RNTI, can be defined for the CG-PUSCH transmission corresponding to the sixth data set, and the new RNTI is used to indicate that the CG-PUSCH transmission is used to transmit the sixth data set.

[0166] During the model update process, the terminal device needs to send the eighth data set to the network device. The transmission method of the eighth data set is similar to the transmission method of the sixth data set mentioned above. The transmission of the eighth data set can be implemented by referring to the transmission method of the sixth data set mentioned above.

[0167] In the technical solution of the embodiment of the present application, the terminal device initiates model training. Specifically, the terminal device trains the third model based on the fifth data set, and the terminal device sends the sixth data set to the network device, so that the network device trains the fourth model based on the sixth data set. The trained fourth model and the first part of the third model (which can be understood as a pair of AI models) are used for CSI reporting. In this way, the training method of the pair of AI models used for CSI reporting is clarified.

[0168] The following is an example of the technical solution of the embodiment of the present application in conjunction with a specific application example. Figure 4 The relevant embodiments are corresponding, Figure 4 The description in the related embodiments can be referred to in Application Example 1. Figure 5 The relevant embodiments are corresponding. Figure 5 The description in the related embodiments can be referenced to the second application example.

[0169] Application Example 1

[0170] In this application example, the network device is a base station, the terminal device is UE1, the first data set is data set A for example, the second data set is data set B, the first part of the first model is CSI generation part 1 (referred to as encoder1 for short), the second part of the first model is the CSI recovery part (referred to as decoder for short), the second model includes CSI generation part 2 (referred to as encoder2 for short), the first sample is a channel sample, and the second sample is a quantized bit sample (hereinafter referred to as channel data).

[0171] Model training process

[0172] 1) The base station trains encoder 1 and decoder based on data set A, and sends data set B to UE 1 after the training. Data set A includes M channel samples, where M is a positive integer. The formats of data set B can be as follows:

[0173] Solution 1: Dataset B includes N channel samples and N channel data, which are obtained after the N channel samples are processed by encoder 1. The arrangement of N channel samples and N channel data in data set B can be referred to Figure 4 Description of the related embodiments.

[0174] As a case, if the M channel samples are measured by UE1 and other UEs, and the N channel samples are all or part of the M channel samples, then the above solution 1 can be used to determine the format of data set B.

[0175] Solution 2: Dataset B only includes N channel data, which are obtained after N channel samples are processed by encoder1. The arrangement of N channel data in dataset B can be referred to Figure 4 Description of the related embodiments.

[0176] As a case, if all the M channel samples are measured by UE1, and the N channel samples are all or part of the M channel samples, then the above solution 2 can be used to determine the format of data set B.

[0177] In some implementations, if the base station considers that there are low-quality channel samples among the M channel samples and only uses N channel samples (N<M) among the M channel samples, then the data set B includes the N channel data obtained after the N channel samples are processed by encoder1, and the base station needs to additionally indicate the sample index of the N channel samples to UE1 through the first information. Here, the specific implementation method of the first information can refer to Figure 4 Description of the related embodiments.

[0178] Solution 3: Data set B includes N groups of data, each of the N groups of data includes one channel data, and each of some of the N groups of data also includes a channel sample corresponding to the channel data. For example, for some of the N channel samples, since they are not measured by UE1, it is necessary to include the channel sample and the channel data obtained after the channel sample is processed by encoder1 in data set B. For other channel samples among the N channel samples, since they are measured by UE1, it is only necessary to include the channel data obtained after the channel sample is processed by encoder1 in data set B. The arrangement of the N groups of data in data set B can refer to Figure 4 Description of the related embodiments.

[0179] The above solution 3 can be understood as a combination of the above solution 1 and the above solution 2. Similar to the above solution 2, if the base station only uses part of the channel samples measured by UE1 (such as P channel samples), then the base station also needs to additionally indicate the sample index of the P channel samples to UE1 through the second information. Here, the specific implementation method of the second information can refer to Figure 4 Description of the related embodiments.

[0180] In addition, the base station needs to indicate to UE1 the quantization granularity K of the quantization module on the base station side associated with data set B, that is, in the bit data after the channel data of each channel sample passes through encoder1 and is quantized, each K bits corresponds to a quantization unit or a dequantization unit.

[0181] The above dataset B can be identified using Dataset ID #1.

[0182] 2) After UE1 receives data set B, it trains encoder2 based on data set B, where encoder2 is called model#B or functionality#B. Encoder2 is associated with the decoder on the base station side to form a pair of AI models for UE1's CSI reporting.

[0183] Here, UE1 can report to the base station through the UE capability reporting process: it supports model#B or functionality#B, and this model#B or functionality#B is obtained through the data set B sent by the base station. In addition, UE1 can also report to the base station the number of antennas, the number of subbands, the number of payloads required for CSI reporting, etc. of the base station that can be supported by this model#B or functionality#B.

[0184] The above model#B or functionality#B can be identified using model ID#1 or functionality ID#1.

[0185] The model training can be realized through the above model training process, wherein the trained decoder is deployed on the base station side, and the trained encoder2 is deployed on the terminal device side. The decoder and encoder2 form a pair of AI models.

[0186] The transmission method of the above dataset B can refer to Figure 4 Description of the related embodiments.

[0187] Model update process

[0188] 3) After the AI ​​model is deployed, when the configuration of the base station or the environment in which UE1 is located changes, the base station or UE1 detects that the performance of their respective models cannot meet the requirements, and can initiate a model update process. The base station trains encoder1 and decoder based on data set A′, and sends data set B′ to UE1 after the training, that is, the model training process is initiated again. Among them, UE1 can use data set B′ to fine-tune the model or update the model parameters based on the last trained encoder2, so as to achieve the purpose of updating encoder2. The updated model of encoder2 is recorded as encoder2′.

[0189] The above dataset B′ can be identified by using Dataset ID#2. The dataset B′ has the following association with the dataset B or model#B or functionality#B in the above model training phase:

[0190] a) Dataset B′ and dataset B have the following association relationship:

[0191] Dataset B′ has a subordinate dataset ID, and the subordinate dataset ID = Dataset ID#1 of dataset B;

[0192] Dataset ID#2 of dataset B′=Dataset ID#1 of dataset B.

[0193] b) Dataset B′ and model#B or functionality#B have the following relationship:

[0194] Data set B′ has subordinate model ID#1′ or functionality ID#1′, and model ID#1′=modelID#1 or functionality ID#1′=functionality ID#1.

[0195] In addition, the granularity N′ of the quantization module on the base station side associated with the data set B′=the granularity N associated with the data set B.

[0196] The transmission method of the above data set B′ can refer to Figure 4 Description of the related embodiments.

[0197] The technical solution of the embodiment of the present application proposes a model training initiated by a base station, including a model training process and a model update process. On the one hand, the training of the bilateral model can be completed without model transmission, which provides a feasible training method for the use of the bilateral model. On the other hand, when the performance of the model does not meet the requirements, the technical solution of the embodiment of the present application provides a method for quickly updating the model based on the deployed model, ensuring that the bilateral model can quickly adapt to changes in the base station configuration and the UE environment. At the same time, compared with the retrained model, the model update is based on the trained model to fine-tune the model or update the model parameters, which can significantly reduce the training data volume requirements and the computing power and other overheads of model training while ensuring better reasoning performance. In addition, the matching degree of the two side models of the bilateral model is usually higher than that of the retrained model after the updated model.

[0198] Application Example 2

[0199] Model training process

[0200] 1) The UE side trains encoder and decoder1 based on data set A, and sends data set B to the base station after the training. Data set A includes M channel samples, where M is a positive integer. The format of data set B can be as follows:

[0201] Dataset B includes N (N≤M) channel samples and N channel data. The N channel data are obtained after the N channel samples are processed by the encoder. The arrangement of the N channel samples and the N channel data in data set B can be referred to Figure 5 Description of the related embodiments.

[0202] In addition, the UE needs to report to the base station the granularity L of the quantization module on the UE side associated with the data set B, that is, in the bit data after the channel data of each channel sample passes through the encoder and is quantized, each L bits corresponds to a quantization unit or a dequantization unit.

[0203] The above dataset B can be identified using Dataset ID #1.

[0204] 2) After receiving data set B, the base station trains decoder2 based on data set B, where decoder2 is called model#B or functionality#B. Decoder2 is associated with the encoder on the UE side to form a pair of AI models for CSI reporting of UE1.

[0205] Here, the base station may indicate to the UE that it supports model#B or functionality#B, and that the model#B or functionality#B is obtained through the data set B sent by the UE. In addition, the base station may also indicate to the UE the number of antennas, the number of subbands, the number of payloads required for CSI reporting, etc. of the base station that the model#B or functionality#B can support.

[0206] The above model#B or functionality#B can be identified using model ID#1 or functionality ID#1.

[0207] The model training can be achieved through the above model training process, wherein the trained decoder2 is deployed on the base station side, and the trained encoder is deployed on the terminal device side. Decoder2 and encoder form a pair of AI models.

[0208] The transmission method of the above dataset B can refer to Figure 5 Description of the related embodiments.

[0209] Model update process

[0210] 3) After the AI ​​model is deployed, when the configuration of the base station or the environment in which the UE is located changes, the base station or UE detects that the performance of their respective models cannot meet the requirements, and can initiate a model update process. The UE trains encoder1 and decoder1 based on data set A′, and sends data set B′ to the base station after the training, that is, the model training process is initiated again. Among them, the base station can use data set B′ to fine-tune the model or update the model parameters based on the last trained decoder2, so as to achieve the purpose of updating decoder2. The updated model of decoder2 is recorded as decoder2′.

[0211] The above dataset B′ can be identified by using Dataset ID#2. The dataset B′ has the following association with the dataset B or model#B or functionality#B in the above model training phase:

[0212] a) Dataset B′ and dataset B have the following association relationship:

[0213] Dataset B′ has a subordinate dataset ID, and the subordinate dataset ID = Dataset ID#1 of dataset B;

[0214] Dataset ID#2 of dataset B′=Dataset ID#1 of dataset B.

[0215] b) Dataset B′ and model#B or functionality#B have the following relationship:

[0216] Data set B′ has subordinate model ID#1′ or functionality ID#1′, and model ID#1′=modelID#1 or functionality ID#1′=functionality ID#1.

[0217] In addition, the granularity N′ of the quantization module on the base station side associated with the data set B′=the granularity N associated with the data set B.

[0218] The transmission method of the above data set B′ can refer to Figure 5 Description of the related embodiments.

[0219] The technical solution of the embodiment of the present application proposes a model training initiated by the UE, including a model training process and a model update process. On the one hand, the training of the bilateral model can be completed without transmitting the model, which provides a feasible training method for the use of the bilateral model. On the other hand, when the performance of the model does not meet the requirements, the technical solution of the embodiment of the present application provides a method for quickly updating the model based on the deployed model, ensuring that the bilateral model can quickly adapt to changes in the base station configuration and the UE environment. At the same time, compared with the retrained model, the model update is based on the trained model to fine-tune the model or update the model parameters, which can significantly reduce the training data volume requirements and the computing power and other overheads of model training while ensuring better reasoning performance. In addition, the matching degree of the two side models of the bilateral model is usually higher than that of the retrained model after the updated model.

[0220] Figure 6 This is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. Figure 1 , applied to network equipment, such as Figure 6As shown, the model training device includes:

[0221] A training unit 601 is configured to train a first model based on a first data set, wherein the first model includes a first part and a second part;

[0222] A sending unit 602 is configured to send a second data set to a terminal device, where the first data set includes M first samples, and the second data set includes N second samples, where the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers;

[0223] The second data set is used for training a second model for the terminal device, and the trained second model and the second part of the first model are used for CSI reporting.

[0224] In some embodiments, the second data set also includes the N first samples; the second data set has a first format; in the first format, the second data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indices.

[0225] In some embodiments, the second data set has a second format; in the second format, the second data set includes N second samples, and the N second samples are arranged according to sample indices.

[0226] In some implementations, the sending unit 602 is further used to send first information to the terminal device, where the first information is used to indicate sample indexes of the N second samples.

[0227] In some embodiments, the first information includes a first sample index list, which includes sample indices of the N second samples; or, the first information includes a first bit map, each bit in the first bit map corresponds to a sample index, and the value of the bit is used to indicate whether the second sample corresponding to the sample index corresponding to the bit is included in the second data set.

[0228] In some embodiments, the second data set has a third format; in the third format, the second data set includes N groups of data, each group of data in the N groups of data includes a second sample, and each group of data in some of the N groups of data also includes a first sample corresponding to the second sample; wherein the N groups of data are arranged according to sample indexes.

[0229] In some embodiments, P first samples among the N first samples correspond to P second samples in the second data set, where P is an integer less than N; the sending unit 602 is also used to send second information to the terminal device, where the second information is used to indicate the sample index of the P second samples.

[0230] In some embodiments, the second information includes a second sample index list, the second sample index list includes sample indices of the P second samples; or, the second information includes a second bit map, each bit in the second bit map corresponds to a sample index, and the value of the bit is used to indicate whether the second sample corresponding to the sample index corresponding to the bit is included in the second data set.

[0231] In some implementations, the sending unit 602 is further used to send third information to the terminal device, where the third information is used to indicate a quantization granularity of a quantization module in the first model.

[0232] In some embodiments, the apparatus further includes: a receiving unit 603, for receiving fourth information sent by the terminal device, the fourth information being used to indicate a second model supported by the terminal device and / or configuration information supported by the second model, the configuration information including at least one of the following: the number of antennas, the number of subbands, and the number of payloads required for CSI reporting.

[0233] In some implementations, the training unit 601 is further configured to train the first model based on a third data set;

[0234] The sending unit 602 is further used to send a fourth data set to the terminal device, the third data set includes M' first samples, the fourth data set includes N' second samples, the N' second samples are obtained by processing the N' first samples by the first part of the first model, and M' and N' are positive integers; wherein the fourth data set is used by the terminal device to determine the second model.

[0235] In some implementations, the fourth data set is associated with at least one of the following: the second data set, the second model.

[0236] In some embodiments, the association is characterized by at least one of the following:

[0237] The subordinate data set identifier of the fourth data set is equal to the identifier of the second data set;

[0238] The identifier of the fourth data set is equal to the identifier of the second data set;

[0239] The subordinate model identifier of the fourth data set is equal to the identifier of the second model.

[0240] In some implementations, a quantization granularity of a quantization module in the first model associated with the fourth data set is equal to a quantization granularity of a quantization module in the first model associated with the second data set.

[0241] In some implementations, the sending unit 602 is configured to send the second data set to the terminal device via SPS.

[0242] In some embodiments, the sending unit 602 is used to send a first RRC signaling to the terminal device, the first RRC signaling includes an SPS configuration, and the SPS configuration includes an identifier of the second data set; and send a first activation signaling to the terminal device, the first activation signaling is used to activate the SPS configuration, and the SPS configuration is used for the terminal device to receive the second data set in an SPS manner.

[0243] Those skilled in the art should understand that Figure 6 The implementation functions of each unit in the model training device shown can be understood by referring to the relevant description of the aforementioned method. Figure 6 The functions of each unit in the model training device shown can be implemented by a program running on a processor, or by a specific logic circuit.

[0244] Figure 7 This is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. Figure 2 , applied to terminal devices, such as Figure 7 As shown, the model training device includes:

[0245] A training unit 701 is configured to train a third model based on a fifth data set, wherein the third model includes a first part and a second part;

[0246] A sending unit 702 is configured to send a sixth data set to a network device, wherein the fifth data set includes M first samples, and the sixth data set includes N first samples and N second samples, wherein the N second samples are obtained by processing the N first samples by the first part of the third model, and M and N are positive integers;

[0247] The sixth data set is used by the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

[0248] In some embodiments, the sixth data set has a fourth format; in the fourth format, the sixth data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indexes.

[0249] In some implementations, the sending unit 702 is further used to send fifth information to the network device, where the fifth information is used to indicate a quantization granularity of a quantization module in the third model.

[0250] In some embodiments, the device also includes: a receiving unit 703, used to receive sixth information sent by the network device, the sixth information is used to indicate the fourth model supported by the network device and / or the configuration information supported by the four models, and the configuration information includes at least one of the following: the number of antennas, the number of subbands, and the number of loads required for CSI reporting.

[0251] In some embodiments, the training unit 701 is also used to train the third model based on the seventh data set, and send the eighth data set to the network device, the seventh data set includes M' first samples, the eighth data set includes N' first samples and N' second samples, the N' second samples are obtained by processing the N' first samples by the first part of the third model, and M' and N' are positive integers; wherein the eighth data set is used by the network device to determine the fourth model.

[0252] In some embodiments, the eighth data set is associated with at least one of the following: the sixth data set, the fourth model.

[0253] In some embodiments, the association is characterized by at least one of the following:

[0254] The subordinate data set identifier of the eighth data set is equal to the identifier of the sixth data set;

[0255] The identifier of the eighth data set is equal to the identifier of the sixth data set;

[0256] The subordinate model identifier of the eighth data set is equal to the identifier of the fourth model.

[0257] In some implementations, the quantization granularity of the quantization module in the third model associated with the eighth data set is equal to the quantization granularity of the quantization module in the third model associated with the sixth data set.

[0258] In some implementations, the sending unit 702 is used to send the sixth data set to the network device via the CG method.

[0259] In some embodiments, the receiving unit 703 is also used to receive a second RRC signaling sent by the network device, the second RRC signaling includes a CG-PUSCH configuration, and the CG-PUSCH configuration includes an identifier of the sixth data set; receive a second activation signaling sent by the network device, the second activation signaling is used to activate the CG-PUSCH configuration, and the CG-PUSCH configuration is used by the terminal device to send the sixth data set in a CG manner.

[0260] Those skilled in the art should understand that Figure 7 The implementation functions of each unit in the model training device shown can be understood by referring to the relevant description of the aforementioned method. Figure 7 The functions of each unit in the model training device shown can be implemented by a program running on a processor, or by a specific logic circuit.

[0261] Figure 8 800 is a schematic structural diagram of a communication device 800 provided in an embodiment of the present application. The communication device may be a terminal device or a network device. Figure 8 The communication device 800 shown includes a processor 810, and the processor 810 can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0262] Alternatively, if Figure 8 As shown, the communication device 800 may further include a memory 820. The processor 810 may call and run a computer program from the memory 820 to implement the method in the embodiment of the present application.

[0263] The memory 820 may be a separate device independent of the processor 810 , or may be integrated into the processor 810 .

[0264] Alternatively, if Figure 8 As shown, the communication device 800 may further include a transceiver 830, and the processor 810 may control the transceiver 830 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.

[0265] The transceiver 830 may include a transmitter and a receiver. The transceiver 830 may further include an antenna, and the number of the antennas may be one or more.

[0266] Optionally, the communication device 800 may specifically be a network device of an embodiment of the present application, and the communication device 800 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.

[0267] Optionally, the communication device 800 may specifically be a mobile terminal / terminal device of an embodiment of the present application, and the communication device 800 may implement the corresponding processes implemented by the mobile terminal / terminal device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.

[0268] Fig. 9 It is a schematic structural diagram of the chip of an embodiment of the present application. Fig. 9 The chip 900 shown includes a processor 910, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0269] Alternatively, if Fig. 9 As shown, the chip 900 may further include a memory 920. The processor 910 may call and run a computer program from the memory 920 to implement the method in the embodiment of the present application.

[0270] The memory 920 may be a separate device independent of the processor 910 , or may be integrated into the processor 910 .

[0271] Optionally, the chip 900 may further include an input interface 930. The processor 910 may control the input interface 930 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0272] Optionally, the chip 900 may further include an output interface 940. The processor 910 may control the output interface 940 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0273] Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0274] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0275] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0276] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and performed. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0277] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0278] It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0279] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0280] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0281] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0282] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0283] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0284] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0285] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0286] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0287] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0288] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A model training method, characterized in that: The method comprises: The network device trains a first model based on a first data set, the first model includes a first part and a second part, and sends a second data set to a terminal device, the first data set includes M first samples, the second data set includes N second samples, the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers; The second data set is used for the terminal device to train a second model, and the trained second model and the second part of the first model are used for channel state information CSI reporting.

2. The method according to claim 1, characterized in that The second data set also includes the N first samples; the second data set has a first format; In the first format, the second data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indexes.

3. The method according to claim 1, characterized in that: The second data set has a second format; In the second format, the second data set includes N second samples, and the N second samples are arranged according to sample indices.

4. The method according to claim 3, characterized in that The method further comprises: The network device sends first information to the terminal device, where the first information is used to indicate sample indexes of the N second samples.

5. The method according to claim 4, characterized in that The first information includes a first sample index list, and the first sample index list includes sample indexes of the N second samples; or, The first information includes a first bitmap, each bit in the first bitmap corresponds to a sample index, and the value of the bit is used to indicate whether a second sample corresponding to the sample index corresponding to the bit is included in the second data set.

6. The method according to claim 1, characterized in that The second data set has a third format; In the third format, the second data set includes N groups of data, each group of the N groups of data includes a second sample, and each group of data in some of the N groups of data also includes a first sample corresponding to the second sample; wherein the N groups of data are arranged according to sample indexes.

7. The method according to claim 6, characterized in that P first samples of the N first samples correspond to P second samples in the second data set, where P is an integer less than N; the method further includes: The network device sends second information to the terminal device, where the second information is used to indicate sample indexes of the P second samples.

8. The method according to claim 7, characterized in that The second information includes a second sample index list, and the second sample index list includes sample indices of the P second samples; or, The second information includes a second bitmap, each bit in the second bitmap corresponds to a sample index, and the value of the bit is used to indicate whether the second sample corresponding to the sample index corresponding to the bit is included in the second data set.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: The network device sends third information to the terminal device, where the third information is used to indicate a quantization granularity of a quantization module in the first model.

10. The method according to any one of claims 1 to 8, characterized in that The method further comprises: The network device receives fourth information sent by the terminal device, and the fourth information is used to indicate the second model supported by the terminal device and / or configuration information supported by the second model, and the configuration information includes at least one of the following: the number of antennas, the number of subbands, and the number of payloads required for CSI reporting.

11. The method according to any one of claims 1 to 8, characterized in that The method further comprises: The network device trains the first model based on the third data set, and sends a fourth data set to the terminal device, wherein the third data set includes M' first samples, and the fourth data set includes N' second samples, wherein the N' second samples are obtained by processing the first part of the N' first samples by the first model, and M' and N' are positive integers; The fourth data set is used by the terminal device to determine the second model.

12. The method according to claim 11, characterized in that The fourth data set is associated with at least one of the following: the second data set, the second model.

13. The method according to claim 12, characterized in that The association relationship is characterized by at least one of the following: The subordinate data set identifier of the fourth data set is equal to the identifier of the second data set; The identifier of the fourth data set is equal to the identifier of the second data set; The subordinate model identifier of the fourth data set is equal to the identifier of the second model.

14. The method according to claim 11, characterized in that The quantization granularity of the quantization module in the first model associated with the fourth data set is equal to the quantization granularity of the quantization module in the first model associated with the second data set.

15. The method according to any one of claims 1 to 8, characterized in that The sending the second data set to the terminal device includes: The second data set is sent to the terminal device in a semi-persistent scheduling (SPS) manner.

16. The method according to claim 15, characterized in that The method further comprises: The network device sends a first radio resource control RRC signaling to the terminal device, where the first RRC signaling includes an SPS configuration, and the SPS configuration includes an identifier of the second data set; The network device sends a first activation signaling to the terminal device, where the first activation signaling is used to activate the SPS configuration, and the SPS configuration is used by the terminal device to receive the second data set in an SPS manner.

17. A model training method, characterized in that: The method comprises: The terminal device trains a third model based on the fifth data set, the third model includes a first part and a second part, and sends a sixth data set to the network device, the fifth data set includes M first samples, the sixth data set includes N first samples and N second samples, the N second samples are obtained by processing the N first samples by the first part of the third model, and M and N are positive integers; The sixth data set is used by the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

18. The method according to claim 17, characterized in that The sixth data set has a fourth format; In the fourth format, the sixth data set includes N groups of data, each of the N groups of data includes a first sample and a second sample corresponding to the first sample; wherein the N groups of data are arranged according to sample indexes.

19. The method according to claim 17 or 18, characterized in that The method further comprises: The terminal device sends fifth information to the network device, where the fifth information is used to indicate the quantization granularity of the quantization module in the third model.

20. The method according to claim 17 or 18, characterized in that The method further comprises: The terminal device receives the sixth information sent by the network device, and the sixth information is used to indicate the fourth model supported by the network device and / or the configuration information supported by the fourth model, and the configuration information includes at least one of the following: the number of antennas, the number of subbands, and the number of payloads required for CSI reporting.

21. The method according to claim 17 or 18, characterized in that The method further comprises: The terminal device trains the third model based on the seventh data set, and sends the eighth data set to the network device, the seventh data set includes M' first samples, the eighth data set includes N' first samples and N' second samples, the N' second samples are obtained by processing the N' first samples by the first part of the third model, and M' and N' are positive integers; The eighth data set is used by the network device to determine the fourth model.

22. The method according to claim 21, characterized in that The eighth data set is associated with at least one of the following: the sixth data set, the fourth model.

23. The method according to claim 22, characterized in that The association relationship is characterized by at least one of the following: The subordinate data set identifier of the eighth data set is equal to the identifier of the sixth data set; The identifier of the eighth data set is equal to the identifier of the sixth data set; The subordinate model identifier of the eighth data set is equal to the identifier of the fourth model.

24. The method according to claim 21, characterized in that The quantization granularity of the quantization module in the third model associated with the eighth data set is equal to the quantization granularity of the quantization module in the third model associated with the sixth data set.

25. The method according to claim 17 or 18, characterized in that The sending the sixth data set to the network device includes: The sixth data set is sent to the network device by configuring the authorized CG mode.

26. The method according to claim 25, characterized in that The method further comprises: The terminal device receives a second RRC signaling sent by the network device, where the second RRC signaling includes a CG-PUSCH configuration, and the CG-PUSCH configuration includes an identifier of the sixth data set; The terminal device receives a second activation signaling sent by the network device, where the second activation signaling is used to activate the CG-PUSCH configuration, and the CG-PUSCH configuration is used by the terminal device to send the sixth data set in a CG manner.

27. A model training device, characterized in that: Applied to network equipment, the device comprises: A training unit, configured to train a first model based on a first data set, wherein the first model includes a first part and a second part; a sending unit, configured to send a second data set to a terminal device, wherein the first data set includes M first samples, and the second data set includes N second samples, wherein the N second samples are obtained by processing the N first samples by the first part of the first model, and M and N are positive integers; The second data set is used for training a second model for the terminal device, and the trained second model and the second part of the first model are used for CSI reporting.

28. A model training device, characterized in that: Applied to a terminal device, the device comprises: A training unit, configured to train a third model based on a fifth data set, wherein the third model includes a first part and a second part; a sending unit, configured to send a sixth data set to a network device, wherein the fifth data set includes M first samples, and the sixth data set includes N first samples and N second samples, wherein the N second samples are obtained by processing the N first samples by the first part of the third model, and M and N are positive integers; The sixth data set is used by the network device to train a fourth model, and the trained fourth model and the first part of the third model are used for CSI reporting.

29. A communication device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method as claimed in any one of claims 1 to 26.

30. A chip, characterized in that: It comprises: a processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 26.

31. A computer-readable storage medium, characterized in that: Used to store a computer program, the computer program causing a computer to execute the method according to any one of claims 1 to 26.

Images