Communication method, terminal equipment and network equipment

Abstract

The invention provides a communication method, terminal equipment and network equipment. The method comprises: a terminal device receives a first data set sent by a network device, the first data set including first data and not including second data, and the first data and the second data are both used for training, fine tuning or retraining of a model of the terminal device. In the application, the first data set sent by the network equipment to the terminal equipment can comprise the first data and does not comprise the second data acquired by the terminal equipment, and the terminal equipment can utilize the received first data in the first data set and the second data acquired by the terminal equipment to send the first data to the terminal equipment. According to the method, the model in the terminal equipment is trained, fine-tuned or retrained, and the second data acquired by the terminal equipment does not need to be transmitted at the air interface, so that air interface resources can be saved, the energy consumption can be reduced, and the acceleration of model training is facilitated.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method, terminal equipment, and network equipment. Background Technology

[0002] In new radio (NR) systems, terminal devices that deploy artificial intelligence (AI) / machine learning (ML) models need to train the models. The dataset used for model training is configured by network devices, and the transmission of this dataset requires a large amount of air interface resources. Therefore, it is necessary to improve the transmission method of this dataset. Summary of the Invention

[0003] This application provides a communication method, a terminal device, and a network device. The various aspects covered by this application are described below.

[0004] In a first aspect, a communication method is provided, comprising: a terminal device receiving a first dataset sent by a network device, the first dataset including first data but not including second data, wherein both the first data and the second data are used for training, fine-tuning, or retraining a model of the terminal device.

[0005] In a second aspect, a communication method is provided, comprising: a network device sending a first dataset to a terminal device, the first dataset including first data but not including second data, wherein both the first data and the second data are used for training, fine-tuning, or retraining a model of the terminal device.

[0006] Thirdly, a terminal device is provided, comprising: a transceiver unit for receiving a first dataset sent by a network device, the first dataset including first data but not including second data, wherein both the first data and the second data are used for training, fine-tuning, or retraining a model of the terminal device.

[0007] Fourthly, a network device is provided, comprising: a transceiver unit for sending a first dataset to a terminal device, the first dataset including first data but not including second data, wherein both the first data and the second data are used for training, fine-tuning, or retraining a model of the terminal device.

[0008] Fifthly, a terminal device is provided, including a transceiver, a memory, and a processor, wherein the memory is used to store a program, and the processor is used to invoke the program in the memory and control the transceiver to receive or send signals so that the terminal device performs the method as described in the first aspect.

[0009] In a sixth aspect, a network device is provided, including a transceiver, a memory, and a processor, wherein the memory is used to store a program, and the processor is used to invoke the program in the memory and control the transceiver to receive or transmit signals so that the network device performs the method as described in the second aspect.

[0010] A seventh aspect provides an apparatus including a processor for calling a program from a memory to cause the apparatus to perform the method as described in the first or second aspect.

[0011] Eighthly, a chip is provided, including a processor for calling a program from memory to cause a device having the chip mounted to perform the method as described in the first or second aspect.

[0012] Ninth aspect, a computer-readable storage medium is provided having a program stored thereon that causes a computer to perform the method as described in the first or second aspect.

[0013] A tenth aspect provides a computer program product, including a program that causes a computer to perform the method as described in the first or second aspect.

[0014] Eleventhly, a computer program is provided that causes a computer to perform the method as described in the first or second aspect.

[0015] In this embodiment of the application, the first dataset sent by the network device to the terminal device may include first data, but does not include second data already acquired by the terminal device. The terminal device can use the first data in the received first dataset and the second data it has acquired to train, fine-tune, or retrain the model in the terminal device. Since it is not necessary to transmit the second data already acquired by the terminal device over the air interface, air interface resources can be saved, energy consumption can be reduced, and it is beneficial to accelerate the training of the model. Attached Figure Description

[0016] Figure 1 This is a system architecture example diagram of a communication system applicable to embodiments of this application.

[0017] Figure 2 This is a schematic diagram of a bilateral model.

[0018] Figure 3 This is a flowchart illustrating the communication method according to an embodiment of this application.

[0019] Figure 4 This is a schematic diagram of the original dataset corresponding to the first dataset.

[0020] Figure 5 This is a schematic diagram of the first dataset.

[0021] Figure 6 This is a diagram illustrating how network devices send CSI record information to terminal devices.

[0022] Figure 7 This is a diagram illustrating how network devices send CSI record information to terminal devices.

[0023] Figure 8 A schematic diagram illustrating the data transmission process during cell handover for terminal devices.

[0024] Figure 9 This is a schematic diagram of the structure of a terminal device according to an embodiment of this application.

[0025] Figure 10 This is a schematic diagram of the structure of a network device according to an embodiment of this application.

[0026] Figure 11 This is a schematic diagram of a communication apparatus according to an embodiment of this application. Detailed Implementation

[0027] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0028] Communication system Figure 1 This is an example diagram of the system architecture of a communication system 100 applicable to embodiments of this application. The communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 can provide network coverage for a specific geographical area and can communicate with the terminal device 120 located within that coverage area. The terminal device 120 can access a network, such as a wireless network, through the network device 110. Optionally, the communication system 100 may also include other network entities such as a network controller and a mobility management entity; this application embodiment does not limit this.

[0029] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as fifth-generation (5G) systems, new radio (NR) systems, long-term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as sixth-generation mobile communication systems, satellite communication systems, and so on.

[0030] The technical solutions of this application embodiment can also be applied to communication systems such as wireless local area networks (WLAN), wireless fidelity (WIFI), and high-performance radio local area networks (HIPELAN). The technical solutions provided in this application embodiment can be applied to communication systems using the 802.11 standard. For example, the 802.11 standard includes, but is not limited to, the 802.11ax standard, the 802.11be standard, the 802.11bn standard, and the next-generation 802.11 standard (post802.11bn).

[0031] In this application embodiment, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, vehicle-mounted device, etc. Terminal devices can also be mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes. Optionally, terminal devices can act as base stations. For example, a terminal device can act as a dispatching entity, providing sidelink signals between terminal devices in vehicle-to-everything (V2X) or device-to-device (D2D) systems. For instance, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices communicate without relaying communication signals through base stations.

[0032] In this embodiment, the network device can be a device used to communicate with a terminal device. The network device can be an access network device or a wireless access network device. For example, the network device can be a base station. The term "base station" can broadly encompass various names as follows, or can be replaced by names such as NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, transmitting and receiving point (TRP), transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-standard wireless (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entity, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, or an entity that performs base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network-side device in a 6G network, or an entity that performs base station functions in future communication systems. Base stations can support networks using the same or different access technologies. This application does not limit the specific technology or device form used in the network equipment. In some deployments, the network equipment may include a CU or a DU; or, the network equipment may include both a CU and a DU.

[0033] Furthermore, network equipment can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0034] In other implementations, the terminal device may also include access point stations (AP STAs) and / or non-access point stations (non-AP STAs) in the WLAN, and may support, but is not limited to, 802.11be, 802.11bn or post 802.11bn standards; it may also support various current and future 802.11 family WLAN standards such as 802.11ax, 802.11ac, 802.11n, 802.11g, 802.11b and 802.11a.

[0035] Accordingly, network devices may also include access points (APs) in WLANs, which can support 802.11be, 802.11bnor post 802.11bn standards; and can also support various current and future 802.11 family WLAN standards such as 802.11ax, 802.11ac, 802.11n, 802.11g, 802.11b, and 802.11a.

[0036] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0037] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform such as a cloud platform.

[0038] With the application of multiple-input multiple-output (MIMO) and massive MIMO antennas, the amount of channel state information (CSI) data that terminal devices need to report is increasing. In recent 3GPP research, autoencoders from machine learning can be used to optimize the performance of CSI reporting by terminal devices. An autoencoder consists of two parts: an encoder and a decoder. The encoder is located on the terminal device, which compresses the CSI data and reports the compressed CSI data to the network device. The network device decodes the compressed CSI data to recover the compressed CSI data. The compressed CSI data includes, for example, PMI, precoding matrix, and raw channel estimation (denoted as H matrix). Furthermore, the autoencoder can also be called a two-sided model, deployed on both the terminal device and the network device.

[0039] As an example, Figure 2 A bilateral model is shown, where X represents the target CSI measured by the terminal device, the target CSI is compressed by the encoder and sent to the base station, X' represents the target CSI recovered by the base station through the decoder, and Z represents the latent vector.

[0040] During data collection, the terminal device reports CSI data to the network device, which then organizes the received CSI data and places it into a dataset. When the terminal device is training, fine-tuning, retraining, or testing its model, the network device can send this dataset to the terminal device, which may contain the CSI data reported by the terminal device.

[0041] It is evident that the dataset used by terminal devices for model training is typically configured by the network device. Some data in this dataset may be reported by the terminal devices to the network device; that is, this part of the data is known to the terminal devices, or it is data that the terminal devices have already stored, retained, or recorded. The network device can collect data reported by different terminal devices to form this dataset, and then configure this dataset for the terminal devices when they need to train, fine-tune, or retrain their models. Since the dataset sent by the network device may include data previously reported to the network device by the terminal devices, meaning that data from a certain terminal device may be sent back to that terminal device during model training, this data is exchanged multiple times over the air interface, resulting in significant overhead of shared resources and wasted air interface resources. This is especially true when the data reported by the terminal devices is of high precision; the repeated exchange of this data over the air interface leads to enormous overhead of air interface resources.

[0042] Therefore, in this embodiment of the application, the first dataset sent by the network device to the terminal device may include first data, but does not include the second data already acquired by the terminal device. The terminal device can use the first data in the received first dataset and the second data it has acquired to train, fine-tune, or retrain the model in the terminal device. Since it is not necessary to transmit the second data already acquired by the terminal device over the air interface, air interface resources can be saved, energy consumption can be reduced, and it is beneficial to accelerate the training of the model.

[0043] In the embodiments of this application, the term "model" can also be replaced with terms such as one-sided model, two-sided model, encoder model, decoder model, standard model, reference model, training model, CSI feedback model, function, and functional characteristics.

[0044] The following is combined Figures 3 to 7 The embodiments of this application will be described in detail below.

[0045] Figure 3 This is a flowchart illustrating the communication method provided in an embodiment of this application. Figure 3 The method 300 shown can be performed by a terminal device and a network device. The terminal device may be, for example, a terminal device... Figure 1 The terminal device 120 shown may be, for example, a network device. Figure 1 The network device 110 shown is an example. Network devices may include, for example, a source base station and / or a target base station. Figure 2 The method 300 shown may include some or all of the following steps.

[0046] In step 310, the network device sends a first dataset to the terminal device. Correspondingly, the terminal device receives the first dataset sent by the network device. The first dataset includes first data but excludes second data. Both the first and second data are used for training, fine-tuning, or retraining the terminal device's model. Alternatively, the first dataset omits, excludes, or substitutes for the second data. The second data may include CSI data reported by the terminal device to the network device, and / or include CSI data that the terminal device has already acquired, stored, or recorded.

[0047] For example, after acquiring CSI data, the terminal device can store and report the CSI data to the network device. This CSI data may include, for example, target CSI data and / or CSI load data, and may contain second data. Thus, since the second data was reported by the terminal device to the network device and has already been stored or recorded by the terminal device, the network device does not need to include this second data when sending the first dataset. Target CSI data and CSI load data will be described in detail in later sections.

[0048] The first dataset can be used, for example, for training a bilateral model. That is, the decoder model of the network device and the encoder model of the corresponding terminal device can both be trained based on all or part of the data in the first dataset. The CSI data used for model training may include CSI data previously reported by the terminal device to the network device, and is used by the network device to construct the first dataset.

[0049] The network device can further indicate to the terminal device which data is omitted or excluded in the first dataset sent from the network device to the terminal device. For example, such as... Figure 3 As shown, method 300 may further include step 320. In step 320, the network device sends first information to the terminal device. Accordingly, the terminal device receives the first information sent by the network. This first information is used to indicate second data. For example, the first information includes identification information corresponding to the second data.

[0050] In other words, the first dataset sent by the network device to the terminal device may not include the specific content of the second data. Instead, it may use the first information to indicate the identification information of the second data. This allows the terminal device to identify the second data from its stored CSI data based on the identification information indicated by the first information, and then use both the first and second data for model training, fine-tuning, or retraining, without needing to receive the second data from the network device again. Since the specific content of the second data does not need to be frequently transmitted over the air interface, air interface resources are saved. Furthermore, the reduced amount of data in the transmitted first dataset can accelerate the model training process or the training preparation process.

[0051] The first information can be transmitted in various forms. For example, the first information can be sent simultaneously with the first dataset; or the first information can be sent at different times from the first dataset; or the first information can be included within the first dataset; or the first information can be not included within the first dataset.

[0052] If the first information is not included in the first dataset, meaning it is transmitted independently of the first dataset, it offers greater flexibility and is beneficial for meeting the training requirements of various machine learning models. If the first dataset contains the first information, meaning it is sent to the terminal device as part of the first dataset for training a particular model, it saves on additional signaling control and reduces complexity.

[0053] The first information may be carried in RRC signaling sent by the network device, or contained in a file (e.g., a log or record) transmitted by the network device, or contained in the configuration information of the first dataset sent by the network device, or contained in auxiliary information for model training, i.e., as part of the auxiliary information for model training. This auxiliary information may be sent to the terminal device along with the first dataset during model training, or the auxiliary information and the first dataset may be sent to the terminal device separately.

[0054] The RRC signaling described in this embodiment can be transmitted in chunks. For example, if a terminal device reports CSI data via uplink RRC signaling, due to the size limitation of uplink RRC signaling (e.g., typically 9KB), this CSI data can be transmitted in chunks in some cases. The specific chunk size can be indicated by the network device via MAC CE or RRC signaling. Whether CSI data is transmitted in chunks can be determined by the capabilities of the terminal device. If the terminal device has strong capabilities and can determine large CSI data, then chunk transmission is not required. If the terminal device has weak capabilities, it can request chunk transmission. The network device responds to the terminal device by indicating whether to accept or reject the requested chunk transmission. For example, one bit can be used, where a value of 1 indicates acceptance of chunk transmission, and a value of 0 indicates rejection of chunk transmission. For example, for downlink RRC signaling, such as RRC signaling carrying the first information, a similar block transmission method can also be used. If the terminal device is capable of handling larger RRC signaling, then block transmission is not required. If the terminal device is only capable of handling smaller RRC signaling, then it can request the network device to send the RRC signaling in a block transmission manner.

[0055] The identification information of the second data mentioned above includes one or more of the following, or a combination of at least two of the following: the reporting time (or timestamp) of the second data; the identifier of the data subset to which the second data belongs; the identifier of the first dataset to which the second data belongs; the identifier of the CSI resource configuration corresponding to the second data; the identifier of the CSI reporting configuration corresponding to the second data; the identifier of the model; and the pairing identifier of the model. The encoder model of the terminal device and the decoder model of the corresponding network device share a pairing identifier (paring ID).

[0056] In this embodiment, the identification information of the second data can be determined by the terminal device or the network device. For example, during data collection or model monitoring, the terminal device reports the identification information (or number, record, etc.) of the CSI data to the network device, so that the network device can use the corresponding identification information when indicating the second data not included in the first dataset to the terminal device. Alternatively, the identification information of the second data can also be indicated by the network device to the terminal device.

[0057] First dataset In some implementations, the first dataset can be CSI data shared by multiple terminal devices, including the terminal device (or a public dataset); and / or, the first dataset can be a publicly available dataset; and / or, the first dataset can be a dataset composed of field data collected by the terminal devices (or a field dataset). The field dataset consists of field data, which can be reported by the terminal devices to the network devices.

[0058] The first dataset has corresponding identification information, which may be represented by ID, symbol, signaling, or other means. Alternatively, the identification information of the first dataset may be determined based on the identification information of the original dataset to which the first dataset corresponds. Here, the original dataset is a dataset that includes both the first and second datasets. Corresponding to the original dataset, the first dataset may also be called the transmission dataset.

[0059] The identification information of the first dataset can be formed by adding a prefix and / or suffix to the identification information of the original dataset, or the identification information of the first dataset can be formed by transforming the identification information of the original dataset based on predetermined rules.

[0060] For example, the original dataset includes both the first data and the second data, and the identification information of the original dataset is ID1. The first dataset includes the first data but does not include the second data, and the identification information of the first dataset is ID2. Here, ID2 is formed by adding a prefix or suffix to ID1, or ID2 is formed by expanding, padding, repeating, etc. of ID1.

[0061] The decoder model of the network device corresponds to the encoder model of the terminal device. The pairing of the encoder and decoder models is indicated by a pairing identifier. The encoder and decoder models can share the same pairing identifier, to which both the original dataset and the first dataset are attached.

[0062] Furthermore, the CSI data in the first dataset may be at least a portion of the CSI data in the original dataset, or the first dataset may also include other CSI data besides those in the original dataset. That is, the CSI data in the first dataset may at least partially overlap with the CSI data in the original dataset and / or include non-overlapping CSI data.

[0063] The identification information corresponding to the first dataset can be transmitted to the terminal device, for example, carried in auxiliary information of the model, files (e.g., records or logs), RRC signaling, or configuration information of the first dataset. Auxiliary information used for model training can be transmitted to the terminal device during the training process of the bilateral model.

[0064] In this embodiment, the first data includes, for example, one or more of the following: target CSI data (or simply target CSI) obtained by the terminal device through channel measurement; CSI load data (or simply CSI load or CSI feedback load) obtained by compressing the target CSI data; data generated during the training process of the network device's model; and target CSI data and / or CSI load data reported by other terminal devices to the network device. The second data includes, for example, target CSI data and / or CSI load data, such as target CSI data and / or CSI load data previously reported by the terminal device to the network device and / or already stored.

[0065] In this context, target CSI data refers to CSI data obtained by the terminal device through channel measurement. Target CSI data can accurately reflect the actual state of the channel and is often considered as ground truth. CSI payload data refers to CSI data obtained by compressing the target CSI data. Both target CSI data and CSI payload data have their own identifiers. In this embodiment, target CSI can be replaced with ground truth, and CSI payload can be replaced with CSI feedback payload. The CSI payload data can, for example, carry CSI feedback reported by the terminal device.

[0066] Typically, in certain datasets, a target CSI data point is associated with one or more CSI load data points, or in other words, each target CSI data point corresponds to one or more CSI load data points. For example, different CSI load data points can be generated based on different configuration information. This configuration information includes, for example, one or more of the following: latent vector size, quantization method, number of antenna ports, number of antenna panels, number of subbands used for CSI measurement, channel bandwidth used for CSI measurement, number of transmission layers (i.e., layer number), number of ranks, channel conditions for CSI measurement, CSI measurement scenario (e.g., high-speed mobile, low-speed mobile, indoor, outdoor), and channel type used for CSI measurement. For example, CSI load data is a quantized latent vector, where the latent vector refers to the output of the encoder model. The latent vector is the CSI load data obtained after compressing the target CSI. The CSI load data is associated with the latent vector size, quantization method, number of ports, number of subbands, or number of panels, etc. Each layer can use the same or different quantization methods.

[0067] Additionally, in some datasets, a target CSI can be associated with one or more configured CSI feedbacks; that is, a target CSI data point corresponds to a CSI feedback with one or more CSI payload data sizes. Different CSI feedbacks can be generated based on different configuration information, such as one or more of the following: channel bandwidth for CSI measurement, number of subbands, number of ports, number of ranks, number of antenna panels, channel conditions for the CSI measurement channel, CSI measurement scenario (e.g., high-speed mobile, low-speed mobile, indoor, outdoor), bandwidth, L1-SINR value, L1-RSRP value, channel type, etc.

[0068] In some implementations, the first dataset may include multiple data subsets. A terminal device may be associated with at least one of these subsets; or, a terminal device may be associated with a first dataset.

[0069] Specifically, when collecting CSI data, the CSI data reported by a terminal device can be organized into one or more first datasets, meaning the first dataset is a terminal device-specific dataset. In this case, the first information sent by the network device to the terminal device can carry an identifier of the first dataset associated with the terminal device. Alternatively, when collecting CSI data, the CSI data reported by a terminal device can be organized into one or more data subsets, with a first dataset comprising one or more data subsets. In this case, the first information sent by the network device to the terminal device can carry an identifier of one or more data subsets associated with the terminal device.

[0070] The CSI data in the first dataset may include CSI data reported by the terminal device to the network device within a predetermined time period (e.g., a short period of time), such as target CSI data and / or CSI load data.

[0071] As an example, Figure 4The original dataset corresponding to the first dataset is shown. The original dataset includes one or more data subsets, such as data subset 1, data subset 2, etc. Data subset 1 includes multiple target CSI data, such as target CSI11, target CSI12, etc. The identification information of the target CSI data can use the corresponding report ID, resource ID, or other identifiers. Data subset 1 also includes CSI load data. Each target CSI data in data subset 1 is associated with M CSI load data. For example, target CSI11 is associated with CSI11-Load 1, CSI11-Load 2, ..., CSI11-Load M, and target CSI12 is associated with CSI12-Load 1, CSI12-Load 2, ..., CSI12-Load M. Similarly, data subset 2 includes multiple target CSI data, such as target CSI21, target CSI21, etc. The identification information of the target CSI data can use the corresponding report ID, resource ID, or other identifiers. Data subset 2 also includes CSI load data. Each target CSI data in data subset 2 is associated with M CSI load data. For example, target CSI 21 is associated with CSI 21-load 1, CSI 21-load 2, ..., CSI 21-load M, and target CSI 22 is associated with CSI 22-load 1, CSI 22-load 2, ..., CSI 22-load M.

[0072] Figure 5 It shows Figure 4 The first dataset corresponding to the original dataset, and Figure 4 compared to, Figure 5The first dataset shown does not include target CSI 11 in data subset 1 of the original dataset, nor CSI 21-load 1 associated with target CSI 21 in data subset 2. The identification information of target CSI 11 in data subset 1 and the identification information of CSI 21-load 1 associated with target CSI 21 in data subset 2 can be used as part of the auxiliary information of the model. Based on the identification information of target CSI 11 in received data subset 1 and the identification information of CSI 21-load 1 associated with target CSI 21 in data subset 2, the terminal device knows that the first dataset does not include target CSI 11 in data subset 1 or CSI 21-load 1 associated with target CSI 21 in data subset 2. It then identifies target CSI 11 in data subset 1 and CSI 21-load 1 associated with target CSI 21 in data subset 2 from the already stored CSI data. Combining this with the CSI data in received dataset 1, the terminal device performs model training, fine-tuning, or retraining. Auxiliary information and the first dataset can be sent to the terminal device simultaneously, separately, or determined by the terminal device itself.

[0073] The first dataset may also omit some data, for example, one or more target CSI data, or one or more CSI load data associated with the target CSI, or CSI load data carried in one or more CSI feedbacks associated with the target CSI.

[0074] Optionally, the first dataset sent by the network device to the terminal device may also include configuration information from the terminal device's data collection process or model training process, such as port, subband, training precision, and accuracy requirements (e.g., SGCS value, loss function, etc.). A target CSI data point in the first dataset is associated with multiple (e.g., M) CSI payload data points, which are generated based on different CSI quantization methods, layer numbers, and other configurations. Some of these CSI payload data points may be reported by the terminal device to the network device, some may be generated during the network device's model training process, and some may be reported by other terminal devices to the network device.

[0075] CSI data organization The CSI data described in this application embodiment includes, but is not limited to, target CSI data and / or load CSI data and / or CSI data collected by the terminal device in various ways (e.g., received from network devices or generated during model training) for model training, fine-tuning, or retraining.

[0076] As mentioned above, the second data may be CSI data that the terminal device has already reported, acquired, or stored. Based on the first information, the terminal device can determine the second data for model training from its stored CSI data. This CSI data can be organized in the form of files (e.g., logs or records). When reporting CSI data, the terminal device can perform layer 1 or layer 3 reporting. Furthermore, when reporting CSI data, the terminal device can store or record the reported CSI data in a file. In this embodiment, "storage" includes temporary storage and / or permanent storage.

[0077] For example, in addition to CSI data (e.g., CSI target data and / or CSI load data), the files or logs used by the terminal device to store CSI data may also include one or more of the following: identification information corresponding to the CSI data; timestamp information corresponding to the CSI data; and filter information related to the reporting of CSI data. These are described below.

[0078] The identification information corresponding to CSI data may include one or more of the following: the identification information of the terminal device; the identifier of the CSI resource configuration corresponding to the CSI data; the identifier of the CSI reporting configuration corresponding to the CSI data (CSI-ReportConfigID); the model identifier (model ID); the model pairing identifier (pairing ID); the number of the CSI data; and the CSI identifier used for CSI reporting.

[0079] The identification information of the terminal device includes, for example, UE ID, subscription permanent identifier (SUPI), subscription concealed identifier (SUCI), permanent equipment identifier (PEI), or cell radio network temporary identifier (C-RNTI), cell identifier (CellID) of the cell where the terminal device is located, or serving cell identifier or component carrier ID (CC ID), etc.

[0080] The identifiers for CSI resource configurations corresponding to CSI data include, for example, the CSI-ResourcePair identifier, the CSI-ResourceGroup identifier, the bandwidth part (BWP) identifier, the CSI-RS Resource Set ID identifier, the CSI-ResourceConfigId identifier, and the CSI-ResourcePeriodicityAndOffset identifier. Each CSI data identifier can be associated with a target CSI data set, and / or with the CSI load data corresponding to a target CSI data set, and / or with a CSI feedback. When these identifiers are exchanged between the terminal device and the network device, they can be encrypted to protect the privacy of the terminal device and prevent terminal device-related identifiers from being transmitted over the air interface in plaintext or with simple encoding (e.g., Turbo code encoding). As an example, CSI data can be jointly identified using CSI-ReportConfigID, and / or CSI-ResourceSetID, and / or model ID, and / or pairing ID.

[0081] The CSI data numbering mentioned above is determined based on one or more of the following: the location of the CSI data in a file or log; the reporting order of the CSI data (i.e., which report); the dataset to which the CSI data belongs; the subset of data in the dataset to which the CSI data belongs; and the reporting time of the CSI data.

[0082] For example, if the target CSI data reported by the terminal device is associated with M CSI load data, then each CSI load data can be numbered according to its position in the M CSI load data. For example, the first CSI load data in the M CSI load data is numbered CSI load-1, the second CSI load data is numbered CSI load-2, the third CSI load data is numbered CSI load-3, ..., and the Mth CSI load data is numbered CSI load-M, where M is a positive integer.

[0083] For example, the Mth CSI load data associated with the Lth target CSI data in the dataset can be recorded as {L:M}.

[0084] When establishing the association between CSI data and data numbers, the association can be recorded based on one or more of the following: {Data ID: CSI data reporting time or reporting order}; {Data ID: CSI ID reported by the terminal device}; {Data ID: Identification Information}, which includes one or more of the following: csi-ReportConfigId, CSI resourceSetID, reportConfigType {e.g., periodic, semiPersistent, aperiodic}, timestamp, reporting resource (e.g., puch-ResourceId, ConfiguredGrantConfig (e.g., configuredGrantTimer+timeDomainOffset+frequencyHoppingOffset)); {Data ID: CSI data location in the dataset: CSI ID reported by the terminal}; {Data ID: The data location of CSI data in the dataset}; {Data ID: The ID of the CSI data within the subset of the dataset}.

[0085] The aforementioned CSI ID refers to an identifier inferred from one or more of the following: csi-ReportConfigId, CSI resourceSetID, reportConfigType {e.g., periodic, semiPersisten, aperiodic}, timestamp, and reporting resource (e.g., puch-ResourceId, ConfiguredGrantConfig(configuredGrantTimer+timeDomainOffset+frequencyHoppingOffset)).

[0086] The identification information of the target CSI data is determined, for example, based on the position of the target CSI data in the subset of data to which the dataset belongs, or based on the position of the target CSI data in the corresponding row / column in a subset of data, or based on the CSI load associated with the target CSI data.

[0087] For example, without adding additional identifiers, at least two of the identifiers such as CSI-reportConfigID, model ID, pairing ID, reporting time, CSI group ID, and CSI resource set ID can be combined to indicate the target CSI data. Alternatively, the target CSI data and / or CSI feedback can be numbered according to the order in which they are reported by the terminal device or received by the network device, serving as an index or identifier used when storing CSI data in a file. For example, the data number corresponding to the Mth CSI load data associated with the Lth target CSI data in subset 1 of dataset 1 can be denoted as {dataset 1, subset 1, Lth target CSI data, Mth CSI load data}.

[0088] Terminal devices and network devices can retrieve or determine the corresponding CSI data through the aforementioned identification information or data number.

[0089] The aforementioned CSI data and / or the corresponding identification information can be sent from the terminal device to the network device, and / or from the network device to the terminal device.

[0090] The files or logs on the terminal device used to store CSI data may also record the reporting time of each CSI data point, or in other words, a timestamp. A timestamp corresponds to a single reported CSI data point (e.g., a target CSI and / or CSI feedback), or to CSI data reported over a period of time (e.g., target CSI and / or CSI feedback). Each target CSI can be associated with one or more CSI feedbacks. CSI feedback carries the CSI payload data (or CSI feedback payload) obtained by quantizing the latent vector output from the model compression. The size of the CSI feedback is related to the size of the CSI payload, the number of layers, the number of subbands, etc. Typically, the same transport layer uses the same quantization method.

[0091] The files or logs on the terminal device used to store CSI data may also record filter information (e.g., filter identifiers). Filters are used to filter the CSI data reported by the terminal device to ensure that the reported CSI data meets certain conditions, such as meeting specific configurations or requirements (e.g., L-SINR greater than 10 dB). The unit of filtering can be a dataset, a subset of data in a dataset, a target CSI data set, or a CSI load data set.

[0092] Recording CSI data The above describes how terminal devices organize and record the CSI data they report. Similarly, network devices also need to record the CSI data reported by terminal devices. When collecting data, network devices can collect CSI data reported by one or more terminal devices, or collect data generated by the network device during model training, and form corresponding records.

[0093] In some implementations, the network device can send CSI record information (or CSI records, CSI logs, etc.) and / or the corresponding number or identifier to the terminal device. Correspondingly, the terminal device receives the CSI record information and / or the corresponding number or identifier sent by the network device. The CSI record information is used to indicate the CSI data reported by the terminal device, which is recorded by the network device. This CSI record can be sent to the terminal device at a specific time point, periodically, or non-periodically, to indicate the CSI data reported by the terminal device within a certain period (e.g., the most recent period). The CSI record information can be carried in RRC signaling, files (e.g., logs or records), or other signaling.

[0094] In some implementations, CSI record information includes identification information corresponding to the CSI data reported by the terminal device.

[0095] In some implementations, CSI record information is associated with terminal devices (i.e., CSI record information is UE-specific, with one CSI record information corresponding to each terminal device or one CSI record information corresponding to each dataset of each terminal device); and / or, CSI record information is associated with multiple terminal devices, including terminal devices; and / or, CSI record information is associated with network devices (i.e., CSI record information is base station-specific, with one CSI record information corresponding to each base station or one CSI record information corresponding to each dataset of each base station); and / or, CSI record information is associated with datasets (i.e., one CSI record information is customized for each dataset); and / or, CSI record information is associated with multiple datasets; and / or, CSI record information is associated with models (i.e., CSI record information is model-specific, for example, one CSI record information corresponding to each pairing identifier).

[0096] CSI record information can be transmitted in various forms. For example, CSI record information can be sent simultaneously with the first dataset; or, for example, CSI record information can be sent separately from the first dataset; or, for example, CSI record information can be included in the first dataset; or, for example, CSI record information can be excluded from the first dataset.

[0097] For example, such as Figure 6 As shown, the network device sends CSI record information to the terminal device, which includes the identification information corresponding to the most recently reported CSI data by the terminal device, recorded by the network device. After receiving the CSI record information, the terminal device can reply with confirmation to the network device. The sending of this CSI record information is relatively independent.

[0098] For example, such as Figure 7 As shown, the network device sends CSI record information to the terminal device, which includes the identification information corresponding to the CSI data recently reported by the terminal device recorded by the network device. The CSI record information can be sent at the same time as the first dataset, or it can be included in the first dataset (i.e., sent as part of the first dataset).

[0099] When collecting data, network devices can, for example, number the CSI data reported by terminal devices and periodically or non-periodically send this numbering information to the terminal devices to align the numbers of the CSI data recorded by the network devices and the terminal devices. In some cases, this numbering information may only be transmitted to the terminal devices at the end of the data collection process.

[0100] Whether a terminal device supports the first dataset can be determined by the capabilities of the terminal device. For example, in some implementations, the terminal device can send its capability information to the network device. Accordingly, the network device receives the capability information of the terminal device. This capability information indicates one or more of the following: the terminal device is capable of temporarily storing CSI data (or, indicates that it cannot permanently store CSI data); the terminal device is capable of permanently storing CSI data (or, indicates whether it has the capability to permanently store CSI data); the terminal device is capable of storing CSI data acquired within a predetermined duration; the terminal device supports the first dataset (e.g., supports both the first dataset and the original dataset); the terminal device does not support the first dataset (e.g., only supports the original dataset); the second data not included in the first dataset supported by the terminal device is of a predetermined type (e.g., only supports datasets that do not include CSI payload data and / or target CSI data and / or other data types); the size of the storage space used by the terminal device to store CSI data; the number of CPUs or CPU usage of the terminal device; the number of GPUs or GPU usage of the terminal device. Capability information can be, for example, carried in an applicability report.

[0101] For example, the capability information includes a first bit, where the value of the first bit is a first value (e.g., 1) indicating that the terminal device supports the first dataset; or the value of the first bit is a second value (e.g., 0) indicating that the terminal device does not support the first dataset.

[0102] For example, the capability information includes a second bit. If the value of the second bit is a third value (e.g., true), it means that the terminal device can permanently store CSI data; if the value of the second bit is a third value (e.g., false), it means that the terminal device can only temporarily store CSI data.

[0103] Optionally, the capabilities of the terminal device can be configured. For example, the terminal can be configured to retain data for a predetermined period (e.g., a past period or time range), such as CSI data reported over the past day, week, month, or year. This timeframe can also be reported to the network device as capability information. Alternatively, this timeframe can be configured by the network device or sent to the terminal device.

[0104] In addition, the scheduled time may be associated with the first dataset, and / or with a subset of data in the first dataset, and / or with the storage time of the first dataset, and / or with the storage time of the subset of data, and / or with auxiliary information, and / or with the storage time of the auxiliary information.

[0105] Optionally, if the terminal device has deleted the corresponding data record, it indicates that the terminal device does not support the first dataset, that is, it does not support omitting or excluding certain data in the dataset. The terminal device can indicate to the network device that it has deleted the saved data, or notify the network device that it does not support the first dataset. In this case, if the network device needs to send a dataset for model training to the terminal device, it needs to send a dataset carrying the complete data (i.e., a dataset that includes both the first and second data, or the original dataset) to the terminal device.

[0106] Model testing After training, the model can be tested. In some implementations, the terminal device can send second information to the network device. Correspondingly, the network device receives the second information sent by the terminal device. The second information is used to indicate third data, which is used for testing the terminal device's model.

[0107] The second information may include, for example, the identification information corresponding to the third data. This avoids wasting air interface resources and increasing the power consumption of terminal devices by repeatedly transmitting CSI data over the air interface. The identification information corresponding to the third data may refer to the implementation methods of the various identification information corresponding to CSI data mentioned above. For example, the identification information corresponding to the third data may include one or more of the following: the reporting time of the third data; the group identifier corresponding to the third data; the identifier of the CSI resource configuration corresponding to the third data; the identifier of the CSI reporting configuration corresponding to the third data; the model identifier; and the model pairing identifier.

[0108] Processing of the first dataset in cell handover scenarios The terminal device may undergo cell handover. At this time, the target base station may send a first dataset to the terminal device. For example, the first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: part or all of the CSI data obtained by the target base station from the source base station for model training; CSI data collected by the target base station for model training.

[0109] For example, such as Figure 8 As shown, the source base station can send some or all of its collected CSI data and / or CSI record information (e.g., CSI data and / or CSI record information that meet specific conditions) to the target base station. The target base station can construct its own first dataset based on the CSI data and / or CSI record information obtained from the source base station; or, the target base station can construct its own first dataset based on the CSI data and / or CSI record information obtained from the source base station, combined with its own collected CSI data and / or its own CSI records.

[0110] In other words, the first dataset sent by the target base station to the terminal device may include part or all of the content of the first dataset sent by the source base station. The first dataset sent by the target base station to the terminal device may be the same as or different from the first dataset sent by the source base station.

[0111] Similarly, the first information sent by the target base station to indicate the second data may be the same as or different from the first information sent by the source base station. That is, the target base station can decide for itself whether to omit or exclude the second data in the first dataset it sends to the terminal device, and indicate this to the terminal device through the first information.

[0112] Optionally, the first dataset sent by the target base station to the terminal device may not include the CSI data already sent to the terminal device by the source base station and / or may only carry the identification information corresponding to this CSI data.

[0113] See also Figure 8The source base station of the terminal device has collected data, but the terminal device has not downloaded the corresponding dataset. After the terminal device switches from the source base station to the target base station, the source base station can transmit the corresponding dataset and corresponding CSI record information to the terminal device, or the target base station can transmit the corresponding dataset and corresponding CSI record information to the terminal device.

[0114] For example, the target base station can query the source base station to see if it has a dataset that meets certain conditions.

[0115] For example, the source base station replies to the target base station that it has a dataset and transmits the corresponding dataset and CSI record information.

[0116] For example, when the terminal device needs to use the first dataset for model training, the target base station transmits the corresponding dataset and CSI record information to the terminal device.

[0117] The source base station may transmit only a portion of the CSI data from its collected dataset to the target base station, such as partial target CSI data and / or CSI payload data. The target base station uses the CSI data received from the source base station and combines it with its own model to reconstruct a first dataset corresponding to the target base station, and sends this first dataset to the terminal device during model training.

[0118] The aforementioned source base station and target base station should, for example, belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

[0119] The above text combined Figures 1 to 8 The method embodiments of this application are described in detail below, in conjunction with... Figures 9 to 11 The present application provides a detailed description of the apparatus embodiments. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the foregoing method embodiments.

[0120] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 9 The terminal device 900 shown may include a transceiver unit 910. The transceiver unit 910 is used to receive a first dataset sent by a network device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

[0121] In some implementations, the transceiver unit 910 is further configured to: receive first information sent by the network device, the first information being used to indicate the second data.

[0122] In some implementations, the first information includes the identification information corresponding to the second data.

[0123] In some implementations, the identification information of the second data includes one or more of the following, or a combination of at least two of them: the reporting time of the second data; the identifier of the data subset to which the second data belongs; the identifier of the dataset to which the second data belongs; the identifier of the CSI resource configuration corresponding to the second data; the identifier of the CSI reporting configuration corresponding to the second data; the identifier of the model; and the pairing identifier of the model.

[0124] In some implementations, the first information is sent simultaneously with the first dataset, or the first information is sent at different times from the first dataset; and / or, the first information is included in the first dataset, or the first information is not included in the first dataset.

[0125] In some implementations, the first information is carried in one or more of the following: RRC signaling; files; logs; configuration information of the first dataset; and auxiliary information for model training.

[0126] In some implementations, the first data includes one or more of the following: target CSI data obtained by the terminal device through channel measurement; CSI load data obtained by compressing the target CSI data; and data generated during the training process of the network device's model.

[0127] In some implementations, the transceiver unit 910 is further configured to: send CSI data to the network device, the CSI data including the second data.

[0128] In some implementations, the file or log of the terminal device used to store CSI data further includes one or more of the following: The identification information corresponding to the CSI data; the timestamp information corresponding to the CSI data; and the filter information related to the reporting of the CSI data.

[0129] In some implementations, the identification information corresponding to the CSI data includes one or more of the following: the identifier of the terminal device; the identifier of the CSI resource configuration corresponding to the CSI data; the identifier of the CSI reporting configuration corresponding to the CSI data; the identifier of the model; the pairing identifier of the model; and the number of the CSI data.

[0130] In some implementations, the identification information of the terminal device includes one or more of the following: the identifier of the terminal device; the SUPI of the terminal device; the SUCI of the terminal device; the PEI of the terminal device; the C-RNTI of the terminal device; and the identifier of the cell where the terminal device is located.

[0131] In some implementations, the number of the CSI data is determined based on one or more of the following: the position of the CSI data in the file or log; the reporting order of the CSI data; the dataset to which the CSI data belongs; and the subset of data to which the CSI data belongs in the dataset.

[0132] In some implementations, the CSI data includes: target CSI data obtained by the terminal device through channel measurement; and CSI load data obtained by compressing the target CSI data; wherein the target CSI data and the CSI load data have their own identifiers.

[0133] In some implementations, the transceiver unit 910 is further configured to: receive CSI record information sent by the network device, the CSI record information being used to indicate the CSI data reported by the terminal device recorded by the network device.

[0134] In some implementations, the CSI record information includes identification information corresponding to the CSI data reported by the terminal device.

[0135] In some implementations, the CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, the CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

[0136] In some implementations, the transceiver unit 910 is further configured to: send capability information of the terminal device to the network device, the capability information indicating one or more of the following: the terminal device is capable of temporarily storing CSI data; the terminal device is capable of permanently storing CSI data; the terminal device is capable of storing CSI data acquired within a predetermined duration; the terminal device supports the first dataset; the terminal device does not support the first dataset; the second data not included in the first dataset supported by the terminal device is of a predetermined type.

[0137] In some implementations, the CSI record information is associated with the terminal device; and / or, the CSI record information is associated with multiple terminal devices, including the terminal device; and / or, the CSI record information is associated with the network device; and / or, the CSI record information is associated with a dataset; and / or, the CSI record information is associated with multiple datasets; and / or, the CSI record information is associated with the model.

[0138] In some implementations, the transceiver unit 910 is further configured to: send second information to the network device, the second information being used to indicate third data, the third data being used for testing the model of the terminal device.

[0139] In some implementations, the second information includes the identification information corresponding to the third data.

[0140] In some implementations, the identification information corresponding to the third data includes one or more of the following: the reporting time of the third data; the group identifier corresponding to the third data; the identifier of the CSI resource configuration corresponding to the third data; the identifier of the CSI reporting configuration corresponding to the third data; the identifier of the model; and the pairing identifier of the model.

[0141] In some implementations, the network device is the source base station of the terminal device; or, the network device is the target base station of the terminal device.

[0142] In some implementations, the first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: part or all of the CSI data for model training obtained by the target base station from the source base station; CSI data for model training collected by the target base station.

[0143] In some implementations, the source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

[0144] In some implementations, the first dataset is CSI data shared by multiple terminal devices, including the terminal device; and / or, the first dataset is a publicly available dataset; and / or, the first dataset is a dataset composed of field data collected by the terminal device.

[0145] It is understood that the transceiver unit 910 is, for example, a transceiver 1130. Optionally, the terminal device 900 also includes a processor 1110 and a memory 1120, for example, such as... Figure 11 As shown.

[0146] Figure 10 This is a schematic diagram of the network device provided in an embodiment of this application. Figure 10 The network device 1000 shown may include a transceiver unit 1010. The transceiver unit 1010 is used to send a first dataset to a terminal device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

[0147] In some implementations, the transceiver unit 1010 is further configured to: send first information to the terminal device, wherein the first information is used to indicate the second data.

[0148] In some implementations, the first information includes the identification information corresponding to the second data.

[0149] In some implementations, the identification information of the second data includes one or more of the following, or a combination of at least two of them: the reporting time of the second data; the identifier of the data subset to which the second data belongs; the identifier of the dataset to which the second data belongs; the identifier of the CSI resource configuration corresponding to the second data; the identifier of the CSI reporting configuration corresponding to the second data; the identifier of the model; and the pairing identifier of the model.

[0150] In some implementations, the first information is sent simultaneously with the first dataset, or the first information is sent at different times from the first dataset; and / or, the first information is included in the first dataset, or the first information is not included in the first dataset.

[0151] In some implementations, the first information is carried in one or more of the following: RRC signaling; files; logs; configuration information of the first dataset; and auxiliary information for model training.

[0152] In some implementations, the first data includes one or more of the following: target CSI data obtained by the terminal device through channel measurement; CSI load data obtained by compressing the target CSI data; and data generated during the training process of the network device's model.

[0153] In some implementations, the transceiver unit 1010 is further configured to: receive CSI data sent by the terminal device, wherein the CSI data includes the second data.

[0154] In some implementations, the file or log of the terminal device used to store CSI data may also include one or more of the following: identification information corresponding to the CSI data; timestamp information corresponding to the CSI data; and filter information related to the reporting of the CSI data.

[0155] In some implementations, the identification information corresponding to the CSI data includes one or more of the following: the identifier of the terminal device; the identifier of the CSI resource configuration corresponding to the CSI data; the identifier of the CSI reporting configuration corresponding to the CSI data; the identifier of the model; the pairing identifier of the model; and the number of the CSI data.

[0156] In some implementations, the identification information of the terminal device includes one or more of the following: the identifier of the terminal device; the SUPI of the terminal device; the SUCI of the terminal device; the PEI of the terminal device; the C-RNTI of the terminal device; and the identifier of the cell where the terminal device is located.

[0157] In some implementations, the number of the CSI data is determined based on one or more of the following: the position of the CSI data in the file or log; the reporting order of the CSI data; the dataset to which the CSI data belongs; and the subset of data to which the CSI data belongs in the dataset.

[0158] In some implementations, the CSI data includes: target CSI data obtained by the terminal device through channel measurement; and CSI load data obtained by compressing the target CSI data; wherein the target CSI data and the CSI load data have their own identifiers.

[0159] In some implementations, the transceiver unit 1010 is further configured to: send CSI record information to the terminal device, the CSI record information being used to indicate the CSI data reported by the terminal device recorded by the network device.

[0160] In some implementations, the CSI record information includes identification information corresponding to the CSI data reported by the terminal device.

[0161] In some implementations, the CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, the CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

[0162] In some implementations, the transceiver unit 1010 is further configured to: send capability information of the terminal device to the network device, the capability information indicating one or more of the following: the terminal device is capable of temporarily storing CSI data; the terminal device is capable of permanently storing CSI data; the terminal device is capable of storing CSI data acquired within a predetermined duration; the terminal device supports the first dataset; the terminal device does not support the first dataset; the second data not included in the first dataset supported by the terminal device is of a predetermined type.

[0163] In some implementations, the CSI record information is associated with the terminal device; and / or, the CSI record information is associated with multiple terminal devices, including the terminal device; and / or, the CSI record information is associated with the network device; and / or, the CSI record information is associated with a dataset; and / or, the CSI record information is associated with multiple datasets; and / or, the CSI record information is associated with the model.

[0164] In some implementations, the transceiver unit 1010 is further configured to: receive second information sent by the terminal device, the second information being used to indicate third data, the third data being used for testing the model of the terminal device.

[0165] In some implementations, the second information includes the identification information corresponding to the third data.

[0166] In some implementations, the identification information corresponding to the third data includes one or more of the following: the reporting time of the third data; the group identifier corresponding to the third data; the identifier of the CSI resource configuration corresponding to the third data; the identifier of the CSI reporting configuration corresponding to the third data; the identifier of the model; and the pairing identifier of the model.

[0167] In some implementations, the network device is the source base station of the terminal device; or, the network device is the target base station of the terminal device.

[0168] In some implementations, the first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: part or all of the CSI data for model training obtained by the target base station from the source base station; CSI data for model training collected by the target base station.

[0169] In some implementations, the source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

[0170] In some implementations, the first dataset is CSI data shared by multiple terminal devices, including the terminal device; and / or, the first dataset is a publicly available dataset; and / or, the first dataset is a dataset composed of field data collected by the terminal device.

[0171] In some implementations, the identification information of the first dataset is determined based on the identification information of the original dataset corresponding to the first dataset, wherein the original dataset is a dataset that includes both the first data and the second data.

[0172] It is understood that the transceiver unit 1010 is, for example, a transceiver 1130. Optionally, the network device 1000 also includes a processor 1110 and a memory 1120, for example, as Figure 11 As shown.

[0173] Figure 11 This is a schematic structural diagram of a communication apparatus according to an embodiment of this application. Figure 11 The dashed lines shown indicate that the unit or module is optional. Device 1100 can be used to implement the methods described in the above method embodiments. Device 1100 may be, for example, a chip, a terminal device, or a network device.

[0174] Apparatus 1100 may include one or more processors 1110. Processor 1110 may support apparatus 1100 in implementing the methods described in the foregoing method embodiments. Processor 1110 may be a general-purpose processor or a special-purpose processor. For example, processor 1110 may be a central processing unit (CPU). Alternatively, processor 1110 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors may be microprocessors or any conventional processor.

[0175] The apparatus 1100 may further include one or more memories 1120. The memories 1120 store programs that can be executed by the processor 1110, causing the processor 1110 to perform the methods described in the above method embodiments. The memories 1120 may be independent of the processor 1110, or they may be integrated into the processor 1110.

[0176] The device 1100 may also include a transceiver 1130. The processor 1110 can communicate with other devices or chips via the transceiver 1130. For example, the processor 1110 can send and receive data with other devices or chips via the transceiver 1130.

[0177] This application also provides a communication system. The communication system includes the terminal device and network device described above. In some implementations, the system further includes other devices that interact with the terminal device and network device.

[0178] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal device or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0179] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal device or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0180] This application also provides a computer program. This computer program can be applied to the terminal device or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0181] It should be understood that the terms "system" and "network" in the embodiments of this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of this application and is not intended to limit this application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0182] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0183] In the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0184] In the embodiments of this application, the term "correspondence" can indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0185] In this application embodiment, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0186] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0187] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0188] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0189] In the several embodiments provided in this application, it is understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0190] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in the same position or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0191] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0192] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state drives (SSDs)).

[0193] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: The terminal device receives a first dataset sent by the network device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

2. The method according to claim 1, characterized in that, The method further includes: The terminal device receives first information sent by the network device, the first information being used to indicate the second data.

3. The method according to claim 2, characterized in that, The first information includes the identification information corresponding to the second data.

4. The method according to claim 3, characterized in that, The identification information of the second data includes one or more of the following, or a combination of at least two of them: The reporting time of the second data; The identifier of the dataset to which the second data belongs; The identifier of the data subset to which the second data belongs; The identifier of the CSI resource configuration corresponding to the second data; The identifier corresponding to the CSI reporting configuration of the second data; The identifier of the model; The pairing identifier of the model.

5. The method according to any one of claims 2 to 4, characterized in that, The first information is sent simultaneously with the first dataset, or the first information is not sent simultaneously with the first dataset; and / or, The first information is included in the first dataset, or the first information is not included in the first dataset.

6. The method according to any one of claims 2 to 5, characterized in that, The first information is carried in one or more of the following: RRC signaling; document; log; Configuration information for the first dataset; Auxiliary information used for model training.

7. The method according to any one of claims 1 to 6, characterized in that, The first data includes one or more of the following: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The data generated during the training process of the network device's model.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The terminal device stores and sends CSI data to the network device, the CSI data including the second data.

9. The method according to any one of claims 1 to 8, characterized in that, The files or logs used by the terminal device to store CSI data also include one or more of the following: The identification information corresponding to the CSI data; The timestamp information corresponding to the CSI data; Information about filters associated with the reporting of the CSI data.

10. The method according to claim 9, characterized in that, The identification information corresponding to the CSI data includes one or more of the following: The identifier of the terminal device; The identifier of the CSI resource configuration corresponding to the CSI data; The identifier corresponding to the CSI reporting configuration of the CSI data; The identifier of the model; The pairing identifier of the model; The numbering of the CSI data.

11. The method according to claim 10, characterized in that, The identification information of the terminal device includes one or more of the following: The identifier of the terminal device; The SUPI of the terminal device; The SUCI of the terminal device; The PEI of the terminal device; The terminal device's C-RNTI; The identifier of the cell where the terminal device is located.

12. The method according to claim 10 or 11, characterized in that, The numbering of the CSI data is determined based on one or more of the following: The location of the CSI data in the file or log; The order in which the CSI data is reported; The dataset to which the CSI data belongs; The CSI data belongs to the subset of data in the dataset.

13. The method according to any one of claims 9 to 12, characterized in that, The CSI data includes: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The target CSI data and the CSI load data each have their own identifiers.

14. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The terminal device receives CSI record information sent by the network device, and the CSI record information is used to indicate the CSI data reported by the terminal device recorded by the network device.

15. The method according to claim 14, characterized in that, The CSI record information includes the identification information corresponding to the CSI data reported by the terminal device.

16. The method according to claim 14 or 15, characterized in that, The CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, The CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

17. The method according to any one of claims 14 to 16, characterized in that, The method further includes: The terminal device sends its capability information to the network device, the capability information indicating one or more of the following: The terminal device can temporarily store CSI data; The terminal device can permanently store CSI data; The terminal device is capable of storing CSI data acquired within a predetermined time period; The terminal device supports the first dataset; The terminal device does not support the first dataset; The second data, which is not included in the first dataset supported by the terminal device, is a predetermined type.

18. The method according to any one of claims 14 to 17, characterized in that, The CSI record information is associated with the terminal device; and / or, The CSI record information is associated with multiple terminal devices, including the terminal device; and / or, The CSI record information is associated with the network device; and / or, The CSI record information is associated with the dataset; and / or, The CSI record information is associated with multiple datasets; and / or, The CSI record information is associated with the model.

19. The method according to any one of claims 1 to 18, characterized in that, The method further includes: The terminal device sends a second message to the network device, the second message being used to indicate third data, the third data being used for testing the model of the terminal device.

20. The method according to claim 19, characterized in that, The second information includes the identification information corresponding to the third data.

21. The method according to claim 20, characterized in that, The identification information corresponding to the third data includes one or more of the following: The reporting time of the third data; The group identifier corresponding to the third data; The identifier of the CSI resource configuration corresponding to the third data; The identifier corresponding to the CSI reporting configuration of the third data; The identifier of the model; The pairing identifier of the model.

22. The method according to any one of claims 19 to 21, characterized in that, The network device is the source base station of the terminal device; or... The network device is the target base station of the terminal device.

23. The method according to claim 22, characterized in that, The first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: The target base station obtains some or all of the CSI data used for model training from the source base station; The target base station collects CSI data for model training.

24. The method according to claim 22 or 23, characterized in that, The source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

25. The method according to any one of claims 1 to 24, characterized in that, The first dataset is CSI data shared by multiple terminal devices, including the aforementioned terminal device; and / or, The first dataset is a publicly available dataset; and / or, The first dataset is a dataset composed of on-site data collected by the terminal device.

26. The method according to any one of claims 1 to 25, characterized in that, The identification information of the first dataset is determined based on the identification information of the original dataset corresponding to the first dataset, wherein the original dataset is a dataset that includes both the first data and the second data.

27. The method according to claim 26, characterized in that, The identification information of the first dataset is formed by adding a prefix and / or suffix to the identification information of the original dataset, or by transforming the identification information of the original dataset based on predetermined rules.

28. A communication method, characterized in that, include: The network device sends a first dataset to the terminal device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

29. The method according to claim 28, characterized in that, The method further includes: The network device sends first information to the terminal device, the first information being used to indicate the second data.

30. The method according to claim 29, characterized in that, The first information includes the identification information corresponding to the second data.

31. The method according to claim 30, characterized in that, The identification information of the second data includes one or more of the following, or a combination of at least two of them: The reporting time of the second data; The identifier of the dataset to which the second data belongs; The identifier of the data subset to which the second data belongs; The identifier of the CSI resource configuration corresponding to the second data; The identifier corresponding to the CSI reporting configuration of the second data; The identifier of the model; The pairing identifier of the model.

32. The method according to any one of claims 29 to 31, characterized in that, The first information is sent simultaneously with the first dataset, or the first information is not sent simultaneously with the first dataset; and / or, The first information is included in the first dataset, or the first information is not included in the first dataset.

33. The method according to any one of claims 29 to 32, characterized in that, The first information is carried in one or more of the following: RRC signaling; document; log; Configuration information for the first dataset; Auxiliary information used for model training.

34. The method according to any one of claims 28 to 33, characterized in that, The first data includes one or more of the following: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The data generated during the training process of the network device's model.

35. The method according to any one of claims 28 to 34, characterized in that, The method further includes: The network device receives CSI data sent by the terminal device, and the CSI data includes the second data.

36. The method according to any one of claims 28 to 35, characterized in that, The files or logs used by the terminal device to store CSI data also include one or more of the following: The identification information corresponding to the CSI data; The timestamp information corresponding to the CSI data; Information about filters associated with the reporting of the CSI data.

37. The method according to claim 36, characterized in that, The identification information corresponding to the CSI data includes one or more of the following: The identifier of the terminal device; The identifier of the CSI resource configuration corresponding to the CSI data; The identifier corresponding to the CSI reporting configuration of the CSI data; The identifier of the model; The pairing identifier of the model; The numbering of the CSI data.

38. The method according to claim 37, characterized in that, The identification information of the terminal device includes one or more of the following: The identifier of the terminal device; The SUPI of the terminal device; The SUCI of the terminal device; The PEI of the terminal device; The terminal device's C-RNTI; The identifier of the cell where the terminal device is located.

39. The method according to claim 37 or 38, characterized in that, The numbering of the CSI data is determined based on one or more of the following: The location of the CSI data in the file or log; The order in which the CSI data is reported; The dataset to which the CSI data belongs; The CSI data belongs to the subset of data in the dataset.

40. The method according to any one of claims 36 to 39, characterized in that, The CSI data includes: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The target CSI data and the CSI load data each have their own identifiers.

41. The method according to any one of claims 28 to 40, characterized in that, The method further includes: The network device sends CSI record information to the terminal device, and the CSI record information is used to indicate the CSI data reported by the terminal device recorded by the network device.

42. The method according to claim 41, characterized in that, The CSI record information includes the identification information corresponding to the CSI data reported by the terminal device.

43. The method according to claim 41 or 42, characterized in that, The CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, The CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

44. The method according to any one of claims 41 to 43, characterized in that, The method further includes: The terminal device sends its capability information to the network device, the capability information indicating one or more of the following: The terminal device can temporarily store CSI data; The terminal device can permanently store CSI data; The terminal device is capable of storing CSI data acquired within a predetermined time period; The terminal device supports the first dataset; The terminal device does not support the first dataset; The second data, which is not included in the first dataset supported by the terminal device, is a predetermined type.

45. The method according to any one of claims 41 to 44, characterized in that, The CSI record information is associated with the terminal device; and / or, The CSI record information is associated with multiple terminal devices, including the terminal device; and / or, The CSI record information is associated with the network device; and / or, The CSI record information is associated with the dataset; and / or, The CSI record information is associated with multiple datasets; and / or, The CSI record information is associated with the model.

46. ​​The method according to any one of claims 28 to 45, characterized in that, The method further includes: The network device receives second information sent by the terminal device, the second information being used to indicate third data, the third data being used for testing the model of the terminal device.

47. The method according to claim 46, characterized in that, The second information includes the identification information corresponding to the third data.

48. The method according to claim 47, characterized in that, The identification information corresponding to the third data includes one or more of the following: The reporting time of the third data; The group identifier corresponding to the third data; The identifier of the CSI resource configuration corresponding to the third data; The identifier corresponding to the CSI reporting configuration of the third data; The identifier of the model; The pairing identifier of the model.

49. The method according to any one of claims 46 to 48, characterized in that, The network device is the source base station of the terminal device; or... The network device is the target base station of the terminal device.

50. The method according to claim 49, characterized in that, The first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: The target base station obtains some or all of the CSI data used for model training from the source base station; The target base station collects CSI data for model training.

51. The method according to claim 49 or 50, characterized in that, The source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

52. The method according to any one of claims 28 to 51, characterized in that, The first dataset is CSI data shared by multiple terminal devices, including the aforementioned terminal device; and / or, The first dataset is a publicly available dataset; and / or, The first dataset is a dataset composed of on-site data collected by the terminal device.

53. The method according to any one of claims 28 to 52, characterized in that, The identification information of the first dataset is determined based on the identification information of the original dataset corresponding to the first dataset, wherein the original dataset is a dataset that includes both the first data and the second data.

54. The method according to claim 53, characterized in that, The identification information of the first dataset is formed by adding a prefix and / or suffix to the identification information of the original dataset, or by transforming the identification information of the original dataset based on predetermined rules.

55. A terminal device, characterized in that, include: The transceiver unit is used to receive a first dataset sent by a network device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

56. The terminal device according to claim 55, characterized in that, The transceiver unit is also used for: The system receives first information sent by the network device, the first information being used to indicate the second data.

57. The terminal device according to claim 56, characterized in that, The first information includes the identification information corresponding to the second data.

58. The terminal device according to claim 57, characterized in that, The identification information of the second data includes one or more of the following, or a combination of at least two of them: The reporting time of the second data; The identifier of the dataset to which the second data belongs; The identifier of the data subset to which the second data belongs; The identifier of the CSI resource configuration corresponding to the second data; The identifier corresponding to the CSI reporting configuration of the second data; The identifier of the model; The pairing identifier of the model.

59. The terminal device according to any one of claims 56 to 58, characterized in that, The first information is sent simultaneously with the first dataset, or the first information is not sent simultaneously with the first dataset; and / or, The first information is included in the first dataset, or the first information is not included in the first dataset.

60. The terminal device according to any one of claims 56 to 59, characterized in that, The first information is carried in one or more of the following: RRC signaling; document; log; Configuration information for the first dataset; Auxiliary information used for model training.

61. The terminal device according to any one of claims 55 to 60, characterized in that, The first data includes one or more of the following: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The data generated during the training process of the network device's model.

62. The terminal device according to any one of claims 55 to 61, characterized in that, The transceiver unit is also used for: Send CSI data to the network device, the CSI data including the second data.

63. The terminal device according to any one of claims 55 to 62, characterized in that, The files or logs used by the terminal device to store CSI data also include one or more of the following: The identification information corresponding to the CSI data; The timestamp information corresponding to the CSI data; Information about filters associated with the reporting of the CSI data.

64. The terminal device according to claim 63, characterized in that, The identification information corresponding to the CSI data includes one or more of the following: The identifier of the terminal device; The identifier of the CSI resource configuration corresponding to the CSI data; The identifier corresponding to the CSI reporting configuration of the CSI data; The identifier of the model; The pairing identifier of the model; The numbering of the CSI data.

65. The terminal device according to claim 64, characterized in that, The identification information of the terminal device includes one or more of the following: The identifier of the terminal device; The SUPI of the terminal device; The SUCI of the terminal device; The PEI of the terminal device; The terminal device's C-RNTI; The identifier of the cell where the terminal device is located.

66. The terminal device according to claim 64 or 65, characterized in that, The numbering of the CSI data is determined based on one or more of the following: The location of the CSI data in the file or log; The order in which the CSI data is reported; The dataset to which the CSI data belongs; The CSI data belongs to the subset of data in the dataset.

67. The terminal device according to any one of claims 63 to 66, characterized in that, The CSI data includes: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The target CSI data and the CSI load data each have their own identifiers.

68. The terminal device according to any one of claims 55 to 67, characterized in that, The transceiver unit is also used for: The network device receives CSI record information, which is used to indicate the CSI data reported by the terminal device and recorded by the network device.

69. The terminal device according to claim 68, characterized in that, The CSI record information includes the identification information corresponding to the CSI data reported by the terminal device.

70. The terminal device according to claim 68 or 69, characterized in that, The CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, The CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

71. The terminal device according to any one of claims 68 to 70, characterized in that, The transceiver unit is also used for: Send the terminal device's capability information to the network device, the capability information indicating one or more of the following: The terminal device can temporarily store CSI data; The terminal device can permanently store CSI data; The terminal device is capable of storing CSI data acquired within a predetermined time period; The terminal device supports the first dataset; The terminal device does not support the first dataset; The second data, which is not included in the first dataset supported by the terminal device, is a predetermined type.

72. The terminal device according to any one of claims 68 to 71, characterized in that, The CSI record information is associated with the terminal device; and / or, The CSI record information is associated with multiple terminal devices, including the terminal device; and / or, The CSI record information is associated with the network device; and / or, The CSI record information is associated with the dataset; and / or, The CSI record information is associated with multiple datasets; and / or, The CSI record information is associated with the model.

73. The terminal device according to any one of claims 55 to 72, characterized in that, The transceiver unit is also used for: A second message is sent to the network device, the second message being used to indicate third data, the third data being used for testing the model of the terminal device.

74. The terminal device according to claim 73, characterized in that, The second information includes the identification information corresponding to the third data.

75. The terminal device according to claim 74, characterized in that, The identification information corresponding to the third data includes one or more of the following: The reporting time of the third data; The group identifier corresponding to the third data; The identifier of the CSI resource configuration corresponding to the third data; The identifier corresponding to the CSI reporting configuration of the third data; The identifier of the model; The pairing identifier of the model.

76. The terminal device according to any one of claims 73 to 75, characterized in that, The network device is the source base station of the terminal device; or... The network device is the target base station of the terminal device.

77. The terminal device according to claim 76, characterized in that, The first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: The target base station obtains some or all of the CSI data used for model training from the source base station; The target base station collects CSI data for model training.

78. The terminal device according to claim 76 or 77, characterized in that, The source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

79. The terminal device according to any one of claims 55 to 78, characterized in that, The first dataset is CSI data shared by multiple terminal devices, including the aforementioned terminal device; and / or, The first dataset is a publicly available dataset; and / or, The first dataset is a dataset composed of on-site data collected by the terminal device.

80. The terminal device according to any one of claims 55 to 79, characterized in that, The identification information of the first dataset is determined based on the identification information of the original dataset corresponding to the first dataset, wherein the original dataset is a dataset that includes both the first data and the second data.

81. The terminal device according to claim 80, characterized in that, The identification information of the first dataset is formed by adding a prefix and / or suffix to the identification information of the original dataset, or by transforming the identification information of the original dataset based on predetermined rules.

82. A network device, characterized in that, include: The transceiver unit is used to send a first dataset to a terminal device. The first dataset includes first data but does not include second data. Both the first data and the second data are used for training, fine-tuning, or retraining the model of the terminal device.

83. The network device according to claim 82, characterized in that, The transceiver unit is also used for: Send first information to the terminal device, the first information being used to indicate the second data.

84. The network device according to claim 83, characterized in that, The first information includes the identification information corresponding to the second data.

85. The network device according to claim 84, characterized in that, The identification information of the second data includes one or more of the following, or a combination of at least two of them: The reporting time of the second data; The identifier of the dataset to which the second data belongs; The identifier of the data subset to which the second data belongs; The identifier of the CSI resource configuration corresponding to the second data; The identifier corresponding to the CSI reporting configuration of the second data; The identifier of the model; The pairing identifier of the model.

86. The network device according to any one of claims 83 to 85, characterized in that, The first information is sent simultaneously with the first dataset, or the first information is not sent simultaneously with the first dataset; and / or, The first information is included in the first dataset, or the first information is not included in the first dataset.

87. The network device according to any one of claims 83 to 86, characterized in that, The first information is carried in one or more of the following: RRC signaling; document; log; Configuration information for the first dataset; Auxiliary information used for model training.

88. The network device according to any one of claims 82 to 87, characterized in that, The first data includes one or more of the following: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The data generated during the training process of the network device's model.

89. The network device according to any one of claims 82 to 88, characterized in that, The transceiver unit is also used for: The terminal device receives CSI data, which includes the second data.

90. The network device according to any one of claims 82 to 89, characterized in that, The files or logs used by the terminal device to store CSI data also include one or more of the following: The identification information corresponding to the CSI data; The timestamp information corresponding to the CSI data; Information about filters associated with the reporting of the CSI data.

91. The network device according to claim 90, characterized in that, The identification information corresponding to the CSI data includes one or more of the following: The identifier of the terminal device; The identifier of the CSI resource configuration corresponding to the CSI data; The identifier corresponding to the CSI reporting configuration of the CSI data; The identifier of the model; The pairing identifier of the model; The numbering of the CSI data.

92. The network device according to claim 91, characterized in that, The identification information of the terminal device includes one or more of the following: The identifier of the terminal device; The SUPI of the terminal device; The SUCI of the terminal device; The PEI of the terminal device; The terminal device's C-RNTI; The identifier of the cell where the terminal device is located.

93. The network device according to claim 91 or 92, characterized in that, The numbering of the CSI data is determined based on one or more of the following: The location of the CSI data in the file or log; The order in which the CSI data is reported; The dataset to which the CSI data belongs; The CSI data belongs to the subset of data in the dataset.

94. The network device according to any one of claims 90 to 93, characterized in that, The CSI data includes: The target CSI data obtained by the terminal device through channel measurement; The CSI load data obtained after compressing the target CSI data; The target CSI data and the CSI load data each have their own identifiers.

95. The network device according to any one of claims 82 to 94, characterized in that, The transceiver unit is also used for: The network device sends CSI record information to the terminal device, the CSI record information being used to indicate the CSI data reported by the terminal device and recorded by the network device.

96. The network device according to claim 95, characterized in that, The CSI record information includes the identification information corresponding to the CSI data reported by the terminal device.

97. The network device according to claim 95 or 96, characterized in that, The CSI record information is sent simultaneously with the first dataset, or the CSI record information is not sent simultaneously with the first dataset; and / or, The CSI record information is included in the first dataset, or the CSI record information is not included in the first dataset.

98. The network device according to any one of claims 95 to 97, characterized in that, The transceiver unit is also used for: Send the terminal device's capability information to the network device, the capability information indicating one or more of the following: The terminal device can temporarily store CSI data; The terminal device can permanently store CSI data; The terminal device is capable of storing CSI data acquired within a predetermined time period; The terminal device supports the first dataset; The terminal device does not support the first dataset; The second data, which is not included in the first dataset supported by the terminal device, is a predetermined type.

99. The network device according to any one of claims 95 to 98, characterized in that, The CSI record information is associated with the terminal device; and / or, The CSI record information is associated with multiple terminal devices, including the terminal device; and / or, The CSI record information is associated with the network device; and / or, The CSI record information is associated with the dataset; and / or, The CSI record information is associated with multiple datasets; and / or, The CSI record information is associated with the model.

100. The network device according to any one of claims 82 to 99, characterized in that, The transceiver unit is also used for: The terminal device receives second information, which is used to indicate third data, and the third data is used for testing the model of the terminal device.

101. The network device according to claim 100, characterized in that, The second information includes the identification information corresponding to the third data.

102. The network device according to claim 101, characterized in that, The identification information corresponding to the third data includes one or more of the following: The reporting time of the third data; The group identifier corresponding to the third data; The identifier of the CSI resource configuration corresponding to the third data; The identifier corresponding to the CSI reporting configuration of the third data; The identifier of the model; The pairing identifier of the model.

103. The network device according to any one of claims 100 to 102, characterized in that, The network device is the source base station of the terminal device; or... The network device is the target base station of the terminal device.

104. The network device according to claim 103, characterized in that, The first dataset sent by the target base station to the terminal device is constructed based on one or more of the following: The target base station obtains some or all of the CSI data used for model training from the source base station; The target base station collects CSI data for model training.

105. The network device according to claim 103 or 104, characterized in that, The source base station and the target base station belong to a trust group of the terminal device, wherein base stations within the same trust group can transmit CSI data and / or CSI record information for model training of the terminal device.

106. The network device according to any one of claims 82 to 105, characterized in that, The first dataset is CSI data shared by multiple terminal devices, including the aforementioned terminal device; and / or, The first dataset is a publicly available dataset; and / or, The first dataset is a dataset composed of on-site data collected by the terminal device.

107. The network device according to any one of claims 82 to 106, characterized in that, The identification information of the first dataset is determined based on the identification information of the original dataset corresponding to the first dataset, wherein the original dataset is a dataset that includes both the first data and the second data.

108. The network device according to claim 107, characterized in that, The identification information of the first dataset is formed by adding a prefix and / or suffix to the identification information of the original dataset, or by transforming the identification information of the original dataset based on predetermined rules.

109. A terminal device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or send signals so that the terminal device performs the method according to any one of claims 1 to 27.

110. A network device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals so that the network device performs the method according to any one of claims 28 to 54.

111. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the apparatus to perform the method according to any one of claims 1 to 54.

112. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method according to any one of claims 1 to 54.

113. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method according to any one of claims 1 to 54.

114. A computer program product, characterized in that, Includes a program that causes a computer to perform the method according to any one of claims 1 to 54.

115. A computer program, characterized in that, The computer program causes the computer to perform the method according to any one of claims 1 to 54.

Images