Wireless communication method, terminal device, and network device

Abstract

Provided are a wireless communication method, a terminal device, and a network device. The method comprises: a terminal device requests, by means of first information, a network device to download an expected model, wherein the first information comprises one or more pieces of second information, and the second information is used for indicating a model type and / or a function type of the model expected by the terminal device, thereby enabling a download function for models of a corresponding model type and / or function type.

Description

Wireless communication methods, terminal devices, and network devices Technical Field

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

[0002] In some communication systems (e.g., new radio (NR) systems or next-generation systems), devices running models (e.g., artificial intelligence (AI) / machine learning (ML) models) may need to acquire models from other devices. Therefore, how these devices can efficiently download models becomes a problem that needs to be solved.

[0003] Summary of the Invention

[0004] This application provides a wireless communication method, terminal device, and network device. The various aspects covered by this application are described below.

[0005] In a first aspect, a wireless communication method is provided, comprising: a terminal device sending first information to a network device, wherein the first information is used to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being used to indicate the model type and / or function type of the model desired by the terminal device.

[0006] In a second aspect, a wireless communication method is provided, comprising: a network device receiving first information sent by a terminal device, wherein the first information is used to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being used to indicate the model type and / or function type of the model desired by the terminal device.

[0007] Thirdly, a terminal device is provided, comprising: a transceiver unit, configured to send first information to a network device, wherein the first information is configured to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being configured to indicate the model type and / or function type of the model desired by the terminal device.

[0008] Fourthly, a network device is provided, comprising: a transceiver unit, configured to receive first information sent by a terminal device, wherein the first information is configured to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being configured to indicate the model type and / or function type of the model desired by the terminal device.

[0009] 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.

[0010] 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.

[0011] 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 any one of the first or second aspects.

[0012] Eighthly, a chip is provided, including a processor for calling a program from memory, causing a device having the chip mounted to perform the method as described in the first or second aspect.

[0013] A ninth aspect provides a computer-readable storage medium having a program stored thereon that causes a computer to perform the method as described in the first or second aspect.

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

[0015] Eleventhly, a computer program is provided that causes a computer to perform the method as described in the first or second aspect.

[0016] In this embodiment of the application, the terminal device requests the network device to download the desired model through first information, wherein the first information includes one or more second information, which is used to indicate the model type and / or function type of the model desired by the terminal device. Therefore, the download function of the model for the corresponding model type and / or function type is realized. Attached Figure Description

[0017] Figure 1 is a system architecture example diagram of a wireless communication system applicable to embodiments of this application.

[0018] Figure 2 is a flowchart illustrating the wireless communication method according to an embodiment of this application.

[0019] Figure 3 is a schematic diagram of the structure of the terminal device according to an embodiment of this application.

[0020] Figure 4 is a schematic diagram of the structure of a network device according to an embodiment of this application.

[0021] Figure 5 is a schematic diagram of a communication apparatus according to an embodiment of this application. Detailed Implementation

[0022] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0023] Figure 1 is an example diagram of the system architecture of a wireless communication system 100 to which embodiments of this application can be applied. The wireless 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 wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity; this embodiment of the application does not limit this.

[0024] 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), 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, etc.

[0025] 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, in-vehicle equipment, 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.

[0026] In this embodiment, the network device can be a device used for communicating 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. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), femtocell, 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), centralized unit-control plane (CU-CP), centralized unit-user plane (CU-UP), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or device. A base station can also be a mobile switching center, or a device 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 a device performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0027] Furthermore, base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0028] Network equipment may also include core network equipment. Core network equipment includes, but is not limited to, location management function (LMF) network elements, network slice selection function (NSSF) network elements, authentication server function (AUSF) network elements, unified data management (UDM) network elements, access and mobility management function (AMF) network elements, session management function (SMF) network elements, policy control function (PCF) network elements, user plane function (UPF) network elements, sensing function (SF) network elements, network data analytics function (NWDAF) network elements, and AI function management entities.

[0029] 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.

[0030] 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.

[0031] The application of models can effectively improve the communication performance between terminal devices and network devices. For example, models can be used to achieve functions such as channel estimation and signal recovery, channel-state information (CSI) feedback, positioning, beam management, and mobility control. It should be noted that the "model" mentioned in the embodiments of this application can also be referred to as a "function." For example, multiple different models can be set for various functions, or multiple models can be set for a single function.

[0032] Traditional application-layer model update mechanisms allow terminal devices to download one or more AI models from a server via the application layer. However, this method is transparent to the 3GPP system, meaning that downloading AI models through the application layer is not within the scope of 3GPP technical discussions. For models used at the application layer (e.g., AI models for optimizing mobile phone cameras), this method is sufficient because the timeliness requirements for update operations are not high, and updating through the application layer does not present any serious problems. However, for models used in the 3GP access stratum (AS) layer (e.g., models used in the aforementioned time-domain prediction, spatial-domain prediction, and frequency-domain prediction scenarios), the download or update operation of the model is more sensitive to latency. Downloading or updating models used in the AS layer through the application layer is not conducive to the AS layer quickly activating the corresponding AI model. On the other hand, the mode of downloading or updating models used in the AS layer through the application layer greatly limits the number of AI model vendors. For example, for 3GPP communication systems, using the application layer to download or update models used in the AS layer often means that only AS module chip manufacturers can provide AI model download or update services. Insufficient competition is not conducive to the upgrading of AI models.

[0033] Therefore, this application provides a model download method in which a terminal device requests the download of a desired model from a network device through first information. The first information includes one or more second information, which is used to indicate the model type and / or function type of the model desired by the terminal device. Thus, the download of a model for the corresponding model type and / or function type is realized.

[0034] The embodiments of this application will be described in detail below with reference to Figure 2.

[0035] Figure 2 is a flowchart illustrating a wireless communication method provided in an embodiment of this application. The method 200 shown in Figure 2 can be executed by a terminal device and a network device. The terminal device can be, for example, the terminal device 120 shown in Figure 1, and the network device can be, for example, the network device 110 shown in Figure 1.

[0036] Referring to Figure 2, in step 210, the terminal device sends first information to the network device; correspondingly, the network device receives the first information sent by the terminal device.

[0037] The first information is used to request the network device to download the model desired by the terminal device; in other words, the first information is associated with the model download function of the terminal device. Here, the terminal device can request one or more models, meaning it can simultaneously request the download of one or more models through the first information. The specific content of the first information is described in detail below.

[0038] The first information includes one or more second information.

[0039] The second information is used to indicate the model type and / or function type of the model desired by the terminal device. Here, model type refers to the type of model requested for download by the terminal device, while function type refers to the type of function associated with the model requested for download by the terminal device. Each function may have one model, or each function may have multiple different models. Generally, different models of the same function may correspond to different inference accuracies and / or different application conditions. In one implementation, the second information is used to indicate the model type of the model desired by the terminal device. For example, a model that implements the spatial domain prediction function of beam measurement results is called a first-type model, and a model that implements the temporal domain prediction function of beam measurement results is called a second-type model, etc. In another implementation, the second information is used to indicate the function type of the model desired by the terminal device. For example, a model that implements the spatial domain prediction function of beam measurement results is called a first-function model, and a model that implements the temporal domain prediction function of beam measurement results is called a second-function model, etc. In yet another implementation, the second information is used to indicate both the function type and model type of the model desired by the terminal device. In this case, the model type is a further classification of the function type. In other words, the model type is a sub-functional classification of the corresponding functional type. For example, the model that realizes the spatial domain prediction function of beam measurement results is called the first functional model. Under the same prediction function, there are models that can be applied to different scenarios. Taking the spatial domain prediction function of beam measurement results as an example, there is a scenario where the measurement results of 4 beams are predicted to obtain the measurement results of 8 beams, and there is also a scenario where the measurement results of 8 beams are predicted to obtain the measurement results of 32 beams. The former can be called the first type of model under the first function, and the latter can be called the second type of model under the first function. The third implementation method of the second information is more flexible than the first two implementation methods because the meaning of the second information is richer under this implementation method.

[0040] The second information may implicitly or explicitly indicate the model type and / or function type of the model desired by the terminal device. For example, in one implementation, the model type of the model desired by the terminal device may be determined based on the position of the parameter corresponding to the second information associated with the model type of the model desired by the terminal device; and / or, the function type of the model desired by the terminal device may be determined based on the position of the parameter corresponding to the second information associated with the function type of the model desired by the terminal device. It is understood that the position of the parameter corresponding to the second information may be an absolute position (e.g., the parameter position agreed upon in the protocol) or a relative position (e.g., the relative position between multiple pieces of second information, or the relative order between multiple pieces of second information, etc.).

[0041] As an example, as shown in Table 1, assume that the first information includes N pieces of second information, where N is a positive integer. Each of the N pieces of second information serves as a parameter, occupying a position in the first information. The position of the parameter corresponding to each piece of second information determines the model type or function type associated with that second information. The association between the position of the parameter corresponding to the second information and the model type or function type, as shown in Table 1, can be agreed upon by a protocol, for example. Each parameter position can occupy 1 bit. A value of "0" for this 1-bit information indicates that the model requested for download by the terminal device does not include the model corresponding to the model type or function type associated with the second information at that parameter position; a value of "1" for this 1-bit information indicates that the model requested for download by the terminal device includes the model corresponding to the model type or function type associated with the second information at that parameter position. Assuming the second information at parameter position 1 is associated with the spatial domain prediction function of beam measurement results, a value of "1" for the second information at parameter position 1 indicates that the terminal device expects to download the model corresponding to the spatial domain prediction function of beam measurement results, while a value of "0" indicates that the terminal device does not intend to download the model corresponding to the spatial domain prediction function of beam measurement results. Similarly, if the second information at parameter position 2 is associated with the temporal domain prediction function of beam measurement results, a value of "1" for the second information at parameter position 2 indicates that the terminal device expects to download the model corresponding to the temporal domain prediction function of beam measurement results, while a value of "0" indicates that the terminal device does not intend to download the model corresponding to the temporal domain prediction function of beam measurement results. The meanings of the second information values ​​at other parameter positions are similar and will not be elaborated here.

[0042] Table 1

[0043] For example, in another implementation, the second information may include model identifier information of the model expected by the terminal device, and / or functional identifier information of the model expected by the terminal device. If the second information is model identifier information, this model identifier information is used to indicate the model type corresponding to the model expected by the terminal device. For example, the protocol may stipulate the association between model identifiers and model types. Based on the model identifier information carried in the received second information and the association between the model identifier and the model type, the network device determines which type of model the terminal device expects to download. Alternatively, the terminal device may determine the association between the model identifier and the model type based on implementation details. For the network device, it may not need to know the association between the model identifier and the model type. After receiving the model identifier information carried in the second information, the network device can directly send the model bound to that model identifier to the terminal device. Similarly, if the second information is function identification information, this information indicates the function type corresponding to the model desired by the terminal device. For example, the protocol can stipulate the association between function identifiers and function types. Based on the function identification information carried in the received second information and the association between function identifiers and function types, the network device determines which type of function the terminal device wants to download. Alternatively, the terminal device can determine the association between function identifiers and function types based on implementation details. For the network device, it may not need to know the association between function identifiers and function types. After receiving the function identification information carried in the second information, the network device can directly send the model bound to that function identifier to the terminal device. The second information may include function identification information and model identification information of the model desired by the terminal device. In this case, the function corresponding to the model desired by the terminal device is indicated by the function identification information, and different types of models under the same function are distinguished by the model identification information.

[0044] As an example, as shown in Table 2, assume the terminal device requests to download M models, where M is a positive integer. If the second information includes model identification information, that is, the first information includes one or more model identification information, and each model identification corresponds to a model type, it means the terminal device requests to download the model corresponding to that model identification. If the second information includes function identification information, that is, the first information includes one or more function identification information, and each function identification corresponds to a function of a model, it means the terminal device requests to download the model associated with that function identification. For example, model identification ID1 / function identification ID1 corresponds to the spatial domain prediction function of beam measurement results, model identification ID2 / function identification ID2 corresponds to the temporal domain prediction function of beam measurement results, model identification ID3 / function identification ID3 corresponds to the mobility control function, etc.

[0045] Table 2

[0046] The first information includes the third information.

[0047] Third information may include one or more of the following:

[0048] The first identification information is used to indicate the first applicable condition information associated with the model expected by the terminal device, and the first identification information is related to the network device;

[0049] The second identification information is used to indicate the second applicable condition information associated with the model expected by the terminal device, and the second identification information is related to the terminal device;

[0050] The first indication information is used to indicate the model accuracy requirements;

[0051] The second instruction is used to indicate the model size requirement.

[0052] The first identification information, indicating the first applicable condition, is primarily used to ensure consistency in model performance during training and inference. Each dataset used for model training can be associated with a first identification information, and the resulting model can also be associated with that first identification information after training. When a terminal device arrives at a network environment, it can decide which first applicable condition a model to request from the network device to download, based on historical experience or one or more first identification information provided by the current network. After the terminal device downloads the requested model, if the first identification information indicated in the inference configuration provided by the network device is the same as the first identification information associated with the corresponding function model stored by the terminal device, then the model stored by the terminal device is considered to at least satisfy the first applicable condition. Optionally, the first identification information is an ID identifier. For example, the first identification information is related to the implementation of the network device and can be distinguished by hardware configuration (e.g., antenna size, antenna angle, antenna height, etc.) and / or software configuration (e.g., software program, data, etc.). A model deployed by a terminal device that satisfies the first applicable condition alone may not necessarily achieve good performance, but if none of the first applicable conditions are met, it is generally considered that the corresponding model cannot work at high performance. The first applicable condition is only one of the conditions that need to be met to achieve high-performance model operation. The second identification information, indicating the second applicable condition, is primarily designed to ensure consistency in model performance during training and inference. Each dataset used for model training can be associated with a second identification information. After training, the resulting model can also be associated with this second identification information. When a terminal device reaches a network environment, it can determine which second applicable condition model to download based on its own characteristics. This ensures that the models downloaded by the terminal device at least meet the second applicable condition. Optionally, the second identification information can be an ID identifier. For example, the second identification information is related to the implementation of the terminal device and can distinguish different terminal devices through hardware configuration (e.g., chip version, antenna type, etc.) and / or software configuration (e.g., software program, data, etc.). For instance, different second identification information can be used to distinguish terminal devices supporting different protocol versions or different chip versions. The first indication information can, for example, refer to the range of difference between the predicted and actual measured values ​​of the measurement result. For instance, this range of difference can be less than a certain threshold (e.g., 1dB, 2dB, or 3dB, etc.). The difference range requirement can also be called the accuracy requirement. The first indication information is optional. For example, in some cases, if all models with an accuracy less than a certain threshold (e.g., 1dB, 2dB, or 3dB) are allowed to join the network, the third information may not include the first indication information.Regarding the model size requirement indicated by the second instruction information, for the same manufacturer, generally speaking, the larger the model, the better the model performance. However, the terminal device also needs to choose an appropriate model size according to its own capabilities to avoid being unable to run the model effectively. Therefore, as an option, the terminal device can also carry the second instruction information in the third information.

[0053] For example, the third information may include first identification information, second identification information, first instruction information, or second instruction information. Alternatively, the third information may include first identification information and second identification information, or include first identification information and first instruction information, or include first identification information and second instruction information, or include second identification information and first instruction information, or include second identification information and second instruction information, or include both first and second instruction information. Another example is that the third information may include first identification information, second identification information, and first instruction information, or include first identification information, second identification information, and second instruction information, or include first identification information, first instruction information, and second instruction information, or include second identification information, first instruction information, and second instruction information. Yet another example is that the third information may include first identification information, second identification information, first instruction information, and second instruction information.

[0054] When a terminal device provides third-party information during the process of requesting to download a model, the network device can accurately understand the model download requirements of the terminal device, thus avoiding the situation where the network device provides a model that cannot meet the actual needs of the terminal device due to inaccurate information provided by the terminal device.

[0055] As an example, as shown in Table 3, the first information includes one or more second information pieces, where each second information piece can be associated with a third information piece. The first information is used to request the download of one or more models expected by the terminal device. The second information is used to indicate the model type or function type corresponding to the model expected by the terminal device (the two implementation methods of the second information can be referred to the descriptions in Tables 1 and 2 above, and will not be detailed here). The third information further provides the requirement information corresponding to the model expected by the terminal device, such as one or more of the first identification information, second identification information, first indication information, and second indication information. Due to the different application scenarios of the models, there may be a need to train multiple models for one function, and different models under the same function have different applicable scenarios (or applicable conditions). Suppose that, for the spatial prediction function of beam measurement results, network devices or OTT (over the top) servers can train four models, which are referred to as Model 1, Model 2, Model 3, and Model 4, respectively. Model 1 corresponds to the first identifier ID1 and the second identifier ID1. The first identifier ID1 is associated with an implementation of a network device, and the second identifier ID1 is associated with a version of a terminal device. Model 2 corresponds to the first identifier ID1 and the second identifier ID2. Model 3 corresponds to the first identifier ID2 and the second identifier ID1. Model 4 corresponds to the first identifier ID2 and the second identifier ID2.

[0056] Table 3

[0057] Where M is a positive integer. By adding third information associated with the second information to the first information, the network device can clearly understand what kind of application scenario (or application condition) the terminal device expects to download. This avoids the problem of the terminal device initiating a download request again due to the terminal device's vague download requirements, or the problem of the network device downloading an incompatible model for the terminal device. The third information helps to improve the efficiency of model download.

[0058] The first information includes the fourth information.

[0059] The fourth piece of information may include one or more of the following:

[0060] The third indication information is used to indicate the type of input parameters corresponding to the model expected by the terminal device;

[0061] The fourth indication information is used to indicate the number of input parameters corresponding to the model expected by the terminal device;

[0062] The fifth instruction information is used to indicate the type of output parameters corresponding to the model expected by the terminal device;

[0063] The sixth instruction information is used to indicate the number of output parameters corresponding to the model expected by the terminal device;

[0064] The seventh indication information is used to indicate the relationship between the input parameters and output parameters corresponding to the model expected by the terminal device.

[0065] The fourth and sixth indications are optional. For example, if the number of input parameters is already included in the input parameter type of the model, the fourth indication may not include the fourth indication indicating the number of input parameters. Similarly, if the number of output parameters is already included in the output parameter type of the model, the fourth indication may not include the sixth indication indicating the number of output parameters.

[0066] For example, the fourth information may include the third, fourth, fifth, sixth, or seventh instruction information. Alternatively, the fourth information may include the third and fourth instruction information, or include the third and fifth instruction information, or the third and sixth instruction information, or the fourth and fifth instruction information, or the fifth and sixth instruction information, or the third and seventh instruction information, or the fifth and seventh instruction information, or the fifth and seventh instruction information, or the sixth and seventh instruction information. For example, the fourth information may include the third, fourth, and fifth instruction information, or may include the third, fourth, and sixth instruction information, or may include the third, fifth, and sixth instruction information, or may include the fourth, fifth, and sixth instruction information, or may include the third, fourth, and seventh instruction information, or may include the third, fifth, and seventh instruction information, or may include the third, sixth, and seventh instruction information, or may include the fourth, fifth, and seventh instruction information, or may include the fourth, sixth, and seventh instruction information, or may include the fifth, sixth, and seventh instruction information. For example, the fourth information may include the third, fourth, fifth, and sixth instruction information, or it may include the third, fourth, fifth, and seventh instruction information. Alternatively, the fourth information may include the third, fourth, fifth, sixth, and seventh instruction information.

[0067] As an example, as shown in Table 4, the first information includes one or more second information pieces, which are associated with the third and fourth information pieces. The first information is used to request the download of one or more models expected by the terminal device. The second information is used to indicate the model type or function type corresponding to the model expected by the terminal device (the two implementation methods of the second information can be referred to the descriptions in Tables 1 and 2 above, and will not be detailed here). The third information further provides the requirement information corresponding to the model expected by the terminal device (e.g., one or more of the first identification information, second identification information, first indication information, and second indication information). The fourth information is used to indicate the parameter requirements corresponding to the model expected by the terminal device, such as one or more of the input parameter type, output parameter type, number of input parameters, number of output parameters, and the relationship between input parameters and output parameters. Due to the different input and output parameters corresponding to the models, there may be a need to train multiple models for one function, and different models under the same function have different input and output parameters. Assume that for the spatial domain prediction function of beam measurement results, the network device or OTT server can train four models, which are represented as Model 1, Model 2, Model 3, and Model 4, respectively.In Model 1, there are first identifier ID1, second identifier ID1, input parameter type 1 (e.g., beam measurement results), output parameter type 1 (e.g., beam measurement results), number of input parameters 1 (e.g., 4 beams), and number of output parameters 1 (e.g., 8 beams). That is, the measurement results of 4 beams are used to predict the measurement results of another 4 beams to obtain the measurement results of 8 beams. First identifier ID1 is associated with an implementation of a network device (e.g., different network device implementations are distinguished by hardware and / or software configuration), and second identifier ID1 is associated with a version of a terminal device (e.g., different terminal device versions are distinguished by hardware and / or software). Model 2 corresponds to first identifier ID1, second identifier ID1, input parameter type 1 (e.g., beam measurement results), output parameter type 1 (e.g., beam measurement results), number of input parameters 2 (e.g., 8 beams), and output parameter... Model 2 corresponds to a quantity of 2 (e.g., 32 beams), meaning that the measurement results of 8 beams are used to predict the measurement results of another 24 beams to obtain the measurement results of 32 beams; Model 3 corresponds to a first identifier ID1, a second identifier ID1, input parameter type 2 (e.g., wide beam measurement results) and output parameter type 2 (e.g., narrow beam measurement results), input parameter quantity 1 (e.g., 4 wide beams) and output parameter quantity 1 (e.g., 8 narrow beams), meaning that the measurement results of 4 wide beams are used to predict the measurement results of 8 narrow beams; Model 4 corresponds to a first identifier ID1, a second identifier ID1, input parameter type 2 (e.g., wide beam measurement results) and output parameter type 2 (e.g., narrow beam measurement results), input parameter quantity 2 (e.g., 8 wide beams) and output parameter quantity 2 (e.g., 32 narrow beams), meaning that the measurement results of 8 wide beams are used to predict the measurement results of 32 narrow beams.

[0068] The relationship between the input parameters and output parameters of the model can be, for example, agreed upon in the protocol. The relationship between the input parameters and output parameters can also be called the model input-output inference rule, model input-output inference requirement, or model input-output inference mode. For example, different relationships can be indicated by different identification information. The seventh indication information may include, for example, identification information indicating the relationship between the input parameters and output parameters of the model that the terminal device expects. As an example, taking the spatial prediction function of beam measurement results as an example, network devices or OTT servers can train various types of models. The fourth information can include the input parameter types corresponding to these models (e.g., beam identification information, and the beam's reference signal receiving power (RSRP) measurement results, reference signal receiving quality (RSRQ) measurement results, or signal to interference noise ratio (SINR) measurement results), output parameter types (e.g., beam identification information, and the beam's RSRP measurement results, RSRQ measurement results, or SINR measurement results), and the correlation between input parameters and output parameters (e.g., using the measurement results of 4 beams to predict the measurement results of another 4 beams to obtain the measurement results of 8 beams, or using the measurement results of 8 beams to predict the measurement results of another 24 beams to obtain the measurement results of 32 beams, or using the measurement results of 4 wide beams to predict the measurement results of 8 narrow beams, or using the measurement results of 8 wide beams to predict the measurement results of 32 narrow beams). For example, taking the time-domain prediction function of beam measurement results as an example, network devices or OTT servers can train various types of models. The fourth information can include the input parameter types (e.g., RSRP measurement results, RSRQ measurement results, or SINR measurement results of the cell), output parameter types (e.g., RSRP measurement results, RSRQ measurement results, or SINR measurement results of the cell), and the correlation between input parameters and output parameters (e.g., using the cell measurement results of K1 historical moments to predict the cell measurement results of the same cell at K2 future moments, or using the cell measurement results of historical moments to predict the cell measurement results of the same cell at K2 future moments, or using the cell measurement results of historical moments to predict the cell measurement results of the same cell within the first future time period, where K1 and K2 are positive integers).Furthermore, considering that the input parameter type and the output parameter type are usually the same, the third and fifth indication information can be the same indication information, that is, the input parameter type and the output parameter type can be indicated by one indication information at the same time. In this case, the fourth information may include two types of indication information, namely, indication information for indicating the input parameter type and the output parameter type, and indication information for indicating the relationship between the input parameter and the output parameter.

[0069] Table 4

[0070] Where M is a positive integer. By adding a fourth piece of information related to the second piece of information to the first piece of information, the network device can clearly understand what kind of model input and output requirements the terminal device expects to download. This avoids the problem of the terminal device initiating a download request again due to the terminal device's vague download requirements, or the problem of the network device downloading an incompatible model for the terminal device. The fourth piece of information improves the efficiency of model downloading.

[0071] In one implementation, the first information includes one or more second information; in another implementation, the first information includes one or more second information and third information associated with the second information; in yet another implementation, the first information includes one or more second information and fourth information associated with the second information; in yet another implementation, the first information includes one or more second information, third information associated with the second information, and fourth information associated with the second information.

[0072] Referring again to Figure 2, in some implementations, method 200 may also include step 220.

[0073] In step 220, the terminal device receives the fifth information sent by the network device; correspondingly, the network device sends the fifth information to the terminal device.

[0074] In this embodiment of the application, the first information mentioned above can also be called download request information, which is used to request the download of the model desired by the terminal device; the fifth information here can also be called download assistance information, which is used to indicate the models stored by the network device, or in other words, to assist the terminal device in determining which models it can request to download.

[0075] The fifth piece of information can be carried through system broadcast messages or dedicated signaling. If the fifth piece of information is carried through system broadcast messages, it helps to save system signaling overhead; if the fifth piece of information is carried through dedicated signaling, it has greater flexibility because network devices can determine the content of the fifth piece of information based on the capabilities supported by the terminal devices, which better meets the personalized needs of the terminal devices.

[0076] The following is a detailed description of the fifth piece of information.

[0077] The fifth information includes one or more sixth information.

[0078] The sixth piece of information is used to indicate the model type and / or function type of the model stored by the network device.

[0079] Here, model type refers to the type of model stored by the network device, while function type refers to the type of function associated with the model stored by the network device. Each function may have one model, or each function may have multiple different models. Generally, different models for the same function may correspond to different inference accuracies and / or different application conditions. In one implementation, the sixth piece of information is used to indicate the model type of the model stored by the network device. For example, a model implementing spatial domain prediction of beam measurement results is called a first-type model, and a model implementing temporal domain prediction of beam measurement results is called a second-type model, etc. In another implementation, the sixth piece of information is used to indicate the function type of the model stored by the network device. For example, a model implementing spatial domain prediction of beam measurement results is called a first-function model, and a model implementing temporal domain prediction of beam measurement results is called a second-function model, etc. In yet another implementation, the sixth piece of information is used to indicate both the function type and model type of the model stored by the network device. In this case, the model type is a further classification of the function type. In other words, the model type is a sub-functional classification of the corresponding functional type. For example, the model that realizes the spatial domain prediction function of beam measurement results is called the first functional model. Even under the same prediction function, there are models applied to different scenarios. Taking the spatial domain prediction function of beam measurement results as an example, there is a scenario where the measurement results of 4 beams are predicted to obtain the measurement results of 8 beams, and there is also a scenario where the measurement results of 8 beams are predicted to obtain the measurement results of 32 beams. The former can be called the first type of model under the first function, and the latter can be called the second type of model under the first function. The third implementation method of the sixth information is more flexible than the previous two implementation methods because the meaning of the sixth information is richer under this implementation method.

[0080] The sixth piece of information can implicitly or explicitly indicate the model type and / or function type of the model stored by the network device. For example, in one implementation, the model type of the model stored by the network device can be determined based on the position of the parameter corresponding to the sixth piece of information associated with the model type of the model stored by the network device in one or more pieces of sixth information; and / or, the function type of the model stored by the network device can be determined based on the position of the parameter corresponding to the sixth piece of information associated with the function type of the model stored by the network device in one or more pieces of sixth information. It is understood that the position of the parameter corresponding to the sixth piece of information can be an absolute position (e.g., the parameter position agreed upon in the protocol) or a relative position (e.g., the relative position between multiple pieces of sixth information, or the relative order between multiple pieces of sixth information, etc.).

[0081] As an example, as shown in Table 5, assume that the fifth piece of information includes N pieces of sixth information, where N is a positive integer. Each of the N pieces of sixth information serves as a parameter, occupying a position within the fifth piece of information. The position of the parameter corresponding to each piece of sixth information determines the model type or functional type of the model associated with that sixth piece of information. The association between the position of the parameter corresponding to the sixth piece of information and the model type or functional type, as shown in Table 5, can be, for example, agreed upon by a protocol. Each parameter position can, for example, occupy 1 bit. A value of "0" for this 1-bit information indicates that the network device does not store a model corresponding to the model type or functional type associated with the sixth piece of information at that parameter position; a value of "1" for this 1-bit information indicates that the network device stores a model corresponding to the model type or functional type associated with the sixth piece of information at that parameter position. Assuming the sixth information at parameter position 1 is associated with the spatial domain prediction function of beam measurement results, a value of "1" indicates that the network device stores a model corresponding to the spatial domain prediction function of beam measurement results, while a value of "0" indicates that the network device does not store such a model. Similarly, the sixth information at parameter position 2 is associated with the temporal domain prediction function of beam measurement results. A value of "1" indicates that the network device stores a model corresponding to the temporal domain prediction function of beam measurement results, while a value of "0" indicates that the network device does not store such a model. The meanings of the sixth information values ​​at other parameter positions are similar and will not be elaborated upon here.

[0082] Table 5

[0083] For example, in another implementation, the sixth information may include model identifier information of the model stored by the network device, and / or function identifier information of the model stored by the network device. Wherein, if the sixth information is model identifier information, this model identifier information is used to indicate the model type corresponding to the model stored by the network device. For example, the protocol may stipulate the association between model identifier and model type; or, the terminal device may determine the association between model identifier and model type based on implementation. For the network device, it does not need to know the association between model identifier and model type and can directly send the model bound to the model identifier to the terminal device. Similarly, if the sixth information is function identifier information, this function identifier information is used to indicate the function type corresponding to the model stored by the network device. For example, the protocol may stipulate the association between function identifier and function type; or, the terminal device may determine the association between function identifier and function type based on implementation. For the network device, it does not need to know the association between function identifier and function type and can directly send the model bound to the function identifier to the terminal device.

[0084] As an example, as shown in Table 6, assume the network device stores M models, where M is a positive integer. If the sixth information includes model identification information, that is, the fifth information includes one or more model identification information, and each model identification corresponds to a model type, it means the network device stores a model corresponding to that model identification. If the sixth information includes function identification information, that is, the fifth information includes one or more function identification information, and each function identification corresponds to a function of a model, it means the network device stores a model associated with that function identification. For example, model identification ID1 / function identification ID1 corresponds to the spatial domain prediction function of beam measurement results, model identification ID2 / function identification ID2 corresponds to the temporal domain prediction function of beam measurement results, model identification ID3 / function identification ID3 corresponds to the mobility control function, etc.

[0085] Table 6

[0086] The fifth information includes the seventh information.

[0087] The seventh piece of information may include one or more of the following:

[0088] The third identification information is used to indicate the third applicable condition information associated with the model stored in the network device, and the third identification information is related to the network device;

[0089] The fourth identification information is used to indicate the fourth applicable condition information associated with the model stored in the network device, and the fourth identification information is related to the terminal device;

[0090] The eighth indication information is used to indicate the accuracy information of the model stored by the network device;

[0091] The ninth instruction is used to indicate the size of the model stored by the network device.

[0092] The third identification information, indicating the third applicable condition, is primarily to ensure the consistency of model performance during model training and inference. Its meaning is similar to the first identification information described above and will not be repeated here. The fourth identification information, indicating the fourth applicable condition, is also primarily to ensure the consistency of model performance during model training and inference. Its meaning is similar to the second identification information described above and will not be repeated here. The eighth indication information indicates the accuracy of the model stored in the network device. For example, the eighth indication information could refer to the range of difference between the predicted and actual measured values. This range could be less than a certain threshold (e.g., 1dB, 2dB, or 3dB). This difference range requirement can also be called the accuracy requirement. The eighth indication information is optional. For example, in some cases, if all models with accuracy less than a certain threshold (e.g., 1dB, 2dB, or 3dB) are allowed to join the network, then the seventh information may not include the eighth indication information. The ninth instruction indicates the size of the model stored by the network device. For the same manufacturer, a larger model usually means better performance. However, terminal devices also need to choose an appropriate model size based on their own capabilities to avoid being unable to run the model effectively. Therefore, as an option, the network device can also include the ninth instruction in the seventh information for the terminal device to refer to.

[0093] For example, the seventh information may include the third identification information, the fourth identification information, the eighth instruction information, or the ninth instruction information. Alternatively, the seventh information may include the third and fourth identification information, or include the third and eighth instruction information, or include the third and ninth instruction information, or include the fourth and eighth instruction information, or include the fourth and ninth instruction information, or include the eighth and ninth instruction information. Another example is that the seventh information may include the third, fourth, and eighth instruction information, or include the third, fourth, and ninth instruction information, or include the third, eighth, and ninth instruction information, or include the fourth, eighth, and ninth instruction information. Yet another example is that the seventh information may include the third, fourth, eighth, and ninth instruction information.

[0094] The network device provides the seventh information to the terminal device, which allows the terminal device to accurately know which functions and / or scenarios the network device has stored, thus avoiding the terminal device blindly initiating model download requests to the network device and improving the efficiency of model download requests.

[0095] As an example, as shown in Table 7, the fifth information includes one or more sixth information pieces, where each sixth information piece can be associated with a seventh information piece. The fifth information is used to indicate what models the network device stores, and the sixth information is used to indicate the model type or function type corresponding to the models stored by the network device (the two implementation methods of the sixth information can be referred to the descriptions in Tables 5 and 6 above, and will not be detailed here). The seventh information further provides detailed information about the models stored by the network device, such as one or more of the third identification information, fourth identification information, eighth indication information, and ninth indication information. Due to different application scenarios of the models, there may be a need to train multiple models for one function, and different models under the same function have different applicable scenarios (or applicable conditions). Suppose that for the spatial prediction function of beam measurement results, network devices or OTT servers can train four models, which are referred to as Model 1, Model 2, Model 3 and Model 4 respectively. Model 1 corresponds to the third identifier ID1 and the fourth identifier ID1. The third identifier ID1 is associated with an implementation of a network device, and the fourth identifier ID1 is associated with a version of a terminal device. Model 2 corresponds to the third identifier ID1 and the fourth identifier ID2. Model 3 corresponds to the third identifier ID2 and the fourth identifier ID1. Model 4 corresponds to the third identifier ID2 and the fourth identifier ID2.

[0096] Table 7

[0097] Where M is a positive integer. By adding a seventh piece of information related to the sixth piece of information to the fifth piece of information, the terminal device can clearly understand what kind of application scenario (or application condition) the network device has stored, thus avoiding the problem of the terminal device initiating a download request again due to the lack of specific model download assistance information provided by the network device. The seventh piece of information improves the efficiency of model download.

[0098] The fifth information includes the eighth information.

[0099] The eighth piece of information may include one or more of the following:

[0100] The tenth instruction information is used to indicate the type of input parameters corresponding to the model stored by the network device;

[0101] The eleventh instruction is used to indicate the number of input parameters corresponding to the model stored by the network device;

[0102] The twelfth instruction information is used to indicate the type of output parameters corresponding to the model stored by the network device;

[0103] The thirteenth instruction is used to indicate the number of output parameters corresponding to the model stored by the network device;

[0104] The fourteenth instruction is used to indicate the relationship between the input parameters and output parameters corresponding to the model stored by the network device.

[0105] Among them, the eleventh and thirteenth indication information are optional. For example, if the number of input parameters is already included in the input parameter type of the model, the eleventh indication information indicating the number of input parameters may not be included in the eighth information. Similarly, if the number of output parameters is already included in the output parameter type of the model, the thirteenth indication information indicating the number of output parameters may not be included in the eighth information.

[0106] For example, the eighth information may include the tenth, eleventh, twelfth, thirteenth, or fourteenth instruction information. Alternatively, the eighth information may include the tenth and eleventh instruction information, or include the tenth and twelfth instruction information, or include the tenth and thirteenth instruction information, or include the eleventh and twelfth instruction information, or include the eleventh and thirteenth instruction information, or include the twelfth and thirteenth instruction information, or include the tenth and fourteenth instruction information, or include the eleventh and fourteenth instruction information, or include the twelfth and fourteenth instruction information, or include the thirteenth and fourteenth instruction information. For example, the eighth information may include the tenth, eleventh, and twelfth instruction information, or include the tenth, eleventh, and thirteenth instruction information, or include the eleventh, eleventh, and thirteenth instruction information, or include the eleventh, eleventh, and thirteenth instruction information, or include the tenth, eleventh, and fourteenth instruction information, or include the tenth, eleventh, and fourteenth instruction information, or include the eleventh, eleventh, and fourteenth instruction information, or include the eleventh, thirteenth, and fourteenth instruction information, or include the eleventh, thirteenth, and fourteenth instruction information, or include the twelfth, thirteenth, and fourteenth instruction information. For example, the eighth information may include the tenth, eleventh, twelfth, and thirteenth instruction information, or may include the tenth, eleventh, twelfth, and fourteenth instruction information, or may include the tenth, eleventh, thirteenth, and fourteenth instruction information, or may include the tenth, twelfth, thirteenth, and fourteenth instruction information. For example, the fourth information may include the tenth, eleventh, eleventh, twelfth, thirteenth, and fourteenth instruction information.

[0107] As an example, as shown in Table 8, the fifth information includes one or more sixth information pieces. The sixth information is associated with the seventh and eighth information pieces. The fifth information indicates which models the network device stores, and the sixth information indicates the model type or function type corresponding to the models stored by the network device (the two implementation methods of the sixth information can be referred to in Tables 5 and 6 above, and will not be detailed here). The seventh information further provides detailed information corresponding to the models stored by the network device (e.g., one or more of the third, fourth, eighth, and ninth indication information). The eighth information indicates the parameter requirements corresponding to the models stored by the network device, such as one or more of the input parameter type, output parameter type, number of input parameters, and number of output parameters. Due to the different input and output parameters of the models, there may be a need to train multiple models for one function, and different models under the same function may have different input and output parameters. For example, for the spatial domain prediction function of beam measurement results, the network device or OTT server can train four models, denoted as Model 1, Model 2, Model 3, and Model 4, respectively.In this model, Model 1 corresponds to the third identifier ID1, the fourth identifier ID1, input parameter type 1 (e.g., beam measurement results), output parameter type 1 (e.g., beam measurement results), input parameter quantity 1 (e.g., 4 beams), and output parameter quantity 1 (e.g., 8 beams). That is, it uses the measurement results of 4 beams to predict the measurement results of another 4 beams, thus obtaining the measurement results of 8 beams. The third identifier ID1 is associated with an implementation of a network device (e.g., different network device implementations are distinguished by hardware and / or software configuration). The fourth identifier ID1 is associated with a version of the terminal device (e.g., different terminal device versions are distinguished by hardware and / or software); Model 2 corresponds to the third identifier ID1, the fourth identifier ID1, input parameter type 1 (e.g., beam measurement results) and output parameter type 1 (e.g., beam measurement results), input parameter quantity 2 (e.g., 8 beams) and output parameter quantity 2 (e.g., 32 beams), that is, the measurement results of the other 24 beams are predicted using the measurement results of 8 beams to obtain the measurement results of 32 beams; Model 3 The model corresponds to the third identifier ID1, the fourth identifier ID1, input parameter type 2 (e.g., measurement results of wide beams) and output parameter type 2 (e.g., measurement results of narrow beams), input parameter quantity 1 (e.g., 4 wide beams) and output parameter quantity 1 (e.g., 8 narrow beams). That is, the measurement results of 4 wide beams are used to predict the measurement results of 8 narrow beams. The model 4 corresponds to the third identifier ID1, the fourth identifier ID1, input parameter type 2 (e.g., measurement results of wide beams) and output parameter type 2 (e.g., measurement results of narrow beams), input parameter quantity 2 (e.g., 8 wide beams) and output parameter quantity 2 (e.g., 32 narrow beams). That is, the measurement results of 8 wide beams are used to predict the measurement results of 32 narrow beams.

[0108] The relationship between the input parameters and output parameters of the model can be, for example, agreed upon in the protocol. The relationship between the input parameters and output parameters can also be called the model input-output inference rule, model input-output inference requirement, or model input-output inference mode. For example, different relationships can be indicated by different identification information. The fourteenth indication information may include, for example, identification information indicating the relationship between the input parameters and output parameters of the model stored by the network device. As an example, taking the spatial prediction function of beam measurement results as an example, network devices or OTT servers can train various types of models. The eighth information can include the input parameter types (e.g., beam identification information, and beam RSRP measurement results, RSRQ measurement results, or SINR measurement results), output parameter types (e.g., beam identification information, and beam RSRP measurement results, RSRQ measurement results, or SINR measurement results), and the correlation between input parameters and output parameters (e.g., using the measurement results of 4 beams to predict the measurement results of another 4 beams to obtain the measurement results of 8 beams, or using the measurement results of 8 beams to predict the measurement results of another 24 beams to obtain the measurement results of 32 beams, or using the measurement results of 4 wide beams to predict the measurement results of 8 narrow beams, or using the measurement results of 8 wide beams to predict the measurement results of 32 narrow beams). For example, taking the time-domain prediction function of beam measurement results as an example, network devices or OTT servers can train various types of models. The eighth information can include the input parameter types (e.g., RSRP measurement results, RSRQ measurement results, or SINR measurement results of the cell), output parameter types (e.g., RSRP measurement results, RSRQ measurement results, or SINR measurement results of the cell), and the correlation between input parameters and output parameters (e.g., using the cell measurement results of K1 historical moments to predict the cell measurement results of the same cell at K2 future moments, or using the cell measurement results of historical moments to predict the cell measurement results of the same cell at K2 future moments, or using the cell measurement results of historical moments to predict the cell measurement results of the same cell within the first future time period, where K1 and K2 are positive integers). Furthermore, considering that the input parameter type and the output parameter type are usually the same, the tenth and twelfth indication information can be the same indication information, that is, the input parameter type and the output parameter type can be indicated by one indication information at the same time. In this case, the eighth information may include two types of indication information, namely, indication information for indicating the input parameter type and the output parameter type, and indication information for indicating the relationship between the input parameter and the output parameter.

[0109] Table 8

[0110] Where M is a positive integer. By adding an eighth piece of information, which is associated with the sixth piece of information, to the fifth piece of information, the terminal device can clearly understand what kind of model with what kind of function and what kind of model input and output requirements the network device has already stored. This avoids the problem of the terminal device initiating a download request again because the model download assistance information provided by the network device is not specific. The efficiency of model download is improved by adding the eighth piece of information.

[0111] In one implementation, the fifth information includes one or more sixth information; in another implementation, the fifth information includes one or more sixth information and a seventh information associated with the sixth information; in yet another implementation, the fifth information includes one or more sixth information and an eighth information associated with the sixth information; in yet another implementation, the fifth information includes one or more sixth information, a seventh information associated with the sixth information, and an eighth information associated with the sixth information.

[0112] Referring again to Figure 2, in some implementations, method 200 may also include step 230.

[0113] In step 230, the terminal device sends the ninth information to the network device; correspondingly, the network device receives the ninth information sent by the terminal device.

[0114] The ninth information may include the tenth information and / or one or more eleventh information. The tenth information is used to request a query for the association information of the models stored by the network device, or in other words, the tenth information is used to trigger the network device to send the aforementioned fifth information. For example, the network device may spontaneously send the fifth information to the terminal device (e.g., through broadcast signaling or dedicated signaling); or, for example, the act of the network device sending the fifth information to the terminal device may be triggered by a request from the terminal device, that is, the terminal device obtains the association information of the models stored by the network device by sending the ninth information. For example, the terminal device sends a query for which models the network device stores through the ninth information. After the ninth information is successfully received by the network device, the network device knows that the terminal device wants to know which models the network device currently stores. In response to the terminal device, the network device may send the fifth information to the terminal device, which is used to indicate which models the network device actually stores. It can be understood that the ninth information can also be called an information query request, used to request a query for the association information of the models stored by the network device. Optionally, the association information of the models stored by the network device may include, for example, at least one of the aforementioned sixth, seventh, and eighth information. As an example, the associated information may include the sixth, seventh, or eighth information, or include the sixth and seventh information, or include the sixth and eighth information, or include the seventh and eighth information, or include the sixth, seventh, and eighth information.

[0115] The eleventh piece of information indicates the model type and / or function type requested by the terminal device. Here, the one or more models requested by the terminal device may be the same as or different from the one or more models requested to be downloaded by the terminal device in the first piece of information. For example, the one or more models requested by the terminal device may include all models that the terminal device is interested in, assuming there are K models, while the models requested to be downloaded may be all or some of these K models (e.g., currently only one or a few of the K models need to be downloaded).

[0116] For example, the ninth piece of information includes the tenth piece of information, or includes one or more eleventh pieces of information. If the ninth piece of information includes the tenth piece of information, it means that the terminal device is requesting to know what models the network device currently stores. Since the tenth piece of information does not provide association information for the models the terminal device is requesting to query, the network device can determine the scope of association information for the models included in the fifth piece of information based on the capabilities supported by the terminal device. If the ninth piece of information includes one or more eleventh pieces of information, the network device can determine the scope of association information for the models included in the fifth piece of information based on the content of the eleventh pieces of information provided by the terminal device. As another example, the ninth piece of information includes the tenth piece of information and one or more eleventh pieces of information. In this case, the network device can determine the scope of association information for the models included in the fifth piece of information based on the content of the eleventh pieces of information provided by the terminal device.

[0117] The eleventh piece of information can implicitly or explicitly indicate the model type and / or function type of the model requested by the terminal device. For example, in one implementation, the model type and / or function type of the model requested by the terminal device can be determined based on the position of the parameter corresponding to the eleventh piece of information associated with the model requested by the terminal device in the ninth piece of information. It is understood that the position of the parameter corresponding to the eleventh piece of information can be an absolute position (e.g., the parameter position agreed upon in the protocol) or a relative position (e.g., the relative position between multiple eleventh pieces of information, or the relative order between multiple eleventh pieces of information, etc.).

[0118] As an example, as shown in Table 9, assume that the ninth piece of information includes N eleventh pieces of information, where N is a positive integer. Each of the N eleventh pieces of information serves as a parameter, occupying a position within the ninth piece of information. The position of the parameter corresponding to each eleventh piece of information determines the model type or function type associated with that eleventh piece of information. The association between the position of the parameter corresponding to the eleventh piece of information and the model type or function type, as shown in Table 9, can be agreed upon by a protocol, for example. Each parameter position can occupy 1 bit. A value of "0" for this 1-bit information indicates that the model requested by the terminal device does not include the model corresponding to the model type or function type associated with the eleventh piece of information at that parameter position; a value of "1" for this 1-bit information indicates that the model requested by the terminal device includes the model corresponding to the model type or function type associated with the eleventh piece of information at that parameter position. Assuming the eleventh piece of information at parameter position 1 is associated with the spatial domain prediction function of beam measurement results, a value of "1" for the eleventh piece of information at parameter position 1 indicates that the terminal device wants to query the association information of the model corresponding to the spatial domain prediction function of beam measurement results, while a value of "0" indicates that the terminal device does not want to know the association information of the model corresponding to the spatial domain prediction function of beam measurement results. Similarly, if the eleventh piece of information at parameter position 2 is associated with the temporal domain prediction function of beam measurement results, a value of "1" for the eleventh piece of information at parameter position 2 indicates that the terminal device wants to query the association information of the model corresponding to the temporal domain prediction function of beam measurement results, while a value of "0" for the eleventh piece of information at parameter position 2 indicates that the terminal device does not want to know the association information of the model corresponding to the temporal domain prediction function of beam measurement results. The meanings of the eleventh pieces of information at other parameter positions are similar and will not be elaborated here.

[0119] Table 9

[0120] For example, in another implementation, the eleventh piece of information may include model identifier information of the model requested by the terminal device, and / or functional identifier information of the model requested by the terminal device. If the eleventh piece of information is model identifier information, this model identifier information is used to indicate the model type corresponding to the model requested by the terminal device. For example, the protocol may stipulate the association between model identifiers and model types. Based on the model identifier information carried in the received eleventh piece of information and the association between the model identifier and the model type, the network device determines which type of model association information the terminal device wants to query. Alternatively, the terminal device may determine the association between the model identifier and the model type based on the implementation. For the network device, it may not need to know the association between the model identifier and the model type. After receiving the model identifier information carried in the eleventh piece of information, the network device can directly send the association information of the model bound to that model identifier to the terminal device. Similarly, if the eleventh message is a function identifier, this function identifier is used to indicate the function type corresponding to the model requested by the terminal device. For example, the protocol can stipulate the association between function identifiers and function types. Based on the function identifier information carried in the received eleventh message and the association between function identifiers and function types, the network device determines which type of function-related model association information the terminal device wants to query. Alternatively, the terminal device can determine the association between function identifiers and function types based on implementation. For the network device, it does not need to know the association between function identifiers and function types. After receiving the function identifier information carried in the eleventh message, the network device can directly send the association information of the model bound to the function identifier to the terminal device.

[0121] As an example, as shown in Table 10, assume the terminal device requests a query for M models, where M is a positive integer. If the eleventh piece of information includes model identification information, that is, the ninth piece of information includes one or more model identification information, each model identification corresponding to a model type, it means the terminal device is requesting a query for the association information of the model corresponding to that model identification. If the eleventh piece of information includes function identification information, that is, the ninth piece of information includes one or more function identification information, each function identification corresponding to a function of a model, it means the terminal device is requesting a query for the association information of the model associated with that function identification. For example, model identification ID1 / function identification ID1 corresponds to the spatial domain prediction function of beam measurement results, model identification ID2 / function identification ID2 corresponds to the temporal domain prediction function of beam measurement results, model identification ID3 / function identification ID3 corresponds to the mobility control function, etc.

[0122] Table 10

[0123] As can be seen, by using the ninth piece of information, the terminal device can know what models the network device currently stores before requesting to download a model. This makes the terminal device's request to download a model based on the first piece of information more accurate, and can minimize the occurrence of the terminal device requesting a model that the network device does not store, thereby improving the model download efficiency.

[0124] Referring again to Figure 2, in some implementations, method 200 may also include step 240.

[0125] In step 240, the terminal device receives the twelfth information sent by the network device; correspondingly, the network device sends the twelfth information to the terminal device.

[0126] The twelfth piece of information is used to reject all requests in the first piece of information or to reject a portion of requests in the first piece of information. Here, rejecting all requests in the first piece of information means rejecting all models requested for download in the first piece of information; rejecting a portion of requests in the first piece of information means rejecting a portion of models requested for download in the first piece of information. The twelfth piece of information may also include, for example, a rejection duration indication and / or a rejection reason indication. For instance, the second piece of information may include a rejection duration indication, or a rejection reason indication, or both.

[0127] The rejection duration indication information is used to indicate that the terminal device is not allowed to request downloading a model within a first duration, or to indicate that the terminal device is not allowed to request downloading the model associated with the rejection duration indication information within a first duration. The first duration can be considered the effective duration of the twelfth message, indicating how long the terminal device must wait before requesting to download the model again. The first duration can be, for example, agreed upon by the protocol, or it can be carried in the rejection duration indication information, meaning the rejection duration indication information indicates the value of the first duration. As an example, the rejection duration indication information can be used to indicate that the terminal device is not allowed to download a model within the first duration (e.g., not allowed to download any model); or, the rejection duration indication information can be used to indicate that the terminal device is not allowed to request downloading the part of the model associated with the rejection duration indication information within the first duration. As an example, corresponding to the case where the twelfth message indicates that all requests in the first message are rejected, the rejection duration indication information in the twelfth message is used to indicate that the terminal device is not allowed to download models (e.g., no models are allowed to be downloaded) within the first duration; corresponding to the case where the twelfth message indicates that some requests in the first message are rejected, the rejection duration indication information in the twelfth message is used to indicate that the terminal device is not allowed to download the part of the models that were rejected within the first duration, in which case the terminal device can download the part of the models that were not rejected.

[0128] The rejection reason indication information is used to indicate the reason why the model download request is rejected. For example, it may include one or more of the following: the network device's resources are congested; the network device does not currently store the model expected by the terminal device; the network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information sent by the terminal device.

[0129] Regarding the third reason for rejection mentioned above, taking one of the second pieces of information in the first information, i.e., the target second information, as an example, suppose the terminal device only provides the target second information and does not provide other information associated with the target second information (e.g., third and / or fourth information associated with the target second information). If the network device determines multiple models based on the target second information, that is, the network device cannot uniquely determine which model to provide to the terminal device, then the model download request of the terminal device can be rejected. In other words, if the model type and / or function type indicated by the target second information is associated with multiple models stored by the network device, then the network device can reject the model download request of the terminal device. Furthermore, suppose the terminal device provides the target second information and its associated third information. If the network device determines multiple models based on the target second information and its associated third information (e.g., multiple models stored by the network device are associated with different seventh indication information), that is, the network device cannot uniquely determine which model to provide to the terminal device, then the model download request of the terminal device can be rejected. Furthermore, assuming the terminal device provides the target second information and its associated fourth information, if the network device determines multiple models based on the target second information and its associated fourth information (e.g., multiple models stored by the network device associated with different first indication information), meaning the network device cannot uniquely determine which model to provide to the terminal device, then it can reject the terminal device's model download request. In the above assumptions, if the network device ultimately determines only one model, meaning the network device can uniquely determine which model to provide to the terminal device, then it will not reject the terminal device's model download request. Furthermore, assuming the terminal device simultaneously provides the target second information and its associated third and fourth information, then because the model-related information provided by the terminal device is sufficient, the model determined by the network device based on the target second information and its associated third and fourth information can uniquely determine which model to provide to the terminal device; in this case, the network device will not reject the terminal device's model download request. Of course, in some cases, if the terminal device provides the target second information and its associated third and fourth information at the same time, but the network device still determines multiple models based on the target second information and its associated third and fourth information, it may also reject the terminal device's model download request. In this case, the terminal device may need to provide more information so that the network device can uniquely determine which model to provide to the terminal device.

[0130] Furthermore, optionally, the network device may also carry in the twelfth information what additional information (e.g., third and / or fourth information) the terminal device needs to provide when it requests to download the model of the same function type again, so that the network device can determine, based on this information, which model to provide the download service to the terminal device among the multiple models associated with the function type. Of course, in other implementations, when the function type indicated by the second information is associated with multiple models stored by the network device, the network device may also allow the terminal device to download all models associated with that function type.

[0131] For example, the range of values ​​for the rejection reason indication information may include: the network device's resources are congested; the network device currently does not store the model expected by the terminal device; multiple models determined by the network device based on one or more of the second, third, and fourth information; the network device's resources are congested and the network device currently does not store the model expected by the terminal device; the network device's resources are congested and the network device currently does not store the model expected by the terminal device; multiple models determined by the network device based on one or more of the second, third, and fourth information; the network device currently does not store the model expected by the terminal device and the network device currently determines multiple models based on one or more of the second, third, and fourth information; or the network device's resources are congested, the network device currently does not store the model expected by the terminal device, and multiple models determined by the network device based on one or more of the second, third, and fourth information.

[0132] In some implementations, the rejection reason indication information may not distinguish between model type or function type. That is, when a terminal device requests to download one or more models via the first information, if the network device intends to reject the terminal device's download request, it will reject all download requests for that one or more models. In other implementations, the rejection reason indication information is associated with the model type or function type. For example, there may be a one-to-one correspondence, a one-to-many correspondence, or a many-to-one correspondence. In this case, the twelfth information also includes the model type (e.g., model identification information) and / or function type (e.g., function identification information) associated with the rejection reason indication information. In other words, for each rejection reason, the network device can simultaneously inform the terminal device which model download requests have been rejected based on that rejection reason. The models rejected for different reasons can be the same or at least partially different.

[0133] In this embodiment, the fifth, ninth, and twelfth information mentioned above are optional and not necessarily required to be sent. That is, steps 220, 230, and 240 shown in FIG2 are optional steps. For example, method 200 in this embodiment may include only step 210; or, include steps 210 and 220; or, include steps 210, 220, and 230; or, include steps 210 and 240; or, include steps 210, 220, and 240; or, include steps 210, 220, 230, and 240.

[0134] Additionally, it should be noted that the network devices involved in the embodiments of this application refer to all devices capable of wireless communication with terminal devices. In some implementations, steps 210, 220, 230, and 240 can be performed by the same network device, or at least some of steps 210, 220, 230, and 240 can be performed by different network devices (e.g., core network devices or access network devices). As an example, in step 210, the terminal device can send first information to the core network device to request downloading its desired model from the core network device, and in step 220, the access network device sends fifth information to the terminal device to inform the terminal device which models the core network device stores. This avoids storing similar model sets on numerous access network devices, and storing models on the core network device occupies less memory overall. Indicating which models are stored on the network side through the access network device is more flexible, especially since the indicated models are models used by the access network. For example, the network devices involved in steps 210 and 220 can both be core network devices or both be access network devices. That is, the network device used for the terminal device to request the query model and the network device used for the terminal device to request the download model are the same network devices. This simplifies management. Optionally, the network devices involved in steps 230 and 220 can be the same network devices, such as both being access network devices or both being core network devices. Optionally, the network devices involved in steps 240 and 210 can be the same network devices, such as both being core network devices or both being access network devices.

[0135] The method embodiments of this application have been described in detail above with reference to Figures 1 and 2. The apparatus embodiments of this application will be described in detail below with reference to Figures 3 to 5. 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 referred to the preceding method embodiments.

[0136] Figure 3 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. The terminal device 300 shown in Figure 3 may include a transceiver unit 310. The transceiver unit 310 is used to send first information to a network device, wherein the first information is used to request the network device to download a model desired by the terminal device, and the first information includes one or more second information, the second information being used to indicate the model type and / or function type of the model desired by the terminal device.

[0137] In some implementations, the model type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the model type of the model desired by the terminal device in one or more pieces of second information; and / or, the functional type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the functional type of the model desired by the terminal device in one or more pieces of second information.

[0138] In some implementations, the second information includes: model identification information of the model desired by the terminal device; and / or, functional identification information of the model desired by the terminal device.

[0139] In some implementations, the first information further includes third information, which includes one or more of the following: first identification information, used to indicate the first applicable condition information of the model association expected by the terminal device and the first identification information is related to the network device; second identification information, used to indicate the second applicable condition information of the model association expected by the terminal device and the second identification information is related to the terminal device; first indication information, used to indicate the model accuracy requirement; and second indication information, used to indicate the model size requirement.

[0140] In some implementations, the first information further includes fourth information, which includes one or more of the following: third indication information, used to indicate the type of input parameters corresponding to the model expected by the terminal device; fourth indication information, used to indicate the number of input parameters corresponding to the model expected by the terminal device; fifth indication information, used to indicate the type of output parameters corresponding to the model expected by the terminal device; sixth indication information, used to indicate the number of output parameters corresponding to the model expected by the terminal device; and seventh indication information, used to indicate the correlation between the input parameters and output parameters corresponding to the model expected by the terminal device.

[0141] In some implementations, the transceiver unit 310 is further configured to: receive fifth information sent by the network device, wherein the fifth information includes one or more sixth information, the sixth information being used to indicate the model type and / or function type of the model stored by the network device.

[0142] In some implementations, the model type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the model type of the model stored by the network device in one or more pieces of sixth information; and / or, the function type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the function type of the model stored by the network device in one or more pieces of sixth information.

[0143] In some implementations, the sixth information includes: model identification information of the model stored by the network device; and / or, functional identification information of the model stored by the network device.

[0144] In some implementations, the fifth information further includes a seventh information, which includes one or more of the following: third identification information, used to indicate third applicable condition information associated with the model stored by the network device and the third identification information is related to the network device; fourth identification information, used to indicate fourth applicable condition information associated with the model stored by the network device and the fourth identification information is related to the terminal device; eighth indication information, used to indicate the accuracy information of the model stored by the network device; and ninth indication information, used to indicate the size information of the model stored by the network device.

[0145] In some implementations, the fifth information further includes an eighth information, which includes: a tenth indication information for indicating the type of input parameters corresponding to the model stored by the network device; an eleventh indication information for indicating the number of input parameters corresponding to the model stored by the network device; a twelfth indication information for indicating the type of output parameters corresponding to the model stored by the network device; a thirteenth indication information for indicating the number of output parameters corresponding to the model stored by the network device; and a fourteenth indication information for indicating the relationship between the input parameters and output parameters corresponding to the model stored by the network device.

[0146] In some implementations, the transceiver unit 310 is further configured to: send a ninth message to the network device, wherein the ninth message includes: a tenth message for requesting a query of association information of a model stored by the network device; and / or one or more eleventh messages, wherein the eleventh message is used to indicate the model type and / or function type of the model requested by the terminal device.

[0147] In some implementations, the transceiver unit 310 is further configured to: receive a twelfth message sent by the network device, wherein the twelfth message is used to reject all requests of the first message or to reject part of the requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

[0148] In some implementations, the rejection duration indication information is used to indicate the value of a first duration, indicating that the terminal device is not allowed to request downloading a model within the first duration, or indicating that the terminal device is not allowed to request downloading a model associated with the rejection duration indication information within the first duration.

[0149] In some implementations, the rejection reason indication information indicates one or more of the following reasons: the network device's resources are in a congested state; the network device currently does not store the model expected by the terminal device; the network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

[0150] It is understood that the transceiver unit 310 may be, for example, a transceiver 530. Additionally, the terminal device 300 may optionally include a processor 510 and a memory 520, as detailed in Figure 5.

[0151] Figure 4 is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device 400 shown in Figure 4 may include a transceiver unit 410. The transceiver unit 410 is used to receive first information sent by a terminal device, wherein the first information is used to request the network device to download a model expected by the terminal device, and the first information includes one or more second information, the second information being used to indicate the model type and / or function type of the model expected by the terminal device.

[0152] In some implementations, the model type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the model type of the model desired by the terminal device in one or more pieces of second information; and / or, the functional type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the functional type of the model desired by the terminal device in one or more pieces of second information.

[0153] In some implementations, the second information includes: model identification information of the model desired by the terminal device; and / or, functional identification information of the model desired by the terminal device.

[0154] In some implementations, the first information further includes third information, which includes one or more of the following: first identification information, used to indicate the first applicable condition information of the model association expected by the terminal device and the first identification information is related to the network device; second identification information, used to indicate the second applicable condition information of the model association expected by the terminal device and the second identification information is related to the terminal device; first indication information, used to indicate the model accuracy requirement; and second indication information, used to indicate the model size requirement.

[0155] In some implementations, the first information further includes fourth information, which includes one or more of the following: third indication information, used to indicate the type of input parameters corresponding to the model expected by the terminal device; fourth indication information, used to indicate the number of input parameters corresponding to the model expected by the terminal device; fifth indication information, used to indicate the type of output parameters corresponding to the model expected by the terminal device; sixth indication information, used to indicate the number of output parameters corresponding to the model expected by the terminal device; and seventh indication information, used to indicate the correlation between the input parameters and output parameters corresponding to the model expected by the terminal device.

[0156] In some implementations, the transceiver unit 410 is further configured to: send fifth information to the terminal device, wherein the fifth information includes one or more sixth information, the sixth information being used to indicate the model type and / or function type of the model stored by the network device.

[0157] In some implementations, the model type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the model type of the model stored by the network device in one or more pieces of sixth information; and / or, the function type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the function type of the model stored by the network device in one or more pieces of sixth information.

[0158] In some implementations, the sixth information includes: model identification information of the model stored by the network device; and / or, functional identification information of the model stored by the network device.

[0159] In some implementations, the fifth information further includes a seventh information, which includes one or more of the following: third identification information, used to indicate third applicable condition information associated with the model stored by the network device and the third identification information is related to the network device; fourth identification information, used to indicate fourth applicable condition information associated with the model stored by the network device and the fourth identification information is related to the terminal device; eighth indication information, used to indicate the accuracy information of the model stored by the network device; and ninth indication information, used to indicate the size information of the model stored by the network device.

[0160] In some implementations, the fifth information further includes an eighth information, which includes: a tenth indication information for indicating the type of input parameters corresponding to the model stored by the network device; an eleventh indication information for indicating the number of input parameters corresponding to the model stored by the network device; a twelfth indication information for indicating the type of output parameters corresponding to the model stored by the network device; a thirteenth indication information for indicating the number of output parameters corresponding to the model stored by the network device; and a fourteenth indication information for indicating the relationship between the input parameters and output parameters corresponding to the model stored by the network device.

[0161] In some implementations, the transceiver unit 410 is further configured to: receive a ninth message sent by the terminal device, wherein the ninth message includes: a tenth message for requesting a query of the association information of the model stored by the network device; and / or one or more eleventh messages, wherein the eleventh message is used to indicate the model type and / or function type of the model requested by the terminal device.

[0162] In some implementations, the transceiver unit 410 is further configured to: send a twelfth message to the terminal device, wherein the twelfth message is used to reject all requests of the first message or to reject part of requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

[0163] In some implementations, the rejection duration indication information is used to indicate the value of a first duration, indicating that the terminal device is not allowed to request downloading a model within the first duration, or indicating that the terminal device is not allowed to request downloading a model associated with the rejection duration indication information within the first duration.

[0164] In some implementations, the rejection reason indication information indicates one or more of the following reasons: the network device's resources are in a congested state; the network device currently does not store the model expected by the terminal device; the network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

[0165] It is understood that the transceiver unit 410 may be, for example, a transceiver 530. Additionally, the network device 400 may optionally include a processor 510 and a memory 520, as detailed in Figure 5.

[0166] Figure 5 is a schematic structural diagram of a communication apparatus according to an embodiment of this application. The dashed lines in Figure 5 indicate that the unit or module is optional. The apparatus 500 can be used to implement the methods described in the above method embodiments. The apparatus 500 may be, for example, a chip, a terminal device, or a network device.

[0167] The apparatus 500 may include one or more processors 510. The processors 510 may support the apparatus 500 in implementing the methods described in the foregoing method embodiments. The processor 510 may be a general-purpose processor or a special-purpose processor. For example, the processor 510 may be a central processing unit (CPU). Alternatively, the processor 510 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0168] The apparatus 500 may also include one or more memories 520. The memories 520 store programs that can be executed by the processor 510, causing the processor 510 to perform the methods described in the above method embodiments. The memories 520 may be independent of the processor 510, or they may be integrated into the processor 510.

[0169] The device 500 may also include a transceiver 530. The processor 510 can communicate with other devices or chips via the transceiver 530. For example, the processor 510 can send and receive data with other devices or chips via the transceiver 530.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] In the several embodiments provided in this application, it should be 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 through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0183] 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 one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0184] 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.

[0185] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer 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 may 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 disks (SSDs)).

[0186] 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 method of wireless communication, comprising: The method comprises: a terminal device sending first information to a network device, wherein the first information is used to request the network device to download a model expected by the terminal device, and the first information comprises one or more second information, and the second information is used to indicate a model type and / or a function type of the model expected by the terminal device.

2. The method of claim 1, wherein the model type of the model expected by the terminal device is determined based on a position of a parameter corresponding to second information associated with the model type of the model expected by the terminal device in the one or more second information; and / or the function type of the model expected by the terminal device is determined based on a position of a parameter corresponding to second information associated with the function type of the model expected by the terminal device in the one or more second information.

3. The method of claim 1, wherein, The second information comprises: model identification information of the model expected by the terminal device; and / or function identification information of the model expected by the terminal device.

4. The method according to any one of claims 1 to 3, characterized in that, The first information further comprises third information, and the third information comprises one or more of the following: first identification information used to indicate first applicable condition information associated with the model expected by the terminal device, and the first identification information is related to the network device; second identification information used to indicate second applicable condition information associated with the model expected by the terminal device, and the second identification information is related to the terminal device; first indication information used to indicate model precision requirement; second indication information used to indicate model size requirement.

5. The method according to any one of claims 1 to 4, characterized in that, The first information further comprises fourth information, and the fourth information comprises one or more of the following: third indication information used to indicate input parameter type corresponding to the model expected by the terminal device; fourth indication information used to indicate input parameter quantity corresponding to the model expected by the terminal device; fifth indication information used to indicate output parameter type corresponding to the model expected by the terminal device; sixth indication information used to indicate output parameter quantity corresponding to the model expected by the terminal device; seventh indication information used to indicate association relationship between input parameter and output parameter corresponding to the model expected by the terminal device.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: the terminal device receiving fifth information sent by the network device, wherein the fifth information comprises one or more sixth information, and the sixth information is used to indicate a model type and / or a function type of a model stored by the network device.

7. The method of claim 6, wherein the model type of the model stored by the network device is determined based on a position of a parameter corresponding to sixth information associated with the model type of the model stored by the network device in the one or more sixth information; and / or the function type of the model stored by the network device is determined based on a position of a parameter corresponding the sixth information associated with the function type of the model stored by the network device in the one or more sixth information.

8. The method of claim 6, wherein, The sixth information comprises: model identification information of the model stored by the network device; and / or function identification information of the model stored by the network device.

9. The method according to any one of claims 6 to 8, characterized in that, The fifth information also includes a seventh information, which includes one or more of the following: The third identification information is used to indicate the third applicable condition information associated with the model stored in the network device, and the third identification information is related to the network device; The fourth identification information is used to indicate the fourth applicable condition information associated with the model stored in the network device, and the fourth identification information is related to the terminal device; The eighth indication information is used to indicate the accuracy information of the model stored by the network device; The ninth indication information is used to indicate the size information of the model stored by the network device.

10. The method according to any one of claims 6 to 9, characterized in that, The fifth piece of information also includes an eighth piece of information, which includes: The tenth indication information is used to indicate the type of input parameters corresponding to the model stored by the network device; The eleventh instruction is used to indicate the number of input parameters corresponding to the model stored by the network device; The twelfth instruction information is used to indicate the type of output parameters corresponding to the model stored by the network device; The thirteenth instruction information is used to indicate the number of output parameters corresponding to the model stored by the network device; The fourteenth instruction information is used to indicate the correlation between the input parameters and output parameters corresponding to the model stored by the network device.

11. The method according to any one of claims 6 to 10, characterized in that, The method further includes: The terminal device sends a ninth message to the network device, wherein the ninth message includes: The tenth piece of information is used to request a query for the association information of the model stored in the network device; and / or, One or more eleventh pieces of information, the eleventh pieces of information being used to indicate the model type and / or function type of the model requested by the terminal device.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: The terminal device receives a twelfth message sent by the network device, wherein the twelfth message is used to reject all requests of the first message or to reject part of the requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

13. The method of claim 12, wherein, The rejection duration indication information is used to indicate the value of the first duration. The rejection duration indication information is used to indicate that the terminal device is not allowed to request to download the model within the first duration, or to indicate that the terminal device is not allowed to request to download the model associated with the rejection duration indication information within the first duration.

14. The method according to claim 12 or 13, characterized in that, The rejection reason indication information indicates one or more of the following reasons: The network device's resources are in a state of congestion; The network device does not currently store the model expected by the terminal device; The network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

15. A method for wireless communication, characterized in that, The network device receives first information sent by the terminal device, wherein the first information is used to request the network device to download the model expected by the terminal device, and the first information includes one or more second information, the second information being used to indicate the model type and / or function type of the model expected by the terminal device.

16. The method according to claim 15, characterized in that, The model type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the model type desired by the terminal device in one or more pieces of second information; and / or, The functional type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the functional type of the model desired by the terminal device in one or more pieces of second information.

17. The method of claim 15, wherein, The second information includes: The model identification information of the model desired by the terminal device; and / or, The terminal device expects functional identification information of the model.

18. The method of any one of claims 15-17, wherein, The first information also includes third information, which includes one or more of the following: The first identification information is used to indicate the first applicable condition information associated with the model expected by the terminal device, and the first identification information is related to the network device; The second identification information is used to indicate the second applicable condition information associated with the model expected by the terminal device, and the second identification information is related to the terminal device; The first indication information is used to indicate the model accuracy requirements; The second instruction is used to indicate the model size requirement.

19. The method according to any one of claims 15 to 18, characterized in that, The first information also includes fourth information, which includes one or more of the following: The third indication information is used to indicate the type of input parameters corresponding to the model expected by the terminal device; The fourth indication information is used to indicate the number of input parameters corresponding to the model expected by the terminal device; The fifth indication information is used to indicate the type of output parameters corresponding to the model expected by the terminal device; The sixth indication information is used to indicate the number of output parameters corresponding to the model expected by the terminal device; The seventh indication information is used to indicate the correlation between the input parameters and output parameters corresponding to the model expected by the terminal device.

20. The method of any one of claims 15-19, wherein, The method further includes: The network device sends fifth information to the terminal device, wherein the fifth information includes one or more sixth information, the sixth information being used to indicate the model type and / or function type of the model stored by the network device.

21. The method according to claim 20, characterized in that, The model type of the model stored by the network device is based on the model stored by the network device in one or more of the sixth information. The location of the parameter corresponding to the sixth piece of information associated with the model type is determined; and / or, The functional type of the model stored in the network device is determined based on the position of the parameter corresponding to the sixth information associated with the functional type of the model stored in the network device in one or more sixth information pieces.

22. The method of claim 20, wherein, The sixth piece of information includes: The network device stores the model identification information of the model; and / or, The network device stores the model's functional identification information.

23. The method of any one of claims 20-22, wherein, The fifth information also includes a seventh information, which includes one or more of the following: The third identification information is used to indicate the third applicable condition information associated with the model stored in the network device, and the third identification information is related to the network device; The fourth identification information is used to indicate the fourth applicable condition information associated with the model stored in the network device, and the fourth identification information is related to the terminal device; The eighth indication information is used to indicate the accuracy information of the model stored by the network device; The ninth indication information is used to indicate the size information of the model stored by the network device.

24. The method of any one of claims 20-23, wherein, The fifth piece of information also includes an eighth piece of information, which includes: The tenth indication information is used to indicate the type of input parameters corresponding to the model stored by the network device; The eleventh instruction is used to indicate the number of input parameters corresponding to the model stored by the network device; The twelfth instruction information is used to indicate the type of output parameters corresponding to the model stored by the network device; The thirteenth instruction information is used to indicate the number of output parameters corresponding to the model stored by the network device; The fourteenth instruction information is used to indicate the correlation between the input parameters and output parameters corresponding to the model stored by the network device.

25. The method of any one of claims 20-24, wherein, The method further includes: The network device receives the ninth information sent by the terminal device, wherein the ninth information includes: The tenth piece of information is used to request a query for the association information of the model stored in the network device; and / or, One or more eleventh pieces of information, the eleventh pieces of information being used to indicate the model type and / or function type of the model requested by the terminal device.

26. The method of any one of claims 15-25, wherein, The method further includes: The network device sends a twelfth message to the terminal device, wherein the twelfth message is used to reject all requests of the first message or to reject part of the requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

27. The method of claim 26, wherein, The rejection duration indication information is used to indicate the value of the first duration. The rejection duration indication information is used to indicate that the terminal device is not allowed to request to download the model within the first duration, or to indicate that the terminal device is not allowed to request to download the model associated with the rejection duration indication information within the first duration.

28. The method of claim 26 or 27, wherein, The rejection reason indication information indicates one or more of the following reasons: The network device's resources are in a state of congestion; The network device does not currently store the model expected by the terminal device; The network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

29. A terminal device, comprising: include: A transceiver unit is configured to send first information to a network device, wherein the first information is used to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being used to indicate the model type and / or function type of the model desired by the terminal device.

30. The terminal device according to claim 29, characterized in that, The model type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the model type desired by the terminal device in one or more pieces of second information; and / or, The functional type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the functional type of the model desired by the terminal device in one or more pieces of second information.

31. The terminal device of claim 29, wherein, The second information includes: The model identification information of the model desired by the terminal device; and / or, The terminal device expects functional identification information of the model.

32. The terminal device of any one of claims 29 to 31, wherein, The first information also includes third information, which includes one or more of the following: The first identification information is used to indicate the first applicable condition information associated with the model expected by the terminal device, and the first identification information is related to the network device; The second identification information is used to indicate the second applicable condition information associated with the model expected by the terminal device, and the second identification information is related to the terminal device; The first indication information is used to indicate the model accuracy requirements; The second instruction is used to indicate the model size requirement.

33. The terminal device of any one of claims 29 to 32, wherein, The first information also includes fourth information, which includes one or more of the following: The third indication information is used to indicate the type of input parameters corresponding to the model expected by the terminal device; The fourth indication information is used to indicate the number of input parameters corresponding to the model expected by the terminal device; The fifth indication information is used to indicate the type of output parameters corresponding to the model expected by the terminal device; The sixth indication information is used to indicate the number of output parameters corresponding to the model expected by the terminal device; The seventh indication information is used to indicate the correlation between the input parameters and output parameters corresponding to the model expected by the terminal device.

34. The terminal device of any one of claims 29-33, wherein, The transceiver unit is also used for: The network device receives fifth information, wherein the fifth information includes one or more sixth information, the sixth information being used to indicate the model type and / or function type of the model stored by the network device.

35. The terminal device according to claim 34, characterized in that, The model type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the model type of the model stored by the network device in one or more pieces of sixth information; and / or, The functional type of the model stored in the network device is determined based on the position of the parameter corresponding to the sixth information associated with the functional type of the model stored in the network device in one or more sixth information pieces.

36. The terminal device of claim 34, wherein, The sixth piece of information includes: The network device stores the model identification information of the model; and / or, The network device stores the model's functional identification information.

37. The terminal device of any one of claims 34 to 36, wherein, The fifth information also includes a seventh information, which includes one or more of the following: The third identification information is used to indicate the third applicable condition information associated with the model stored in the network device, and the third identification information is related to the network device; The fourth identification information is used to indicate the fourth applicable condition information associated with the model stored in the network device, and the fourth identification information is related to the terminal device; The eighth indication information is used to indicate the accuracy information of the model stored by the network device; The ninth indication information is used to indicate the size information of the model stored by the network device.

38. The terminal device of any one of claims 34 to 37, wherein, The fifth piece of information also includes an eighth piece of information, which includes: The tenth indication information is used to indicate the type of input parameters corresponding to the model stored by the network device; The eleventh instruction is used to indicate the number of input parameters corresponding to the model stored by the network device; The twelfth instruction information is used to indicate the type of output parameters corresponding to the model stored by the network device; The thirteenth instruction information is used to indicate the number of output parameters corresponding to the model stored by the network device; The fourteenth instruction information is used to indicate the correlation between the input parameters and output parameters corresponding to the model stored in the network device.

39. The terminal device of any one of claims 34 to 38, wherein, The transceiver unit is also used for: Send a ninth message to the network device, wherein the ninth message includes: The tenth piece of information is used to request a query for the association information of the model stored in the network device; and / or, One or more eleventh pieces of information, the eleventh pieces of information being used to indicate the model type and / or function type of the model requested by the terminal device.

40. The terminal device of any one of claims 31 to 39, wherein, The transceiver unit is also used for: The network device receives a twelfth message, wherein the twelfth message is used to reject all requests of the first message or to reject part of requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

41. The terminal device of claim 40, wherein, The rejection duration indication information is used to indicate the value of the first duration. The rejection duration indication information is used to indicate that the terminal device is not allowed to request to download the model within the first duration, or to indicate that the terminal device is not allowed to request to download the model associated with the rejection duration indication information within the first duration.

42. The terminal device of claim 40 or 41, wherein, The rejection reason indication information indicates one or more of the following reasons: The network device's resources are in a state of congestion; The network device does not currently store the model expected by the terminal device; The network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

43. A network device, characterized in that, A transceiver unit is configured to receive first information sent by a terminal device, wherein the first information is used to request the network device to download a model desired by the terminal device, the first information including one or more second information, the second information being used to indicate the model type and / or function type of the model desired by the terminal device.

44. The network device according to claim 43, characterized in that, The model type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the model type desired by the terminal device in one or more pieces of second information; and / or, The functional type of the model desired by the terminal device is determined based on the position of the parameter corresponding to the second information associated with the functional type of the model desired by the terminal device in one or more pieces of second information.

45. The network device of claim 43, wherein, The second information includes: The model identification information of the model desired by the terminal device; and / or, The terminal device expects functional identification information of the model.

46. The network device according to any of claims 43-45, wherein, The first information also includes third information, which includes one or more of the following: The first identification information is used to indicate the first applicable condition information associated with the model expected by the terminal device, and the first identification information is related to the network device; The second identification information is used to indicate the second applicable condition information associated with the model expected by the terminal device, and the second identification information is related to the terminal device; The first indication information is used to indicate the model accuracy requirements; The second instruction is used to indicate the model size requirement.

47. The network device according to any of claims 43-46, wherein, The first information also includes fourth information, which includes one or more of the following: The third indication information is used to indicate the type of input parameters corresponding to the model expected by the terminal device; The fourth indication information is used to indicate the number of input parameters corresponding to the model expected by the terminal device; The fifth indication information is used to indicate the type of output parameters corresponding to the model expected by the terminal device; The sixth indication information is used to indicate the number of output parameters corresponding to the model expected by the terminal device; The seventh indication information is used to indicate the correlation between the input parameters and output parameters corresponding to the model expected by the terminal device. 48.The network device according to any one of claims 43-47, characterized by, The transceiver unit is also used for: Send fifth information to the terminal device, wherein the fifth information includes one or more sixth information, the sixth information being used to indicate the model type and / or function type of the model stored by the network device.

49. The network device according to claim 48, characterized in that, The model type of the model stored by the network device is determined based on the position of the parameter corresponding to the sixth information associated with the model type of the model stored by the network device in one or more pieces of sixth information; and / or, The functional type of the model stored in the network device is determined based on the position of the parameter corresponding to the sixth information associated with the functional type of the model stored in the network device in one or more sixth information pieces.

50. The network device of claim 48, wherein, The sixth piece of information includes: The network device stores the model identification information of the model; and / or, The network device stores the model's functional identification information.

51. The network device according to any of claims 48-50, wherein, The fifth information also includes a seventh information, which includes one or more of the following: The third identification information is used to indicate the third applicable condition information associated with the model stored in the network device, and the third identification information is related to the network device; The fourth identification information is used to indicate the fourth applicable condition information associated with the model stored in the network device, and the fourth identification information is related to the terminal device; The eighth indication information is used to indicate the accuracy information of the model stored by the network device; The ninth indication information is used to indicate the size information of the model stored by the network device.

52. The network device according to any of claims 48-51, wherein, The fifth piece of information also includes an eighth piece of information, which includes: The tenth indication information is used to indicate the type of input parameters corresponding to the model stored by the network device; The eleventh instruction is used to indicate the number of input parameters corresponding to the model stored by the network device; The twelfth instruction information is used to indicate the type of output parameters corresponding to the model stored by the network device; The thirteenth instruction information is used to indicate the number of output parameters corresponding to the model stored by the network device; The fourteenth instruction information is used to indicate the correlation between the input parameters and output parameters corresponding to the model stored in the network device.

53. The network device of any of claims 48-52, wherein, The transceiver unit is also used for: Receive the ninth message sent by the terminal device, wherein the ninth message includes: The tenth piece of information is used to request a query for the association information of the model stored in the network device; and / or, One or more eleventh pieces of information, the eleventh pieces of information being used to indicate the model type and / or function type of the model requested by the terminal device.

54. The network device of any of claims 43-53, wherein, The transceiver unit is also used for: Send a twelfth message to the terminal device, wherein the twelfth message is used to reject all requests of the first message or to reject part of the requests of the first message, and the twelfth message includes rejection reason indication information and / or rejection duration indication information.

55. The network device of claim 54, wherein, The rejection duration indication information is used to indicate the value of the first duration. The rejection duration indication information is used to indicate that the terminal device is not allowed to request to download the model within the first duration, or to indicate that the terminal device is not allowed to request to download the model associated with the rejection duration indication information within the first duration.

56. The network device of claim 54 or 55, wherein, The rejection reason indication information indicates one or more of the following reasons: The network device's resources are in a state of congestion; The network device does not currently store the model expected by the terminal device; The network device determines multiple models based on one or more of the target second information, the third information associated with the target second information, and the fourth information.

57. A terminal device, comprising: 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 14.

58. A network device, comprising: 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 15 to 28.

59. An apparatus comprising: 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 28.

60. A chip, comprising: 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 28.

61. 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 28.

62. A computer program product, characterised in that, Includes a program that causes a computer to perform the method according to any one of claims 1 to 28.

63. A computer program characterised in that, The computer program causes the computer to perform the method according to any one of claims 1 to 28.

Images