Wireless communication method, terminal device and network device

Abstract

Provided are a wireless communication method, a terminal device and a network device. The wireless communication method comprises: a terminal device receiving first information sent by a network device, wherein the first information is used for data preprocessing before first model inference and / or for first model management.

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] For a pre-trained model, the amount of input data required (i.e., the number of data points) is fixed. When using this model for inference, if the amount of input data provided to the model (i.e., the number of data points) does not match the amount of input data required by the model, the model may fail to perform inference.

[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 receiving first information sent by a network device, the first information being used for data preprocessing before inference of a first model and / or management of the first model.

[0006] In a second aspect, a wireless communication method is provided, comprising: a network device sending first information to a terminal device, the first information being used for data preprocessing before inference of a first model and / or management of the first model.

[0007] Thirdly, a terminal device is provided, comprising: a receiving module for receiving first information sent by a network device, the first information being used for data preprocessing before inference of a first model and / or management of the first model.

[0008] Fourthly, a network device is provided, comprising: a sending module for sending first information to a terminal device, the first information being used for data preprocessing before inference of a first model and / or management of the first model.

[0009] Fifthly, a terminal device is provided, including a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to invoke the computer programs in the memory to cause the terminal device to perform some or all of the steps in the method of the first aspect.

[0010] In a sixth aspect, a network device is provided, including a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to invoke the computer programs in the memory to cause the network device to perform some or all of the steps in the method of the second aspect.

[0011] Seventhly, embodiments of this application provide a communication system including the aforementioned terminal device and / or network device. In another possible design, the system may further include other devices that interact with the terminal device or network device as described in the embodiments of this application.

[0012] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps in the methods described above.

[0013] Ninthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of the methods described in the foregoing aspects. In some implementations, the computer program product may be a software installation package.

[0014] In a tenth aspect, embodiments of this application provide a chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the foregoing aspects.

[0015] In this embodiment, the network device can instruct the terminal device on how to perform data preprocessing and / or model management before model inference using first information. For example, if the amount of input data provided to the model does not match the amount of input data required by the model, the network device can instruct the terminal device on how to perform data preprocessing and / or model management before model inference using the first information. Considering that the network device has more comprehensive information, allowing the terminal device to perform data preprocessing and / or model management based on the network device's instructions helps ensure that the data preprocessing and / or model management methods are more reasonable. Attached Figure Description

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

[0017] Figure 2 is an example diagram of the AI / ML functional framework.

[0018] Figure 3 is a flowchart illustrating the wireless communication method provided in an embodiment of this application.

[0019] Figure 4 is a schematic diagram of the structure of the terminal device provided in the embodiment of this application.

[0020] Figure 5 is a schematic diagram of the structure of the network device provided in an embodiment of this application.

[0021] Figure 6 is a schematic structural diagram of the communication device provided in an embodiment of this application. Detailed Implementation

[0022] Communication system architecture

[0023] Figure 1 is a system architecture example diagram 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 may provide communication coverage for a specific geographical area and may communicate with the terminal device 120 located within that coverage area.

[0024] Figure 1 illustrates an exemplary network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include other numbers of terminal devices within its coverage area. This application embodiment does not limit this.

[0025] Optionally, the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment.

[0026] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: 5th generation (5G) systems or 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 6th generation mobile communication systems, satellite communication systems, and so on.

[0027] The terminal device in this application embodiment can 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 device. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, vehicle-mounted device, etc. The terminal devices in the embodiments of this application can 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, etc. Optionally, the UE can act as a base station. For example, the UE can act as a scheduling entity, providing sidelink signals between UEs in V2X or D2D, etc. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices communicate without relaying communication signals through a base station.

[0028] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, transmitting and receiving point (TRP), transmitting point (TP), master MeNB, auxiliary SeNB, multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. Base stations can also be mobile switching centers, devices that perform base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, network-side devices in 6G networks, and devices that perform base station functions in future communication systems. Base stations 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.

[0029] 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.

[0030] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0031] 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.

[0032] 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 (e.g., a cloud platform).

[0033] Artificial intelligence / machine learning (AI / ML) functions

[0034] The 3rd Generation Partnership Project (3GPP), in its Release 18 (Rel 18), investigated whether AI / ML functions (or AI / ML models) contribute to improving physical layer performance. The relevant research results are documented in Technical Report TR38.843. This report, in addition to recording the evaluation methods and results related to AI / ML functions, also documents the steps and content for managing AI / ML on the network device side, the terminal device side, or both sides. These related contents constitute the content of lifecycle management (LCM) in this technical report. It should be noted that LCM is a broad term, encompassing data collection, model training, function / model identification, model transfer, model inference, function / model selection, activation, deactivation, replacement, and fallback, function / model monitoring, model updates, and terminal device capability reporting, among others.

[0035] To facilitate understanding, the LCM of AI / ML will be introduced below with reference to Figure 2.

[0036] Figure 2 is an example diagram of the functional framework of AI / ML. Referring to Figure 2, AI / ML can include functional modules such as data collection, model training, model storage, model inference, and model management. The data collection module can be used to collect data, such as training data, monitoring data, and inference data. The model training module can use the training data to train the model. The model storage module can be used to store trained or updated models for later use according to actual needs. The model inference module can be used to perform model inference, that is, to obtain the model's output result after providing specific inference data, which is usually a prediction (or inference, estimation) result. The model management module can be used to monitor and / or manage the model. For example, the model management module can use monitoring data (or model labels) to monitor the model and provide feedback to the model training module when the model performance is poor, so that the model can be retrained. Another example is that the model management module can send instructions to the model storage module to complete the deployment of a specific model. Yet another example is that the model management module can send instructions to the model inference module when the model performance is poor or the model is unsuitable, instructing it to deactivate the model.

[0037] As an example, AI / ML can use training data to train a model. After training, the trained (or updated) model is stored for later deployment based on actual needs. Once deployed, communication devices with the model can use it for inference. The model management module can monitor the model's inference process and manage the model based on the monitoring results.

[0038] For a pre-trained model, the amount of input data required is fixed. When using this model for inference, if the amount of input data provided to the model does not match the amount of input data it requires, the model may fail to perform inference. For example, if the amount of input data provided to a model is less than the amount of input data it requires, the model may fail to perform inference. Or, if the amount of input data provided to a model is more than the amount of input data it requires, the model may fail to perform inference.

[0039] Taking Model A for radio resource management (RRM) measurement as an example, assume that Model A requires the input data amount of layer 3-reference signal receiving power (L3-RSRP) of 3 cells, that is, Model A needs 3 L3-RSRP values. When the input data amount provided to Model A is 2 L3-RSRP values, Model A cannot perform inference; when the input data amount provided to Model A is 4 L3-RSRP values, Model A also cannot perform inference.

[0040] Taking Model B for RRM measurement as an example, assume that Model B requires input data of 64 downlink beams from a single cell. During the terminal device's movement, the beam configurations of different cells vary; for example, some cells include 32 downlink beams, some include 64, and some include 128. For cells with 64 downlink beams, the terminal device can directly use Model B for inference. However, for cells with 32 or 128 downlink beams, the terminal device does not know how to use Model B.

[0041] To address the aforementioned issues, this application provides a technical solution that enables model inference and / or model management when the amount of input data provided to the model does not match the amount of input data required (or expected) by the model.

[0042] As one possible implementation, when the amount of input data provided to the model is less than the amount of input data required by the model, this embodiment of the application can enable the model to perform inference by filling in placeholders. Taking the amount of input data required by model A as 3 L3-RSRP values ​​as an example, this embodiment of the application can use the collected 2 L3-RSRP values ​​and one placeholder as the input data of model A to perform inference using model A.

[0043] As another possible implementation, when the amount of input data provided to the model exceeds the amount of input data required by the model, this embodiment can select a portion of the data as the model's input data, enabling the model to perform inference. Taking the requirement of three L3-RSRP values ​​for model A as an example, this embodiment can select three L3-RSRP values ​​from the four collected L3-RSRP values ​​as the input data for model A to perform inference. For instance, this embodiment can use the three largest L3-RSRP values ​​from the four collected L3-RSRP values ​​as the input data for model A.

[0044] However, the above methods are not reasonable in some situations. For example, if the model is able to reason by filling in placeholders, the output results may not be reliable; or, if the model is able to reason by selecting a portion of the data, the selected data may not be appropriate.

[0045] Based on this, embodiments of this application provide a wireless communication method, a terminal device, and a network device. When the amount of input data provided to the model does not match the amount of input data required by the model, the network device can use first information to guide the terminal device in model inference and / or model management. The method embodiments of this application will be described below.

[0046] Figure 3 is a schematic flowchart of a wireless communication method provided in an embodiment of this application. The method shown in Figure 3 is described from the perspective of interaction between a terminal device and a network device, which can be, for example, the terminal device 120 and the network device 110 shown in Figure 1. The method shown in Figure 3 includes step S310, which will be described below.

[0047] In step S310, the terminal device receives first information sent by the network device. This first information can be used to instruct the terminal device to perform model inference and / or model management. Considering that the network device has more comprehensive information, having the terminal device perform model inference and / or model management based on the network device's instructions helps ensure that the model inference and / or model management methods are more reasonable.

[0048] This application does not limit the method of carrying the first information in its embodiments. In some embodiments, the first information may be carried in the measurement configuration message. In some embodiments, the first information may be independent of the measurement configuration message.

[0049] In some embodiments, the statement "first information is independent of measurement configuration message" can be understood as meaning that the first information and the measurement configuration message are different messages.

[0050] In some embodiments, when the first information is independent of the measurement configuration message, the first information may be sent simultaneously with the measurement configuration message or sent at a different time.

[0051] This application does not limit the measurement configuration message. For example, the measurement configuration message may include one or more of the following: radio resource control (RRC) reconfiguration messages (such as RRCReconfiguration messages), and RRC recovery messages (such as RRCResume messages).

[0052] In some embodiments, the first information may be sent based on one or more of the following: the sending of a measurement configuration message, a request from the terminal device, a change in the mobility state of the terminal device, or an implementation of the network device. In other words, the timing of the sending of the first information may be determined based on one or more of the following: the sending of a measurement configuration message, a request from the terminal device, a change in the mobility state of the terminal device, or an implementation of the network device.

[0053] As an example, the first piece of information could be sent at the same time as the measurement configuration message is sent.

[0054] As another example, the first information may be sent by the network device after receiving a request from the terminal device. This application embodiment does not limit the method of carrying the above request. Exemplarily, the above request may be carried in one or more of the following: RRC message, medium access control element (MAC CE), uplink control information (UCI).

[0055] As another example, the first message could be sent when the mobile state of the terminal device changes. For instance, the first message could be sent when the location of the terminal device changes.

[0056] As yet another example, the first message could be sent based on the implementation of the network device.

[0057] In some embodiments, after receiving the first information, the terminal device may store the first information. For example, continuing to refer to FIG3, in some embodiments, the method shown in FIG3 may further include step S320, in which the terminal device stores the first information and forms a local configuration. In some embodiments, this local configuration may be used for data preprocessing before model inference and / or model management; for example, the local configuration may be used for data preprocessing before the first model inference and / or the management of the first model.

[0058] The following section uses the first model as an example to provide a more detailed description of the first information. It should be noted that the first model can be any model; for example, it can be any AI / ML model deployed on the terminal device side, and this application embodiment is not limited in this regard. As an example, the first model can be an AI / ML model used to predict measurement results related to the mobility of the terminal device, such as predicting RRM measurement results. As another example, the first model can be an AI / ML model used in data retransmission scenarios. As yet another example, the first model can be an AI / ML model used in beam management scenarios.

[0059] In some embodiments, the first information may be used for data preprocessing before the first model inference and / or for the management of the first model.

[0060] In some embodiments, data preprocessing prior to inference of the first model and / or management of the first model are triggered by the terminal device. For example, after the terminal device determines the input data (or input information) to be used for inference using the first model based on the first information, the terminal device can perform inference of the first model based on the input data. As another example, after the terminal device determines to deactivate the first model based on the first information, the terminal device can deactivate the first model.

[0061] In some embodiments, data preprocessing before the first model inference and / or the management of the first model are triggered by the network device. For example, after the terminal device determines to deactivate the first model based on the first information, the terminal device can deactivate the first model after receiving the deactivation instruction information sent by the network device.

[0062] In some embodiments, the first information used for data preprocessing before the first model inference may include: when the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information may be used for data preprocessing before the first model inference.

[0063] In some embodiments, the first information used for data preprocessing before the first model inference can be understood or replaced by one or more of the following: the first information can be used to preprocess the input data used during the first model inference, or the first information can be used to determine the input data used when using the first model for inference. For example, if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information can be used to preprocess the input data used during the first model inference or to determine the input data used when using the first model for inference.

[0064] This application does not limit the implementation method of using the first information for data preprocessing before the first model inference, or in other words, this application does not limit the implementation method of using the first information to determine the input data used when using the first model for inference. As one possible implementation, the first information can be used to indicate the input data used when using the first model for inference. As another possible implementation, the first information can be used to indicate the priority of the input data used when using the first model for inference. As yet another possible implementation, the first information can be used to indicate the input data used when using the first model for inference and the priority of the used input data.

[0065] In some embodiments, the use of first information for the management of a first model may include: when the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information may be used for the management of the first model.

[0066] In some embodiments, the first information used for managing the first model may include: the first information may be used to determine the processing method corresponding to the first model. For example, if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information may be used to determine the processing method corresponding to the first model.

[0067] In some embodiments, the processing method corresponding to the first model can be understood or replaced by one or more of the following: the reasoning method of the first model, the management method of the first model.

[0068] This application does not limit the processing method corresponding to the first model. For example, the processing method corresponding to the first model may include one or more of the following: deactivating the first model, not using (or stopping) the first model for inference, or using (or continuing to use) the first model for inference.

[0069] As an example, the use of first information for managing the first model can include: using first information to deactivate the first model. For instance, if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information can be used to deactivate the first model.

[0070] In some embodiments, after the terminal device deactivates the first model, it can operate in a non-AI manner, or in other words, it can revert to operating in a non-AI manner. Taking the first model as an example for predicting RRM measurement results, after the terminal device deactivates the first model, it can actually perform RRM measurements to obtain the RRM measurement results.

[0071] In some embodiments, after the terminal device deactivates the first model, it can activate other models besides the first model to perform operations. Taking the first model used to predict RRM measurement results as an example, after the terminal device deactivates the first model, it can activate other models used to predict RRM measurement results (such as the second model) to predict the RRM measurement results.

[0072] In some embodiments, after the terminal device deactivates the first model, it can switch to another model other than the first model for operation. This other model may be, for example, an already activated model. Taking the first model as an example for predicting RRM measurement results, after the terminal device deactivates the first model, it can switch to another model (such as the third model) used to predict RRM measurement results to predict the RRM measurement results.

[0073] As another example, the first information used for managing the first model can include: the first information indicating that the first model should not be used for inference. For example, if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information can be used to indicate that the first model should not be used for inference.

[0074] In some embodiments, after the terminal device does not use the first model for inference, it can operate in a non-AI manner, or in other words, it can revert to operating in a non-AI manner. Taking the first model as an example for predicting RRM measurement results, after the terminal device does not use the first model for inference, it can actually perform RRM measurement to obtain the RRM measurement results.

[0075] In some embodiments, after the terminal does not use the first model for inference, the terminal device can use (e.g., activate or switch to) other models besides the first model for operation. Taking the first model as an example for predicting RRM measurement results, after the terminal device does not use the first model for inference, it can use other models (such as the second model) for predicting RRM measurement results to predict the RRM measurement results.

[0076] As yet another example, the first information used for managing the first model can include: the first information being used to instruct the use of the first model for inference. For instance, if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first information can be used to instruct the use of the first model for inference.

[0077] In some embodiments, the first information used for data preprocessing before inference of the first model and for the management of the first model may include: the first information may be used to indicate the use of the first model for inference and to determine the input data used when using the first model for inference.

[0078] In other words, in some embodiments, the first information may be used to indicate one or more of the following: deactivating the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; not using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; and the priority of the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0079] In some embodiments, the first information may be used to indicate one of the aforementioned information.

[0080] As an example, the first information can be used to indicate when the amount of input data provided to the first model does not match the amount of input data required by the first model, so as to activate the first model.

[0081] As another example, the first information can be used to indicate that if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model should not be used for inference.

[0082] As another example, the first information can be used to indicate that the first model should be used for inference if the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0083] As yet another example, the first information can be used to indicate the input data used when performing inference with the first model if the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0084] As yet another example, the first information can be used to indicate the priority of the input data used when performing inference with the first model if the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0085] In some embodiments, the first information may be used to indicate multiple of the information described above.

[0086] As an example, the first information can be used to indicate that if the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model should be activated but not used for inference.

[0087] As another example, the first information can be used to indicate the use of the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model, and to indicate the input data used when using the first model for inference.

[0088] As yet another example, the first information can be used to indicate the use of the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model, and to indicate the priority of the input data used when using the first model for inference.

[0089] Taking the first model used to predict measurements related to the mobility of terminal devices (e.g., the first model used to predict RRM measurements) as an example, the first information can be used to indicate one or more of the following: deactivating the first model, not using the first model for inference, using the first model for inference, cell priority, beam priority, beam pair priority, cell information used when using the first model for inference, beam information used when using the first model for inference, and beam pair information used when using the first model for inference.

[0090] As an example, when the first model is used to predict measurements related to the mobility of a terminal device, the first information can be used to instruct the activation of the first model.

[0091] As another example, when the first model is used to predict measurements related to the mobility of a terminal device, the first information can be used to instruct the use of the first model for inference, and to fill in missing input data with placeholders when using the first model for inference.

[0092] As yet another example, when the first model is used to predict measurements related to the mobility of a terminal device, the first information can be used to indicate the priority of a cell, or to indicate the cell information used when inference is performed using the first model, so that the terminal device can select data from high-priority cells as input data for inference of the first model.

[0093] As yet another example, when the first model is used to predict measurement results related to the mobility of the terminal device, the first information can be used to indicate the priority of the beam / beam pair, or to indicate the information of the beam / beam pair used when inference using the first model, so that the terminal device selects the data of the high-priority beam / beam pair as the input data when the first model is inferred.

[0094] As yet another example, when the first model is used to predict measurement results related to the mobility of a terminal device, the first information can be used to indicate the priority of the cell and the priority of the beam / beam pair, or to indicate the information of the cell and the information of the beam / beam pair used when using the first model for inference, so that the terminal device selects data of the high-priority cell and the high-priority beam / beam pair as input data when the first model is used for inference.

[0095] In scenarios where the first model is used to predict measurement results related to the mobility of a terminal device, the input data provided to the first model and / or the input data required by the first model may include one or more of the following: cell-level input data, beam-level input data, and beam-pair-level input data. For example, the input data of the first model may include RSRP measurement information of a cell (cell-level input data). Another example is that the input data of the first model may include L1-RSRP measurement information of a downlink beam in a cell (beam-level input data). Yet another example is that the input data of the first model may include L1-RSRP measurement information of a beam pair between a cell and a terminal device (beam-pair-level input data). Yet another example is that the input data of the first model may include both cell-level input data and beam / beam-pair-level input data; for instance, the terminal device needs to select 3 cells from 4 cells as input data for the model based on first information, and further select L1-RSRP measurement information of 8 beams from the 32 downlink beams of each of the 3 cells as input data for the model.

[0096] In some embodiments, the phrase "the amount of input data provided to the first model does not match the amount of input data required by the first model" mentioned in this application may include: the amount of input data provided to the first model is less than the amount of input data required by the first model.

[0097] In some embodiments, the phrase "the amount of input data provided to the first model does not match the amount of input data required by the first model" mentioned in this application may include: the amount of input data provided to the first model is greater than the amount of input data required by the first model.

[0098] To facilitate understanding, the following describes the content of the first information in different scenarios, in conjunction with Examples 1 and 2.

[0099] Example 1: The amount of input data provided to the first model is less than the amount of input data required by the first model.

[0100] In some embodiments, if the amount of input data provided to the first model is less than the amount of input data required by the first model, the first information may be used to indicate one or more of the following: deactivating the first model, not using the first model for inference, using the first model for inference, and the input data used when using the first model for inference.

[0101] In some embodiments, when the amount of input data provided to the first model is less than the amount of input data required by the first model, if the first information indicates the input data used when performing inference using the first model, then the input data used when performing inference using the first model may include placeholders. This application embodiment does not limit the placeholders used when performing inference using the first model; the placeholders can be data of any type, such as character data, numeric data, etc. In some embodiments, the data type of the placeholders can be the same as the data type of the input data provided to the first model. For example, when the data type of the input data provided to the first model is numeric, the placeholders can also be numeric.

[0102] As an example, if the amount of input data provided to the first model is less than the amount of input data required by the first model, the first information can instruct the activation of the first model or the non-use of the first model for inference. In this way, when the first model is not applicable, the embodiments of this application help to avoid the first model outputting unreliable results.

[0103] As another example, when the amount of input data provided to the first model is less than the amount of input data required by the first model, the first information can instruct the use of the first model for inference, and to fill in the missing input data with placeholders when using the first model for inference. In this way, the first model has strong generalization performance and can handle model inference under different data missing conditions.

[0104] It should be noted that Embodiment 1 is not limited to scenarios where the amount of input data provided to the first model is less than the amount of input data required by the first model, but is applicable to all scenarios where the amount of input data provided to the first model does not match the amount of input data required by the first model. For example, Embodiment 1 can also be applied to scenarios where the amount of input data provided to the first model is more than the amount of input data required by the first model. That is, when the amount of input data provided to the first model is more than the amount of input data required by the first model, the network device can also send first information to the terminal device to instruct one or more of the following: deactivate the first model, not use the first model for inference, use the first model for inference, and the input data used when using the first model for inference.

[0105] As an example, if the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information can be used to indicate whether to activate the first model or not to use the first model for inference.

[0106] As another example, if the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information can be used to instruct the first model to be used for inference.

[0107] As another example, when the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information can be used to indicate the input data used when performing inference using the first model.

[0108] As another example, when the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information can be used to indicate the use of the first model for inference and the input data used when using the first model for inference.

[0109] In some embodiments, if the amount of input data provided to the first model is greater than the amount of input data required by the first model, and if the first information can indicate the input data used when using the first model for inference, then the first information can indicate the input data used when using the first model for inference in the manner of Embodiment 2.

[0110] Example 2: The amount of input data provided to the first model is greater than the amount of input data required by the first model.

[0111] In some embodiments, if the amount of input data provided to the first model exceeds the amount of input data required by the first model, the terminal device needs to determine (determine) which input data should be used as input data for the first model. In this case, the first information can be used to determine the input data used when performing inference using the first model.

[0112] In some embodiments, if the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information may be used to indicate one or more of the following: the input data used when performing inference using the first model, and the priority of the input data used when performing inference using the first model.

[0113] Taking the first model used to predict measurement results related to the mobility of terminal devices (e.g., the first model used to predict RRM measurement results) as an example, the first information may be used to indicate one or more of the following: cell priority, beam priority, beam pair priority, cell information used when using the first model for inference, beam information used when using the first model for inference, and beam pair information used when using the first model for inference.

[0114] In some embodiments, the cell priority and / or the cell information used when inference using the first model can be indicated by one or more of the following: cell identification information that is prioritized for inference of the first model, cell priority indication information, a first threshold corresponding to the cell measurement results, and information on the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input.

[0115] In some embodiments, the first information may indicate identification information (or a set of cell identifiers) of one or more cells to indicate cells that are preferentially used for inference in the first model. In this way, if the terminal device detects a cell containing the cell indicated by the first information, it preferentially uses the information of that cell as input data for model inference.

[0116] This application does not limit the cell identification information. For example, the cell identification information may include one or more of the following: physical cell identifier (PCI), cell global identifier (CGI), and cell index.

[0117] This application does not limit the indication of cell identification information preferentially used for inference in the first model. In some embodiments, the cell identification information preferentially used for inference in the first model may be sent independently of the measurement configuration information; for example, the cell identification information preferentially used for inference in the first model may be sent based on the location update of the terminal device. In some embodiments, the cell identification information preferentially used for inference in the first model may be sent simultaneously with the measurement configuration information.

[0118] In some embodiments, cell priority indication information can be used to indicate the priority of one or more cells so that the terminal device can preferentially use information from higher-priority cells as input data for model inference.

[0119] In some embodiments, cell priority indication information can be sent simultaneously with the measurement configuration message. For example, the cell priority indication information can be carried in the measurement configuration message. As an example, the cell priority indication information can be included in the measConfig, where the cell priority is explicitly indicated. However, this embodiment is not limited to this; for example, the network device can indicate the priority of one or more cells to the terminal device separately.

[0120] As one possible implementation, a cell can correspond to 1 bit of indication information to indicate the priority of the cell, that is, whether the information of the cell is given priority as input data of the first model.

[0121] In some embodiments, if the cell measurement result of the first cell is greater than or equal to a first threshold, the first cell is preferentially used for inference of the first model; and / or, if the cell measurement result of the first cell is less than the first threshold, the first cell is not preferentially used for inference of the first model.

[0122] This application does not specifically limit the measurement quantities corresponding to the cell measurement results. Exemplarily, the measurement quantities corresponding to the cell measurement results may include one or more of the following: RSRP, reference signal receiving quality (RSRQ), signal to interference plus noise ratio (SINR), and received signal strength indicator (RSSI). For example, the measurement quantities corresponding to the cell measurement results may be RSRP, RSRQ, SINR, or RSSI. Another example is that the measurement quantities corresponding to the cell measurement results may be RSRP and RSRQ. Yet another example is that the measurement quantities corresponding to the cell measurement results may be RSRP and SINR, and so on.

[0123] In some embodiments, the cell priority and / or information about the cells used in inference using the first model can be indicated by one of the aforementioned information. As an example, the cell priority and / or information about the cells used in inference using the first model can be indicated by identification information of cells preferentially used for inference in the first model. As another example, the cell priority and / or information about the cells used in inference using the first model can be indicated by cell priority indication information. As yet another example, the cell priority and / or information about the cells used in inference using the first model can be indicated by a first threshold corresponding to the cell measurement results. As yet another example, the cell priority and / or information about the cells used in inference using the first model can be indicated by information about the M cells with the best measurement results in the cell measurement results.

[0124] In some embodiments, the cell priority and / or information about the cells used in inference using the first model can be indicated by a variety of the information described above. As an example, the cell priority and / or information about the cells used in inference using the first model can be indicated by the identification information of the cells preferentially used for inference in the first model and a first threshold corresponding to the cell measurement results. As another example, the cell priority and / or information about the cells used in inference using the first model can be indicated by cell priority indication information and a first threshold corresponding to the cell measurement results. For simplicity, other combinations are not listed.

[0125] In some embodiments, if the cell priority and / or the cell information used for inference using the first model can be indicated by multiple pieces of information described above, the priorities of these multiple pieces of information can be different. For example, the priority of the cell priority indication information can be higher than the priority of the information of the M cells with the best measurement results in the cell measurement results. As another example, the priority of the information of the M cells with the best measurement results in the cell measurement results can be higher than the priority of the cell priority indication information. As yet another example, the priority of the cell identification information preferentially used for inference in the first model is higher than the priority of the first threshold corresponding to the cell measurement results, and so on. For the sake of brevity, other possible priority orders are not listed.

[0126] In some embodiments, cell priority can include multiple levels, such as cells including highest priority cells, second priority cells, and low priority cells. As an example, the cell identification information prioritized for inference in the first model indicates six cells: {1,3,5,6,7,8}, where cells {1,3} are the highest priority cells, and cells {5,6,7,8} are the second priority cells. As another example, cell priority indication information can be used to indicate whether a cell is a highest priority cell, a second priority cell, or a low priority cell, etc.

[0127] In some embodiments, beam priority and / or information about the beams used for inference with the first model can be indicated by one or more of the following: identification information of beams preferentially used for inference of the first model, beam priority indication information, a second threshold corresponding to the beam measurement results, information on the N best-performing beams in the beam measurement results, where N is the number of beams that the first model needs to input. In some embodiments, N and M can be the same or different.

[0128] In some embodiments, the first information may indicate identification information (or a set of beam identifiers) for one or more beams to indicate beams that are preferentially used for inference of the first model. In this way, if the terminal device detects that a beam contains the beam indicated by the first information, it preferentially uses the information of that beam as input data for model inference.

[0129] This application does not limit the beam identification information. For example, the beam identification information can be indicated by one or more of the following: synchronization signal block (SSB) index, channel state information reference signal (CSI-RS) number.

[0130] This application does not limit the indication of the identification information of the beams preferentially used for inference of the first model. In some embodiments, the identification information of the beams preferentially used for inference of the first model may be sent independently of the measurement configuration information; for example, the identification information of the beams preferentially used for inference of the first model may be sent based on the location update of the terminal device. In some embodiments, the identification information of the beams preferentially used for inference of the first model may be sent simultaneously with the measurement configuration information.

[0131] In some embodiments, beam priority indication information can be used to indicate the priority of one or more beams so that the terminal device preferentially uses information from higher-priority beams as input data during model inference.

[0132] In some embodiments, beam priority indication information can be sent simultaneously with the measurement configuration message. For example, the beam priority indication information can be carried in the measurement configuration message. As an example, the beam priority indication information can be included in measConfig, where the beam priority is explicitly indicated. However, the embodiments of this application are not limited to this; for example, the network device can indicate the priority of one or more beams to the terminal device separately.

[0133] As one possible implementation, a beam can correspond to 1 bit of indication information to indicate the priority of the beam, that is, whether the information of the beam is given priority as the input data of the first model.

[0134] In some embodiments, if the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or, if the beam measurement result of the first beam is less than the second threshold, the first beam is not preferentially used for inference of the first model.

[0135] In some embodiments, the priority of beam pairs and / or the information of beam pairs used when performing inference with the first model can be indicated by one or more of the following: identification information of beam pairs that are given priority for inference of the first model, indication information of beam pair priority, a third threshold corresponding to the beam pair measurement results, information of the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input. In some embodiments, K and M can be the same or different. In some embodiments, K and N can be the same or different.

[0136] In some embodiments, the first information may indicate identification information (or a set of beam pair identifiers) for one or more beam pairs to indicate beam pairs that are preferentially used for inference of the first model. In this way, if the terminal device detects that a beam pair contains the beam pair indicated by the first information, it preferentially uses the information of that beam pair as input data for model inference.

[0137] This application does not limit the identification information of beam pairs. Exemplarily, the identification information of beam pairs can be indicated by one or more of the following: SSB index, CSI-RS number.

[0138] This application does not limit the indication of the identification information of beam pairs preferentially used for inference of the first model. In some embodiments, the identification information of beam pairs preferentially used for inference of the first model may be sent independently of the measurement configuration information; for example, the identification information of beam pairs preferentially used for inference of the first model may be sent based on the location update of the terminal device. In some embodiments, the identification information of beam pairs preferentially used for inference of the first model may be sent simultaneously with the measurement configuration information.

[0139] In some embodiments, beam pair priority indication information can be used to indicate the priority of one or more beam pairs so that the terminal device preferentially uses the information of the higher priority beam pair as input data during model inference.

[0140] In some embodiments, beam pair priority indication information can be sent simultaneously with the measurement configuration message. For example, the beam pair priority indication information can be carried in the measurement configuration message. As an example, the beam pair priority indication information can be included in measConfig, where the priority of the beam pair is explicitly indicated. However, the embodiments of this application are not limited to this; for example, the network device can indicate the priority of one or more beam pairs to the terminal device separately.

[0141] As one possible implementation, a beam pair can correspond to 1 bit of indication information to indicate the priority of the beam pair, that is, whether the information of the beam pair is given priority as input data of the first model.

[0142] In some embodiments, if the beam measurement result of the first beam pair is greater than or equal to a third threshold, the first beam pair is preferentially used for inference of the first model; and / or, if the beam measurement result of the first beam pair is less than the third threshold, the first beam pair is not preferentially used for inference of the first model.

[0143] This application does not specifically limit the measurement quantities corresponding to the beam measurement results. Exemplarily, the measurement quantities corresponding to the beam measurement results may include one or more of the following: RSRP, RSRQ, SINR, and RSSI. For example, the measurement quantities corresponding to the beam measurement results may be RSRP, RSRQ, SINR, or RSSI. Another example is that the measurement quantities corresponding to the beam measurement results may be RSRP and RSRQ. Yet another example is that the measurement quantities corresponding to the beam measurement results may be RSRP and SINR, and so on.

[0144] In some embodiments, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by one of the aforementioned information. As an example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by identification information of beam / beam pairs preferentially used for inference with the first model. As another example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by beam / beam pair priority indication information. As yet another example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by thresholds (such as a second threshold and / or a third threshold) corresponding to the beam measurement results. As yet another example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by the M beams with the best measurement results from the beam measurement results / beam pair measurement results.

[0145] In some embodiments, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by a variety of the information described above. As an example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by the identification information of the beam / beam pair preferentially used for inference with the first model and the threshold corresponding to the beam measurement results. As another example, the priority of a beam / beam pair and / or the information of the beam / beam pair used during inference with the first model can be indicated by the indication information of the beam / beam pair priority and the threshold corresponding to the beam measurement results. For simplicity, other combinations are not listed.

[0146] In some embodiments, if the priority of a beam / beam pair and / or the information about the beam / beam pair used during inference using the first model can be indicated by multiple pieces of information described above, these multiple pieces of information may have different priorities. For example, the priority of information indicating beam / beam pair priority may be higher than the priority of information about the M best beam / beam pairs in the beam measurement results / beam pair measurement results. As another example, the priority of information about the M best beam / beam pairs in the beam measurement results / beam pair measurement results may be higher than the priority of information indicating beam / beam pair priority. For simplicity, other possible priority orders are not listed.

[0147] In some embodiments, the priority of beam / beam pairs can include multiple levels. For example, beam / beam pairs can include the highest priority beam / beam pair, the second priority beam / beam pair, the low priority beam / beam pair, etc. As an example, the identification information of the beams preferentially used for inference of the first model indicates six beams {1,3,5,6,7,8}, where beams {1,3} are the highest priority beams, and beams {5,6,7,8} are the second priority beams. As another example, the indication information of beam / beam pair priority can be used to indicate that a beam / beam pair is the highest priority beam / beam pair, or the second priority beam / beam pair, or the low priority beam / beam pair, etc.

[0148] The embodiments of this application do not limit the values ​​of the first threshold, the second threshold, and the third threshold, which can be set according to actual needs. In some embodiments, the first threshold, the second threshold, and the third threshold may be different. In some embodiments, the first threshold, the second threshold, and the third threshold may be partially or completely the same.

[0149] The method embodiments of this application have been described in detail above with reference to Figures 1 to 3. The apparatus embodiments of this application will be described in detail below with reference to Figures 4 to 6. 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.

[0150] Figure 4 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. The terminal device 400 shown in Figure 4 includes a receiving module 410. The receiving module 410 can be used to receive first information sent by a network device, the first information being used for data preprocessing before the first model inference and / or the management of the first model.

[0151] In some embodiments, the first information is used to determine one or more of the following: the processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; the input data used when performing inference using the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0152] In some embodiments, the first information is used to indicate one or more of the following: deactivating the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; not using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; and the priority of the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0153] In some embodiments, the mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: deactivating the first model; not using the first model for inference; using the first model for inference; and the input data used when using the first model for inference.

[0154] In some embodiments, if the first information indicates input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

[0155] In some embodiments, the mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, wherein the first information is used to indicate one or more of the following: the input data used when performing inference using the first model; the priority of the input data used when performing inference using the first model.

[0156] In some embodiments, the first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information is used to indicate one or more of the following: cell priority; beam priority; beam pair priority; cell information used when using the first model for inference; beam information used when using the first model for inference; and beam pair information used when using the first model for inference.

[0157] In some embodiments, the priority of the cell and / or the cell information used when performing inference using the first model is indicated by one or more of the following: identification information of cells that are preferentially used for inference using the first model, and indication information of cell priority. The first threshold corresponding to the cell measurement results, the information of the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or the beam priority and / or the beam information used when using the first model for inference is indicated by one or more of the following: the identification information of the beams that are preferentially used for inference of the first model, the beam priority indication information, the second threshold corresponding to the beam measurement results, the information of the N beams with the best measurement results in the beam measurement results, where N is the number of beams that the first model needs to input; and / or the beam pair priority and / or the beam pair information used when using the first model for inference is indicated by one or more of the following: the identification information of the beam pairs that are preferentially used for inference of the first model, the beam pair priority indication information, the third threshold corresponding to the beam pair measurement results, the information of the K beam pairs with the best measurement results in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

[0158] In some embodiments, if the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or if the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or if the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

[0159] In some embodiments, the first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

[0160] In some embodiments, the first information is sent based on one or more of the following: the sending of a measurement configuration message; a request from the terminal device; a change in the mobility state of the terminal device; or an implementation of the network device.

[0161] In some embodiments, the terminal device further includes a storage module 420 for storing the first information and forming a local configuration, the local configuration being used for data preprocessing before the first model inference and / or for the management of the first model.

[0162] In some embodiments, data preprocessing before the first model inference and / or management of the first model are triggered by the terminal device or the network device.

[0163] In some embodiments, the receiving module 410 may be a transceiver 630. The terminal device 400 may also include a processor 610 and a memory 620, as shown in FIG6.

[0164] Figure 5 is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device 500 shown in Figure 5 includes a sending module 510. The sending module 510 can be used to send first information to a terminal device, the first information being used for data preprocessing before the first model inference and / or the management of the first model.

[0165] In some embodiments, the first information is used to determine one or more of the following: the processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; the input data used when performing inference using the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0166] In some embodiments, the first information is used to indicate one or more of the following: deactivating the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; not using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model; and the priority of the input data used when using the first model for inference when the amount of input data provided to the first model does not match the amount of input data required by the first model.

[0167] In some embodiments, the mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: deactivating the first model; not using the first model for inference; using the first model for inference; and the input data used when using the first model for inference.

[0168] In some embodiments, if the first information indicates input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

[0169] In some embodiments, the mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, wherein the first information is used to indicate one or more of the following: the input data used when performing inference using the first model; the priority of the input data used when performing inference using the first model.

[0170] In some embodiments, the first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model is greater than the amount of input data required by the first model, the first information is used to indicate one or more of the following: cell priority; beam priority; beam pair priority; cell information used when using the first model for inference; beam information used when using the first model for inference; and beam pair information used when using the first model for inference.

[0171] In some embodiments, the priority of the cells and / or the information of the cells used when performing inference using the first model is indicated by one or more of the following: identification information of cells preferentially used for inference of the first model, indication information of cell priority, a first threshold corresponding to the cell measurement results, and information of the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or the priority of the beam and / or the information of the beam used when performing inference using the first model is indicated by one or more of the following: identification information of the beam preferentially used for inference of the first model. Information, including beam priority indication information, a second threshold corresponding to the beam measurement results, information on the N best beams in the beam measurement results, where N is the number of beams that the first model needs to input; and / or the priority of the beam pairs and / or the information on the beam pairs used when performing inference using the first model are indicated by one or more of the following: identification information of beam pairs that are preferentially used for inference of the first model, beam pair priority indication information, a third threshold corresponding to the beam pair measurement results, information on the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

[0172] In some embodiments, if the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or if the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or if the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

[0173] In some embodiments, the first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

[0174] In some embodiments, the first information is sent based on one or more of the following: the sending of a measurement configuration message; a request from the terminal device; a change in the mobility state of the terminal device; or an implementation of the network device.

[0175] In some embodiments, data preprocessing before the first model inference and / or management of the first model are triggered by the terminal device or the network device.

[0176] In some embodiments, the transmitting module 510 may be a transceiver 630. The network device 500 may also include a processor 610 and a memory 620, as shown in FIG6.

[0177] Figure 6 is a schematic structural diagram of a communication device according to an embodiment of this application. The dashed lines in Figure 6 indicate that the unit or module is optional. This device 600 can be used to implement the methods described in the above method embodiments. Device 600 can be a chip, a terminal device, or a network device.

[0178] Apparatus 600 may include one or more processors 610. The processor 610 may support apparatus 600 in implementing the methods described in the preceding method embodiments. The processor 610 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may 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. The general-purpose processor may be a microprocessor or any conventional processor.

[0179] The apparatus 600 may further include one or more memories 620. The memories 620 store a program that can be executed by the processor 610, causing the processor 610 to perform the methods described in the preceding method embodiments. The memories 620 may be independent of the processor 610 or integrated within the processor 610.

[0180] The device 600 may also include a transceiver 630. The processor 610 can communicate with other devices or chips via the transceiver 630. For example, the processor 610 can send and receive data with other devices or chips via the transceiver 630.

[0181] 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 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.

[0182] 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 the embodiments of this application, 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.

[0183] 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 various embodiments of this application.

[0184] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] In the embodiments of this application, the term "comprising" can refer to direct inclusion or indirect inclusion. Optionally, "comprising" in the embodiments of this application can be replaced with "instructing" or "used to determine". For example, "A includes B" can be replaced with "A instructs B" or "A is used to determine B".

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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), etc.

[0197] 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 for wireless communication, characterized in that, include: The terminal device receives first information sent by the network device, and the first information is used for data preprocessing before the first model inference and / or management of the first model.

2. The method according to claim 1, characterized in that, The first information is used to determine one or more of the following: The processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model.

3. The method according to claim 1 or 2, characterized in that, The first information is used to indicate one or more of the following: If the amount of input data provided to the first model does not match the amount of input data required by the first model, then the first model is activated. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model will not be used for inference. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model is used for inference. When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model; If the amount of input data provided to the first model does not match the amount of input data required by the first model, the priority of the input data used when performing inference using the first model.

4. The method according to claim 2 or 3, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: Deactivate the first model; Inference is not performed using the first model; Use the first model for reasoning; The input data used when performing inference using the first model.

5. The method according to claim 4, characterized in that, If the first information indicates the input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

6. The method according to claim 2 or 3, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: The input data used when performing inference using the first model; The priority of the input data used when performing inference using the first model.

7. The method according to any one of claims 1-6, characterized in that, The first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model exceeds the amount of input data required by the first model, the first information is used to indicate one or more of the following: Community priority; Beam priority; Beam pair priority; The cell information used when performing inference using the first model; The beam information used when performing inference using the first model; Information about the beam pairs used when performing inference using the first model.

8. The method according to claim 7, characterized in that: The priority of the cells and / or the cell information used when performing inference using the first model is indicated by one or more of the following: cell identification information prioritized for inference using the first model, cell priority indication information, a first threshold corresponding to the cell measurement results, and information on the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or The beam priority and / or the beam information used when performing inference using the first model are indicated by one or more of the following: identification information of beams preferentially used for inference of the first model, beam priority indication information, a second threshold corresponding to the beam measurement results, information of the N beams with the best measurement results in the beam measurement results, where N is the number of beams that the first model needs to input. The number of bundles; and / or The priority of the beam pairs and / or the information of the beam pairs used when inference using the first model is indicated by one or more of the following: identification information of beam pairs that are given priority for inference of the first model, indication information of beam pair priority, a third threshold corresponding to the beam pair measurement results, and information of the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

9. The method according to claim 8, characterized in that: If the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

10. The method according to any one of claims 1-9, characterized in that, The first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

11. The method according to any one of claims 1-10, characterized in that, The first information is sent based on one or more of the following: Sending measurement configuration messages; The request from the terminal device; The change in the mobile state of the terminal device; Implementation of the network device.

12. The method according to any one of claims 1-11, characterized in that, The method further includes: The terminal device stores the first information and forms a local configuration, which is used for data preprocessing before the first model inference and / or management of the first model.

13. The method according to any one of claims 1-12, characterized in that, The data preprocessing before the first model inference and / or the management of the first model are triggered by the terminal device or the network device.

14. A method for wireless communication, characterized in that, include: The network device sends first information to the terminal device, the first information being used for data preprocessing before the first model inference and / or the management of the first model.

15. The method according to claim 14, characterized in that, The first information is used to determine one or more of the following: The processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model.

16. The method according to claim 14 or 15, characterized in that, The first information is used to indicate one or more of the following: If the amount of input data provided to the first model does not match the amount of input data required by the first model, then the first model is activated. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model will not be used for inference. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model is used for inference. When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model; If the amount of input data provided to the first model does not match the amount of input data required by the first model, the priority of the input data used when performing inference using the first model.

17. The method according to claim 15 or 16, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: Deactivate the first model; Inference is not performed using the first model; Use the first model for reasoning; The input data used when performing inference using the first model.

18. The method according to claim 17, characterized in that, If the first information indicates the input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

19. The method according to claim 15 or 16, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: The input data used when performing inference using the first model; The priority of the input data used when performing inference using the first model.

20. The method according to any one of claims 14-19, characterized in that, The first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model exceeds the amount of input data required by the first model, the first information is used to indicate one or more of the following: Community priority; Beam priority; Beam pair priority; The cell information used when performing inference using the first model; The beam information used when performing inference using the first model; Information about the beam pairs used when performing inference using the first model.

21. The method according to claim 20, characterized in that: The priority of the cells and / or the cell information used when performing inference using the first model is indicated by one or more of the following: cell identification information prioritized for inference using the first model, cell priority indication information, a first threshold corresponding to the cell measurement results, and information on the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or The beam priority and / or the beam information used when performing inference using the first model is indicated by one or more of the following: identification information of beams preferentially used for inference of the first model, beam priority indication information, a second threshold corresponding to the beam measurement results, information of the N beams with the best measurement results in the beam measurement results, where N is the number of beams that the first model needs to input; and / or The priority of the beam pairs and / or the information of the beam pairs used when inference using the first model is indicated by one or more of the following: identification information of beam pairs that are given priority for inference of the first model, indication information of beam pair priority, a third threshold corresponding to the beam pair measurement results, and information of the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

22. The method according to claim 21, characterized in that: If the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

23. The method according to any one of claims 14-22, characterized in that, The first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

24. The method according to any one of claims 14-23, characterized in that, The first information is sent based on one or more of the following: Sending measurement configuration messages; The request from the terminal device; The change in the mobile state of the terminal device; Implementation of the network device.

25. The method according to any one of claims 14-24, characterized in that, The data preprocessing before the first model inference and / or the management of the first model are triggered by the terminal device or the network device.

26. A terminal device, characterized in that, include: The receiving module is used to receive first information sent by the network device, the first information being used for data preprocessing before the first model inference and / or the management of the first model.

27. The terminal device according to claim 26, characterized in that, The first information is used to determine one or more of the following: The processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; If the amount of input data provided to the first model does not match the amount of input data required by the first model, then the first... The input data used by a model when performing inference.

28. The terminal device according to claim 26 or 27, characterized in that, The first information is used to indicate one or more of the following: If the amount of input data provided to the first model does not match the amount of input data required by the first model, then the first model is activated. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model will not be used for inference. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model is used for inference. When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model; If the amount of input data provided to the first model does not match the amount of input data required by the first model, the priority of the input data used when performing inference using the first model.

29. The terminal device according to claim 27 or 28, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: Deactivate the first model; Inference is not performed using the first model; Use the first model for reasoning; The input data used when performing inference using the first model.

30. The terminal device according to claim 29, characterized in that, If the first information indicates the input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

31. The terminal device according to claim 27 or 28, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: The input data used when performing inference using the first model; The priority of the input data used when performing inference using the first model.

32. The terminal device according to any one of claims 26-31, characterized in that, The first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model exceeds the amount of input data required by the first model, the first information is used to indicate one or more of the following: Community priority; Beam priority; Beam pair priority; The cell information used when performing inference using the first model; The beam information used when performing inference using the first model; Information about the beam pairs used when performing inference using the first model.

33. The terminal device according to claim 32, characterized in that: The priority of the cells and / or the cell information used when performing inference using the first model is indicated by one or more of the following: cell identification information prioritized for inference using the first model, cell priority indication information, a first threshold corresponding to the cell measurement results, and information on the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or The beam priority and / or the beam information used when performing inference using the first model is indicated by one or more of the following: identification information of beams preferentially used for inference of the first model, beam priority indication information, a second threshold corresponding to the beam measurement results, information of the N beams with the best measurement results in the beam measurement results, where N is the number of beams that the first model needs to input; and / or The priority of the beam pairs and / or the information of the beam pairs used when inference using the first model is indicated by one or more of the following: identification information of beam pairs that are given priority for inference of the first model, indication information of beam pair priority, a third threshold corresponding to the beam pair measurement results, and information of the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

34. The terminal device according to claim 33, characterized in that: If the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

35. The terminal device according to any one of claims 26-34, characterized in that, The first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

36. The terminal device according to any one of claims 26-35, characterized in that, The first information is sent based on one or more of the following: Sending measurement configuration messages; The request from the terminal device; The change in the mobile state of the terminal device; Implementation of the network device.

37. The terminal device according to any one of claims 26-36, characterized in that, The terminal device also includes: A storage module is used to store the first information and form a local configuration, the local configuration being used for data preprocessing before the first model inference and / or for the management of the first model.

38. The terminal device according to any one of claims 26-37, characterized in that, The data preprocessing before the first model inference and / or the management of the first model are triggered by the terminal device or the network device.

39. A network device, characterized in that, include: The sending module is used to send first information to the terminal device, the first information being used for data preprocessing before the first model inference and / or the management of the first model.

40. The network device according to claim 39, characterized in that, The first information is used to determine one or more of the following: The processing method corresponding to the first model when the amount of input data provided to the first model does not match the amount of input data required by the first model; When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model.

41. The network device according to claim 39 or 40, characterized in that, The first information is used to indicate one or more of the following: If the amount of input data provided to the first model does not match the amount of input data required by the first model, then the first model is activated. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model will not be used for inference. If the amount of input data provided to the first model does not match the amount of input data required by the first model, the first model is used for inference. When the amount of input data provided to the first model does not match the amount of input data required by the first model, the input data used when performing inference using the first model; If the amount of input data provided to the first model does not match the amount of input data required by the first model, the priority of the input data used when performing inference using the first model.

42. The network device according to claim 40 or 41, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is less than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: Deactivate the first model; Inference is not performed using the first model; Use the first model for reasoning; The input data used when performing inference using the first model.

43. The network device according to claim 42, characterized in that, If the first information indicates the input data used when performing inference using the first model, the input data used when performing inference using the first model includes placeholders.

44. The network device according to claim 40 or 41, characterized in that, The mismatch between the amount of input data provided to the first model and the amount of input data required by the first model includes: the amount of input data provided to the first model is greater than the amount of input data required by the first model, and the first information is used to indicate one or more of the following: The input data used when performing inference using the first model; The priority of the input data used when performing inference using the first model.

45. The network device according to any one of claims 39-44, characterized in that, The first model is used to predict measurement results related to the mobility of the terminal device. When the amount of input data provided to the first model exceeds the amount of input data required by the first model, the first information is used to indicate one or more of the following: Community priority; Beam priority; Beam pair priority; The cell information used when performing inference using the first model; The beam information used when performing inference using the first model; Information about the beam pairs used when performing inference using the first model.

46. ​​The network device according to claim 45, characterized in that: The priority of the cells and / or the cell information used when performing inference using the first model is indicated by one or more of the following: cell identification information prioritized for inference using the first model, cell priority indication information, a first threshold corresponding to the cell measurement results, and information on the M cells with the best measurement results in the cell measurement results, where M is the number of cells that the first model needs to input; and / or The beam priority and / or the beam information used when performing inference using the first model is indicated by one or more of the following: identification information of beams preferentially used for inference of the first model, beam priority indication information, a second threshold corresponding to the beam measurement results, information of the N beams with the best measurement results in the beam measurement results, where N is the number of beams that the first model needs to input; and / or The priority of the beam pairs and / or the information of the beam pairs used when inference using the first model is indicated by one or more of the following: identification information of beam pairs that are given priority for inference of the first model, indication information of beam pair priority, a third threshold corresponding to the beam pair measurement results, and information of the K best beam pairs in the beam pair measurement results, where K is the number of beam pairs that the first model needs to input.

47. The network device according to claim 46, characterized in that: If the cell measurement result of the first cell is greater than or equal to the first threshold, the first cell is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam is greater than or equal to the second threshold, the first beam is preferentially used for inference of the first model; and / or If the beam measurement result of the first beam pair is greater than or equal to the third threshold, the first beam pair is preferentially used for inference of the first model.

48. The network device according to any one of claims 39-47, characterized in that, The first information is carried in the measurement configuration message, or the first information is independent of the measurement configuration message.

49. The network device according to any one of claims 39-48, characterized in that, The first information is sent based on one or more of the following: Sending measurement configuration messages; The request from the terminal device; The change in the mobile state of the terminal device; Implementation of the network device.

50. The network device according to any one of claims 39-49, characterized in that, The data preprocessing before the first model inference and / or the management of the first model are triggered by the terminal device or the network device.

51. A terminal device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or send signals so that the terminal device performs the method as described in any one of claims 1-13.

52. A network device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals so that the network device performs the method as described in any one of claims 14-25.

53. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the device to perform the method as described in any one of claims 1-13 or 14-25.

54. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-13 or 14-25.

55. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-13 or 14-25.

56. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-13 or 14-25.

57. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-13 or 14-25.

Images