Wireless communication methods and apparatuses, and device and storage medium

Abstract

Wireless communication methods and apparatuses, and a device and a storage medium, which belong to the technical field of mobile communications. A wireless communication method is executed by a terminal device and comprises: receiving a first measurement configuration sent by a network device (310); and in an idle state or an inactive state, on the basis of the first measurement configuration, performing measurement to obtain first measurement data (320), wherein the first measurement data is used for generating second measurement data.

Description

Wireless communication method, apparatus, device, and storage medium TECHNICAL FIELD

[0001] The present application relates to the technical field of mobile communication, and particularly relates to a wireless communication method, apparatus, device and storage medium. BACKGROUND

[0002] In a wireless communication system, a network device can perform CA / DC configuration on a terminal device.

[0003] In the related art, a terminal device can perform downlink measurement to obtain measurement data of a reference signal, and report the measurement data to a network device, and the network device performs CA / DC configuration on the terminal device according to the measurement data reported by the terminal device.

[0004] SUMMARY

[0005] Embodiments of the present application provide a wireless communication method, apparatus, device and storage medium. The technical solutions are as follows:

[0006] In one aspect, the present application provides a wireless communication method, which is performed by a terminal device, and the method comprises:

[0007] receiving a first measurement configuration sent by a network device;

[0008] obtaining first measurement data according to the first measurement configuration in an idle state or an inactive state; the first measurement data is used to generate second measurement data.

[0009] In one aspect, the present application provides a wireless communication method, which is performed by a network device, and the method comprises:

[0010] sending a first measurement configuration to a terminal device; the first measurement configuration is used to instruct the terminal device to obtain first measurement data in an idle state or an inactive state; the first measurement data is used to generate second measurement data.

[0011] In another aspect, the present application provides a wireless communication apparatus, which comprises:

[0012] a receiving module configured to receive a first measurement configuration sent by a network device;

[0013] a measurement module configured to obtain first measurement data according to the first measurement configuration in an idle state or an inactive state; the first measurement data is used to generate second measurement data.

[0014] In another aspect, the present application provides a wireless communication apparatus, which comprises:

[0015] The sending module is configured to send a first measurement configuration to a terminal device, wherein the first measurement configuration is used to instruct the terminal device to measure first measurement data in an idle state or an inactive state, and the first measurement data is used to generate second measurement data.

[0016] In another aspect, an embodiment of the present application provides a communication device, which comprises a processor, a memory and a transceiver.

[0017] The memory stores a computer program, and the processor executes the computer program, so that the communication device implements the wireless communication method.

[0018] In yet another aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is loaded and executed by a processor to implement the wireless communication method.

[0019] In yet another aspect, the present application further provides a chip, which comprises an integrated circuit and a firmware arranged in the integrated circuit, and the chip is used to run in a communication device, so that the communication device executes the wireless communication method.

[0020] In yet another aspect, the present application provides a computer program product, which comprises computer instructions stored in a computer readable storage medium. A processor of a communication device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the communication device executes the wireless communication method.

[0021] In yet another aspect, the present application provides a computer program, which is executed by a processor of a communication device to implement the wireless communication method.

[0022] Through the scheme provided by the embodiments of the present application, the terminal device can measure a small amount of downlink measurement data (i.e., the first measurement data) in an idle state or an inactive state based on the configuration of the network device, and the remaining part of the downlink measurement data (i.e., the second measurement data) can be generated based on the small amount of downlink measurement data. The terminal device does not need to measure complete downlink measurement data. On the one hand, the terminal device does not need to perform a complete downlink measurement process, thereby saving device energy consumption and memory resources of the terminal device. On the other hand, if the generation process of the second measurement data is performed by the network device, the terminal device only needs to upload a small amount of downlink measurement data to the network device, thereby saving signaling resources between the terminal device and the network device. BRIEF DESCRIPTION OF DRAWINGS

[0023] FIG. 1A is a schematic diagram of an architecture of a communication system provided by an embodiment of the present application;

[0024] FIG. 1B is a schematic diagram of an architecture of another communication system according to an embodiment of the present application;

[0025] FIG. 1C is a schematic diagram of an architecture of another communication system according to an embodiment of the present application;

[0026] FIG. 2 is a schematic diagram of LCM functions;

[0027] FIG. 3 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0028] FIG. 4 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0029] FIG. 5 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0030] FIG. 6 is a schematic diagram of a framework of UE-side AI / ML model inference according to an embodiment of the present application;

[0031] FIG. 7 is a schematic diagram of a framework of network-side AI / ML model inference according to an embodiment of the present application;

[0032] FIG. 8 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0033] FIG. 9 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0034] FIG. 10 is a flowchart of a wireless communication method according to an embodiment of the present application;

[0035] FIG. 11 is a block diagram of a wireless communication apparatus according to an embodiment of the present application;

[0036] FIG. 12 is a block diagram of a wireless communication apparatus according to an embodiment of the present application;

[0037] FIG. 13 is a schematic diagram of a structure of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] For the purpose of making the technical scheme, technical solutions and advantages of the present application clearer, the embodiments of the present application are described in further detail below with reference to the drawings.

[0039] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0040] 1) Communication system scenario

[0041] The communication system scenario can include a terrestrial network (TN) system and a non-terrestrial network (NTN) system. The NTN generally provides communication services to ground users in a satellite communication manner. The NTN system currently includes a new radio (NR)-NTN and an Internet of Things (IoT)-NTN system, and can further include other NTN systems in the future.

[0042] For example, FIG. 1A is a schematic diagram of an architecture of a communication system provided by an embodiment of the present application. As shown in FIG. 1A, the communication system 100 can include a network device 110, which can be a device communicating with a terminal device 120 (or a communication terminal device or a terminal device). The network device 110 can provide communication coverage for a specific geographic area and can communicate with terminal devices located in the coverage area.

[0043] For example, FIG. 1A shows one network device and two terminal devices. In some embodiments of the present application, the communication system 100 can include multiple network devices and each network device can include a different number of terminal devices within its coverage range, which is not limited in the embodiments of the present application.

[0044] For example, FIG. 1B is a schematic diagram of another architecture of a communication system provided by an embodiment of the present application. As shown in FIG. 1B, the communication system includes a terminal device 120 and a satellite 130, and the terminal device 120 and the satellite 130 can communicate wirelessly. The network formed between the terminal device 120 and the satellite 130 can also be referred to as an NTN. In the architecture of the communication system shown in FIG. 1B, the satellite 130 can have the function of a base station, and the terminal device 120 and the satellite 130 can directly communicate. In the system architecture, the satellite 130 can be referred to as a network device. In some embodiments of the present application, the communication system can include multiple network devices, and each network device can include a different number of terminal devices within its coverage range, which is not limited in the embodiments of the present application.

[0045] For example, FIG. 1C is a schematic diagram of another architecture of a communication system provided by an embodiment of the present application. Referring to FIG. 1C, the communication system includes a terminal device 120, a satellite 130, and a base station 140. The terminal device 120 and the satellite 130 can communicate with each other wirelessly, and the satellite 130 can communicate with the base station 140. The network formed by the terminal device 120, the satellite 130, and the base station 140 can also be referred to as an NTN. In the architecture of the communication system shown in FIG. 1C, the satellite 130 can not have the function of a base station, and the communication between the terminal device 120 and the base station 140 needs to be relayed by the satellite 130. In this kind of system architecture, the base station 140 can be referred to as a network device. In some embodiments of the present application, multiple network devices can be included in the communication system, and each network device can include a certain number of terminal devices within its coverage, which is not limited in the embodiments of the present application.

[0046] In future evolved communication systems such as Beyond Fifth Generation (B5G), 6th Generation (6G) mobile communication systems, etc., distributed Multiple-In Multiple-Out (Massive MIMO, also referred to as distributed antenna system) scenarios and / or Massive MIMO (also referred to as massive antenna matrix system) scenarios can also be included. In some cases, Distributed MIMO and / or Massive MIMO or can also support a cell-free or UE-centric network deployment scenario. It should be understood that the above scenarios also apply to TN and / or NTN.

[0047] 2) Early measurement mechanism for IDLE / INACTIVE UEs

[0048] When the UE is in Radio Resource Control IDLE (RRC_IDLE) or RRC_INACTIVE, only cell reselection measurements are needed, and the UE can continue camping on a single cell of the most suitable frequency and Radio Access Technology (RAT). However, during connection setup or resume for the cell where the UE is camping, neither the UE nor the network is aware of the radio conditions for potential cells / carriers for e.g. Carrier Aggregation (CA) and / or other potential cells / carriers. Therefore, after the UE transitions to RRC CONNECTED, before the UE is configured for CA or Dual Connectivity (DC), the network needs to re-configure the UE with new measurement configuration on the potential carriers for CA and / or DC and obtain these measurement results, which introduces additional delay.

[0049] The early measurement mechanism, on the other hand, allows the UE to perform measurements (also referred to as early measurements) on the carriers where CA / DC can be configured while in IDLE / INACTIVE state. When the UE establishes or resumes connection with the so-called primary cell (PCell) again, i.e. when entering the connected state, the UE reports the measurement results. The network can then use these measurements to quickly configure the UE for CA / DC operation.

[0050] During connection setup / resume, the UE can indicate whether it has available early measurement results, and the network can then request the UE to report the results. The early measurement configuration received by the UE when entering IDLE / INACTIVE state includes a list of carriers to be measured and a measurement duration timer (up to five minutes long). The measurement duration timer limits the time the UE needs to perform measurements in IDLE / INACTIVE state to avoid unnecessarily increasing the UE power consumption in case the interval between connections is long.

[0051] 3) Artificial Intelligence (AI)

[0052] The Artificial Intelligence can be implemented by a method of machine learning. The basic method of machine learning can include, for example, supervised learning, unsupervised learning, or reinforcement learning.

[0053] Supervised learning is also known as supervised learning or supervised learning. A pattern (also known as a function or learning model) can be learned or created from training data, and new instances can be inferred according to the pattern. Training data is composed of input objects (usually vectors) and expected outputs. The output can be a continuous value (called regression analysis), or a predicted classification label (called classification). The task of a supervised learner is to predict the output of this function for any possible input after observing some pre-labeled training examples (input and expected output). To achieve this, the learner must generalize from the existing data to non-observed cases in a "reasonable" (inductive bias) way.

[0054] Reinforcement learning emphasizes how to act based on the environment to maximize the expected benefit. Unlike supervised learning, reinforcement learning does not require labeled input-output pairs, nor does it require precise correction of non-optimal solutions. It focuses on finding a balance between exploration (of unknown areas) and utilization (of existing knowledge). The exploration-exploitation trade-off in reinforcement learning is most studied in the multi-armed bandit problem and finite Markov decision processes (MDP). For MDP, in machine learning problems, the environment is usually abstracted as an MDP, and many reinforcement learning algorithms use dynamic programming methods under this assumption. The main difference between traditional dynamic programming methods and reinforcement learning algorithms is that the latter does not require knowledge of the MDP, and is aimed at large-scale MDPs for which exact methods cannot be found.

[0055] 4) AI applications in 3GPP systems

[0056] AI for network (NW) is the application of artificial intelligence technology in the network field to improve the performance, efficiency, scalability and intelligent level of the network. 3GPP has started to study the AI / machine learning (ML) function framework since 5G Rel-17, and has determined the high-level use cases based on AI / ML for the next generation radio access network (NG-RAN). Rel-18 studies AI / ML physical layer use cases (AI / ML-based positioning, AI / ML-based beam management, and AI / ML-based channel state information), as well as the standardization of AI / ML high-level use cases (network energy saving, load balancing, mobility optimization), and gives a general AI / ML framework and AI / ML model lifecycle management (LCM) in TR38.843. The LCM function diagram can be as shown in Figure 2.

[0057] As shown in FIG. 2, the data collection function unit 210 provides input data for the model training unit 220, the management unit 230, and the inference function unit 240.

[0058] The training data is the data required for the input of the AI / ML model training function.

[0059] The monitoring data is the input data required for managing the AI / ML model or the AI / ML function.

[0060] The inference data is the data required for the input of the AI / ML inference function.

[0061] The model training unit 220 is a functional unit for performing AI / ML model training, validation, and testing, and can generate model performance indicators that can be used as part of the model testing process. If necessary, the model training unit 220 can also perform data preparation (e.g., data pre-processing and cleaning, formatting, and conversion) based on the training data provided by the data collection function.

[0062] The trained / updated model in FIG. 2 refers to the transmission of the AI / ML model that has been trained, validated, and tested to the model storage function unit 250, or the transmission of an updated version of the model to the model storage function unit 250, if there is a model storage function unit 250.

[0063] The management unit 230 is a functional unit for supervising the operation (e.g., selection / (de)activation / switching / fallback) and monitoring (e.g., performance) of the AI / ML model or the AI / ML function. The management unit 230 is also responsible for making decisions based on the data received from the data collection function and the inference function to ensure correct inference operation.

[0064] The management instruction issued by the management unit 230 to the inference function unit 240 refers to the input information required for managing the inference function. The relevant information can include the selection / (de)activation / switching of the AI / ML model or the AI / ML-based function, fallback to non-AI / ML operation (i.e., not dependent on the inference process), etc.

[0065] The model transmission / delivery request issued by the management unit 230 to the model storage function unit 250 is used to request a model from the model storage function unit.

[0066] The performance feedback / re-training request issued by the management unit 230 to the model training unit 220 includes information required for the input of the model training function, e.g., information for triggering model (re)training or update.

[0067] The inference function unit 240 is a function unit that uses data provided by the data collection function (i.e., inference data) as input and provides output of a process that applies an AI / ML model or AI / ML function. If necessary, the inference function unit 240 is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and conversion) based on the inference data provided by the data collection function.

[0068] The inference output of the inference function unit 240 can include data that the management unit 230 uses to monitor the performance of the AI / ML model or AI / ML function.

[0069] The model storage function unit 250 is a function unit responsible for storing trained / updated models that can be used to perform inference functions.

[0070] The operation of the model storage function unit 250 initiating model transmission / delivery to the inference function unit 240 can be used to deliver the AI / ML model to the inference function unit 240.

[0071] In the early measurement mechanism in the IDLE / INACTIVE UE state related to the related art, there can be a large number of measurement results occupying the cache space of the UE, and a large amount of signaling overhead when reporting the measurement. In addition, there can be a situation where the UE cannot obtain the measurement result at some measurement time, or the measurement continues in IDLE / INACTIVE, thereby increasing the burden on the UE and increasing power consumption.

[0072] The scheme shown in the subsequent embodiments of the present application can reduce resource consumption of measurement and reporting in the early measurement scenario in the IDLE / INACTIVE UE state through AI. For example, the UE can predict the measurement result through AI to reduce measurement energy consumption and complete the measurement result that cannot be obtained. The network device can also obtain all measurement results by deriving them from a small number of UE measurement results through AI.

[0073] Please refer to FIG. 3, which shows a flowchart of a wireless communication method provided by an embodiment of the present application, which can be executed by a terminal device. The terminal device can be the terminal device 120 in the network architecture described above, or a terminal device in other network architectures, which are not limited in the present application. The method can include at least part of the following steps:

[0074] Step 310: receiving a first measurement configuration sent by a network device.

[0075] The first measurement configuration described above is information for instructing the terminal device to perform early measurement in an idle state or an inactive state.

[0076] In some embodiments, the terminal device can receive the first measurement configuration information sent by the network device in the connected state, for example, the terminal device can receive the first measurement configuration sent by the network device through RRC signaling, medium access control-control element (MAC CE), downlink control information (DCI), etc. in the connected state.

[0077] In some embodiments, the terminal device can also receive the first measurement configuration sent by the network device through the RRC Release message when accessing the network last time.

[0078] In some embodiments, the terminal device can receive the first measurement configuration information sent by the network device before accessing the network device, or during the process of accessing the network device, for example, the terminal device can receive the first measurement configuration sent by the network device through system message broadcast before accessing the network device, and for another example, the terminal device can receive the first measurement configuration sent by the network device through the downlink random access message during the process of accessing the network device.

[0079] Step 320: measuring the first measurement data according to the first measurement configuration in the idle state or the inactive state; the first measurement data is used to generate the second measurement data.

[0080] The above-mentioned first measurement data and second measurement data can constitute complete measurement data required by the network device when configuring the network for the terminal device (such as configuring CA / DC for the terminal device).

[0081] For example, the complete data required by the network device when configuring CA / DC for the terminal device includes the downlink measurement data of the terminal device on at least 10 time-frequency resources, the above-mentioned first measurement data can be the downlink measurement data corresponding to less than 10 time-frequency resources, and the above-mentioned second measurement data can be the downlink measurement data corresponding to other time-frequency resources in at least 10 time-frequency resources.

[0082] In some embodiments, the terminal device can measure the link quality according to the first measurement configuration, for example, the above-mentioned first measurement configuration data can include the downlink measurement data of the layer 1 and / or layer 3 reference signal; in the embodiments of the present application, the above-mentioned first measurement data can be used to predict the second measurement data, for example, the first measurement data can be input into the AI / ML model, and the second measurement data is predicted by the AI / ML model.

[0083] Correspondingly, the above-mentioned second measurement data can also be the downlink measurement data corresponding to the layer 1 and / or layer 3 reference signal.

[0084] The downlink measurement data can include at least one of the following data of a reference signal: Reference Signal Receiving Power (RSRP), Reference Signal Receiving Quality (RSRQ), and Signal to Interference plus Noise Ratio (SINR).

[0085] The first measurement data can be downlink measurement data on part of time-frequency resources in a measurement time period. The second measurement data can be downlink measurement data in the measurement time period, which is different from the first measurement data in terms of time-frequency resource location and / or data type.

[0086] In the scheme shown in the embodiments of the present application, the terminal device can obtain a small amount of downlink measurement data (i.e., the first measurement data) in the idle state or the inactive state based on the configuration of the network device, and the remaining downlink measurement data (i.e., the second measurement data) can be generated based on the small amount of downlink measurement data. The terminal device does not need to measure complete downlink measurement data. On the one hand, the terminal device does not need to perform a complete downlink measurement process, thereby saving device energy consumption and memory resources of the terminal device. On the other hand, if the generation process of the second measurement data is performed by the network device, the terminal device only needs to upload a small amount of downlink measurement data to the network device, thereby saving signaling resources between the terminal device and the network device.

[0087] In addition, in the case that the terminal device cannot measure some measurement data, the scheme shown in the embodiments of the present application can supplement the measurement data, thereby ensuring the availability and accuracy of the CA / DC configuration of the terminal device by the network device.

[0088] Please refer to FIG. 4, which shows a flowchart of a wireless communication method provided by an embodiment of the present application. The method can be performed by a network device. The network device can be the network device 110, the satellite 130, or the base station 140 in the network architecture, or a network device in another network architecture, which is not limited in the present application. The method can include at least part of the following steps:

[0089] Step 410: sending a first measurement configuration to a terminal device; the first measurement configuration is used to instruct the terminal device to measure first measurement data in an idle state or an inactive state; and the first measurement data is used to generate second measurement data.

[0090] In conclusion, in the scheme shown in the embodiments of the present application, the network device can configure the terminal device to actually measure a small amount of downlink measurement data (i.e., the first measurement data) in the idle state or the inactive state, and the remaining part of the downlink measurement data (i.e., the second measurement data) can be generated based on the small amount of downlink measurement data, without the terminal device measuring complete downlink measurement data. On the one hand, the terminal device does not need to perform a complete downlink measurement process, thereby saving device energy consumption and memory resources of the terminal device. On the other hand, if the generation process of the second measurement data is performed by the network device, the terminal device only needs to upload a small amount of downlink measurement data to the network device, thereby saving signaling resources between the terminal device and the network device.

[0091] Based on the schemes shown in FIG. 3 and FIG. 4, please refer to FIG. 5, which shows a flowchart of a wireless communication method provided by an embodiment of the present application, which can be executed by the terminal device and the network device interactively, wherein the terminal device can be the terminal device 120 in the foregoing network architecture, or a terminal device in other network architectures, and the network device can be the network device 110, the satellite 130 or the base station 140 in the foregoing network architecture, or a network device in other network architectures, which are not limited by the present application. The method can include at least part of the following steps:

[0092] Step 510: The network device sends a first measurement configuration to the terminal device, and the terminal device receives the first measurement configuration sent by the network device.

[0093] The first measurement configuration can indicate on which time domain and / or frequency domain resources the terminal device performs downlink measurement.

[0094] For example, in some embodiments, the first measurement configuration includes one or more of the following configurations: frequency domain information of measurement, and time interval of measurement.

[0095] In the foregoing embodiments, the frequency domain information of measurement is used to indicate which frequency domain the terminal device performs downlink measurement on, for example, the frequency domain information of measurement can indicate the frequency point / frequency band / subcarrier, etc. corresponding to the reference information to be measured.

[0096] The time interval of measurement can refer to the time interval between adjacent two times of downlink measurement performed by the terminal device, for example, assuming that the time interval of measurement is 0.5s, the terminal device can perform downlink measurement every 0.5s subsequently.

[0097] In some embodiments, the measured frequency domain information can be information directly indicating the frequency domain resources for which the terminal device performs downlink measurement, that is, the measured frequency domain information refers to the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device.

[0098] For example, the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device include a plurality of frequency bands, and the measured frequency domain information can indicate part of the plurality of frequency bands. The terminal device can perform downlink measurement on all or part of the frequency bands indicated by the measured frequency domain information.

[0099] For example, the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device include at least 10 frequency bands, and the measured frequency domain information can indicate 5 frequency bands. The terminal device can perform downlink measurement on all or part of the 5 frequency bands indicated by the measured frequency domain information.

[0100] In other embodiments, the measured frequency domain information can indicate the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device. For example, the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device include a plurality of frequency bands, and the measured frequency domain information can indicate the plurality of frequency bands. The terminal device can perform downlink measurement on all or part of the frequency bands indicated by the measured frequency domain information.

[0101] For example, the frequency domain resources for which the network device needs complete downlink measurement data of the terminal device to manage the terminal device include at least 10 frequency bands, and the measured frequency domain information can indicate at least 10 frequency bands. The terminal device can perform downlink measurement on all or part of the at least 10 frequency bands indicated by the measured frequency domain information.

[0102] Through the above-mentioned embodiments of the present application, the network device can configure the terminal device to perform downlink measurement on which frequency domain resources and perform downlink measurement once every how long time, thereby ensuring the controllability of the terminal device performing downlink measurement.

[0103] In some embodiments, the duration of each measurement of the terminal device can be defined by a protocol; or, the duration of each measurement of the terminal device can be configured by the network device (for example, the duration of each measurement can also be included in the first measurement configuration described above); or, the duration of each measurement of the terminal device can also be determined by the terminal device itself, for example, the terminal device can determine the duration of each measurement according to its own energy saving needs, or according to the data volume needs of the first measurement data.

[0104] For example, assuming that the time interval of the measurement is 50 ms, the duration of each measurement of the terminal device can be 10 ms.

[0105] In some embodiments, during each measurement of the terminal device, the terminal device can perform downlink measurement on all or part of the time domain resources within the duration of the measurement.

[0106] For example, assuming that the complete downlink measurement data required by the network device to manage the terminal device corresponds to a time duration of 10 ms in the time domain, and the duration of each measurement of the terminal device is 10 ms, the terminal device can perform downlink measurement on all time domain resources within the 10 ms corresponding to one test process (that is, continuously perform downlink measurement within 10 ms), or the terminal device can also perform downlink measurement on part of the time domain resources (for example, continuously perform downlink measurement within 5 ms).

[0107] In some embodiments, the first measurement configuration further includes first data volume configuration information for indicating the data volume of the first measurement data and the data volume of the second measurement data.

[0108] For example, the terminal device can determine how much downlink measurement data to measure, or determine which downlink measurement data on the time-frequency resources to measure, as the first measurement data according to the first data volume configuration information.

[0109] For example, assuming that the complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, the network device can indicate, through the first data amount configuration information, that the first measurement data requires downlink measurement data on 5 time-frequency resources, and the remaining measurement data (second measurement data) can be generated through the first measurement data. Correspondingly, in a measurement process, the terminal device can perform downlink measurement and stop measurement when the downlink measurement data on 5 time-frequency resources is obtained, and the downlink measurement data on the 5 time-frequency resources is taken as the first measurement data. Alternatively, the terminal device can determine, according to the first data amount configuration information, or according to a pre-set resource determination rule, 5 time-frequency resources from the at least 10 time-frequency resources to perform downlink measurement, to obtain the first measurement data.

[0110] In the embodiments of the present application, the network device can also provide the terminal device with the related information of the data amount of the first measurement data and the second measurement data, respectively, and the terminal device can determine, according to the first data amount configuration information in the first measurement configuration, which or how many time-frequency resources on the reference signal to perform downlink measurement to obtain the first measurement data, thereby ensuring the flexibility of the terminal device in performing downlink measurement.

[0111] In some embodiments, the first data amount configuration information includes one or more of the following information:

[0112] 1) First proportion information, used to indicate the proportional relationship between the data amount of the first measurement data and the data amount of the second measurement data.

[0113] The data amount of the first measurement data and the data amount of the second measurement data can be indicated by the proportional relationship between the data amount of the first measurement data and the data amount of the second measurement data. For example, assuming that the complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, and the first proportion information is 5:5, the terminal device can determine, according to the first proportion information, that the first measurement data needs to include or at least include downlink measurement data on 5 time-frequency resources.

[0114] 2) First resource saving information, used to indicate the resources saved by the terminal device in the case of generating the second measurement data through the first measurement data.

[0115] The data amount of the first measurement data and the data amount of the second measurement data can also be indirectly indicated by configuring the resources to be saved by the terminal device. The more resources the terminal device needs to save, the lower the data amount of the first measurement data, and vice versa.

[0116] The resource saved by the terminal device can be represented by a resource saving level. For example, assuming that the resource saving level has three levels, high, medium and low, the resource saving level high means that the terminal device needs to save the most resources (e.g., needs to reduce the downlink measurement as much as possible to save resources), the resource saving level medium means that the terminal device needs to save the medium resources, and the resource saving level low means that the terminal device needs to save the least resources (e.g., needs to appropriately increase the downlink measurement to ensure the accuracy of the measurement data). Assuming that the complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, when the first resource saving information indicates that the resource saving level is high, the terminal device can determine to perform downlink measurement on a small number of time-frequency resources (e.g., 3 time-frequency resources) to obtain the first measurement data, when the first resource saving information indicates that the resource saving level is medium, the terminal device can determine to perform downlink measurement on half of the time-frequency resources (e.g., 5 time-frequency resources) to obtain the first measurement data, and when the first resource saving information indicates that the resource saving level is low, the terminal device can determine to perform downlink measurement on most of the time-frequency resources (e.g., 7 time-frequency resources) to obtain the first measurement data.

[0117] In the embodiments of the present application, the terminal device can indirectly indicate the time-frequency resources on which the terminal device determines to perform downlink measurement by a proportional relationship or the resources required to be saved by the terminal device, so that the terminal device can more flexibly perform the downlink measurement process according to the actual needs.

[0118] In some embodiments, the resources saved by the terminal device include one or more of the following information:

[0119] The energy consumption saved by the terminal device, the memory resources saved by the terminal device, and the signaling overhead saved by the terminal device.

[0120] The energy consumption saved by the terminal device can be the difference between the energy consumption consumed by the terminal device for measuring the complete downlink measurement data (equivalent to the first measurement data + the second measurement data) and the energy consumption consumed by the terminal device for measuring the first measurement data.

[0121] The memory resources saved by the terminal device is the difference between the memory resources occupied by the terminal device for measuring the complete downlink measurement data and the memory resources occupied by the terminal device for measuring the first measurement data.

[0122] The signaling overhead saved by the terminal device is the difference between the signaling overhead required by the terminal device for measuring and reporting the complete downlink measurement data and the signaling overhead required by the terminal device for measuring and reporting the first measurement data.

[0123] In the embodiments of the present application, the terminal device can be instructed to determine the time-frequency resources on which the downlink measurement is performed according to the resource saving requirements in terms of energy consumption, memory resources, signaling overhead, and the like, so as to more accurately and more specifically optimize the downlink measurement process of the terminal device.

[0124] Step 520: The terminal device measures to obtain first measurement data according to the first measurement configuration in the idle state or the inactive state; the first measurement data is used to generate second measurement data.

[0125] In the embodiments of the present application, after the terminal device receives the first measurement configuration, the terminal device can perform a downlink measurement process according to the first measurement configuration when subsequently entering an idle state or an inactive state, to obtain part of the complete downlink measurement data (i.e., the first measurement data) required by the network device for managing the terminal device.

[0126] In some embodiments, the time-frequency resources corresponding to the first measurement data and the time-frequency resources corresponding to the second measurement data can be different time-frequency resources.

[0127] The different time-frequency resources can refer to time-domain same and frequency-domain different time-frequency resources, or the different time-frequency resources can refer to time-domain different and frequency-domain same time-frequency resources, or the different time-frequency resources can refer to time-domain different and frequency-domain different time-frequency resources.

[0128] In some embodiments, the first measurement data and the second measurement data can be measurement data of the same type, such as both containing RSRP or RSRQ, or the first measurement data and the second measurement data can be measurement data of different types, such as the first measurement data containing RSRP and the second measurement data containing RSRQ.

[0129] In some embodiments, the first measurement data and the second measurement data can be measurement data corresponding to the same reference signal, such as both being measurement data corresponding to layer 1 or layer 3 reference signals, or the first measurement data and the second measurement data can be measurement data corresponding to different reference signals, such as the first measurement data being measurement data corresponding to layer 1 reference signals and the second measurement data being measurement data corresponding to layer 3 reference signals.

[0130] In some embodiments, the terminal device generates the second measurement data according to the first measurement data.

[0131] In the above embodiments, the second measurement data can be generated at the terminal device side, such as the terminal device being provided with an AI / ML model, the terminal device inputting the first measurement data into the AI / ML model, and obtaining the second measurement data output by the AI / ML model.

[0132] Optionally, after the terminal device generates the second measurement data, when it needs to access the network again (needs to enter the connected state), it can report the first measurement data and the second measurement data to the network device.

[0133] In the embodiments of the present application, the generation process of the second measurement data can be performed by the terminal device, thereby ensuring the timeliness of the measurement data generation, reducing the computing pressure of the network device, and ensuring the execution performance of the network side.

[0134] In some embodiments, the terminal device generates the second measurement data according to the first measurement data, including: the terminal device generates the second measurement data according to the first measurement data and auxiliary information; wherein the auxiliary information is information used to assist in generating the second measurement data.

[0135] For example, the terminal device can input the first measurement data and the auxiliary information into the AI / ML model together, and obtain the second measurement data output by the AI / ML model.

[0136] For another example, the terminal device can filter the first measurement data through the auxiliary information, and input the filtered first measurement data into the AI / ML model, and obtain the second measurement data output by the AI / ML model. For example, the terminal device can determine which measurement data in the current first measurement data is suitable for generating the second measurement data in combination with the auxiliary information, and input the part of the first measurement data suitable for generating the second measurement data into the AI / ML model, and obtain the second measurement data output by the AI / ML model.

[0137] For example, the terminal device can be pre-configured with a correspondence between the auxiliary information and the time-frequency resource / data type / reference signal type suitable for generating the second measurement data, and the terminal device can determine the time-frequency resource / data type / reference signal type suitable for generating the second measurement data according to the current auxiliary information, and filter the measurement data corresponding to the time-frequency resource / data type / reference signal type suitable for generating the second measurement data from the first measurement data as the input of the AI / ML model.

[0138] The auxiliary information described above can be a specified type of information in a certain time domain in the terminal device, and the time domain corresponding to the auxiliary information is associated with the time domain corresponding to the first measurement data. Optionally, the time domain association can mean that the time domains are the same, there is an overlap between the time domains, or there is a specified offset between the time domains, etc.

[0139] In the embodiments of the present application, the terminal device can also refer to the auxiliary information other than the first measurement data when generating the second measurement data, thereby expanding the basis for generating the second measurement data and improving the accuracy of the second measurement data.

[0140] In some embodiments, the above method further includes: the terminal device reporting the first measurement data to the network device. Correspondingly, the network device receives the first measurement data reported by the terminal device and generates the second measurement data according to the first measurement data.

[0141] In the embodiments of the present application, when the terminal device needs to access the network again (needs to enter the connected state), the terminal device can report the first measurement data to the network device, and the network device generates the second measurement data.

[0142] For example, the network device is provided with an AI / ML model, and the network device inputs the first measurement data into the AI / ML model to obtain the second measurement data output by the AI / ML model.

[0143] In the embodiments of the present application, the generation process of the second measurement data can be performed by the network device, thereby reducing the computing pressure of the terminal device and further improving the resource saving effect of the terminal device.

[0144] In some embodiments, the method further includes: the terminal device reporting the auxiliary information to the network device. Correspondingly, the network device receives the auxiliary information reported by the terminal device; and the network device can generate the second measurement data according to the first measurement data and the auxiliary information.

[0145] In the embodiments of the present application, the terminal device reports not only the first measurement data but also the auxiliary information corresponding to the first measurement data (such as the auxiliary information associated with the first measurement data in the time domain).

[0146] The first measurement data and the auxiliary information can be reported by the terminal device to the network device through the same uplink channel / signal, or the first measurement data and the auxiliary information can be reported by the terminal device to the network device through different uplink channels / signals.

[0147] For example, the network device can input the first measurement data and the auxiliary information into the AI / ML model together to obtain the second measurement data output by the AI / ML model.

[0148] For another example, the network device can filter the first measurement data by the assistance information, and input the filtered first measurement data into the AI / ML model to obtain the second measurement data output by the AI / ML model. For example, the network device can determine, in combination with the assistance information, which measurement data in the current first measurement data is suitable for generating the second measurement data, and input the part of the first measurement data suitable for generating the second measurement data into the AI / ML model to obtain the second measurement data output by the AI / ML model.

[0149] For example, the network device can be pre-configured with a correspondence between the assistance information and the time-frequency resource / data type / reference signal type suitable for generating the second measurement data, and the network device can determine the time-frequency resource / data type / reference signal type suitable for generating the second measurement data according to the assistance information, and filter the measurement data corresponding to the time-frequency resource / data type / reference signal type suitable for generating the second measurement data from the first measurement data as the input of the AI / ML model.

[0150] In the embodiments of the present application, the network device can also refer to the assistance information other than the first measurement data when generating the second measurement data, thereby expanding the basis for generating the second measurement data and improving the accuracy of the second measurement data.

[0151] In some embodiments, the assistance information includes one or more of the following information:

[0152] The movement state information is used to indicate the movement state of the terminal device.

[0153] The scene information is used to indicate the communication scene of the terminal device.

[0154] The movement state of the terminal device can refer to the movement state of the terminal device at the same time or before / after the terminal device performs downlink measurement to obtain the first measurement data.

[0155] The communication scene of the terminal device can refer to the communication scene in which the terminal device is located when the terminal device performs downlink measurement to obtain the first measurement data, such as a Line of Sight (LOS) scene or a Non Line of Sight (NLOS) scene, and the like.

[0156] In different mobile states, different time-frequency resources, different reference signals, and / or different data types corresponding to the relationship between the measurement data may also exist differences, and accordingly, in different communication scenarios, different time-frequency resources, different reference signals, and / or different data types corresponding to the relationship between the measurement data may also exist differences, for which, in the embodiments of the present application, the terminal device / network device can combine the first measurement data, the mobile state information and / or the scene information, and comprehensively generate the second measurement data, thereby being able to improve the accuracy of the second measurement data.

[0157] In some embodiments, the mobile state information includes one or more of the following information:

[0158] Speed information; position information; and, path information.

[0159] The above-mentioned speed information can refer to the moving speed of the terminal device at the same time or before / after the terminal device performs downlink measurement to obtain the first measurement data, or the change of the moving speed (such as acceleration / speed change value).

[0160] The above-mentioned position information can refer to the position (such as geographic coordinates, orientation relative to a certain cell / base station, etc.) of the terminal device at the same time or before / after the terminal device performs downlink measurement to obtain the first measurement data, or the change of the position (such as the moving direction relative to a certain cell / base station (such as close / far, etc.)).

[0161] The above-mentioned path information can refer to the moving route of the terminal device at the same time or before / after the terminal device performs downlink measurement to obtain the first measurement data, such as the geographic positions passed through by the terminal device, and / or the cells passed through / resided by the terminal device, etc.

[0162] In the embodiments of the present application, the speed, position and / or path related information of the terminal device is used to assist in indicating the relationship between different time-frequency resources, different reference signals, and / or different data types corresponding to the measurement data, thereby being able to ensure the accuracy of generating the second measurement data.

[0163] In some embodiments, the mobile state information is determined by one or more of the following information:

[0164] Reference signal received power RSRP measured by the terminal device;

[0165] Information of an application program in the terminal device;

[0166] Sensor information of the terminal device;

[0167] Positioning information of the terminal device.

[0168] The change of the RSRP measured by the terminal device can indicate the state of the movement of the terminal device, for example, the change of the RSRP can indicate that the terminal device is currently moving away from or approaching a certain cell or geographic area, and the speed at which the terminal device is currently moving away from or approaching a certain cell or geographic area, and then the speed information, the location information and / or the path information of the terminal device can be determined.

[0169] The sensor information of the terminal device can indicate the state of the movement of the terminal device, for example, the data collected by the movement sensor / gyroscope of the terminal device can be used to calculate the current movement speed and direction of the terminal device, and thus the speed information of the terminal device can be determined through the sensor information of the terminal device.

[0170] The positioning information of the terminal device can indicate the state of the movement of the terminal device, for example, through the positioning information of the terminal device, the position of the terminal device at each time point within a period of time can be determined, and then at least one of the speed information, the location information and the path information of the terminal device can be determined.

[0171] The application in the terminal device can also obtain information related to the movement state of the terminal device, for example, the application can obtain the sensor information and / or the positioning information of the terminal device, and then calculate and output at least one of the speed information, the location information and the path information of the terminal device.

[0172] In the embodiments of the present application, the terminal device can determine the information related to the movement state of the terminal device through the RSRP, the application, the sensor or the positioning information, and then ensure the accuracy of the subsequent generation of the second measurement data.

[0173] In some embodiments, the density of the distribution of the second measurement data in the time domain is associated with the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device.

[0174] In the embodiments of the present application, the importance of the measurement data in different time domains for the configuration of the network device to the terminal device can also be different, specifically, the importance of the measurement data is related to the time interval between the time corresponding to the measurement data and the time when the terminal device accesses the network device, and for this, when the second measurement data is generated, the density of the second measurement data corresponding to the time (that is, the data amount of the second measurement data in the measurement data of the time) can be determined according to the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device, and the density of the second measurement data corresponding to different times is also different, so that as much second measurement data as possible can be generated at important times, and the accuracy of the subsequent configuration of the network device to the terminal device is ensured.

[0175] For example, there are three time points in time domain in sequence, and the time points are time point 1, time point 2 and time point 3 in sequence from early to late. The terminal device is in an idle state / inactive state at time point 1 and time point 2, and there is measurement data corresponding to time point 1 and time point 2 (each time point has first measurement data and second measurement data). The terminal device accesses the network device at time point 3. Correspondingly, the network device needs to perform the CA / DC configuration operation on the terminal device according to the measurement data corresponding to time point 1 and time point 2 at time point 3. The measurement data corresponding to time point 1 and time point 2 is also different in importance for the terminal device to perform the CA / DC configuration operation. Therefore, the terminal device / network device can generate different amounts of second measurement data corresponding to time point 1 and time point 2 when generating the second measurement data.

[0176] For example, it is assumed that the complete downlink measurement data required by the network device to manage the terminal device includes downlink measurement data on at least 10 time-frequency resources. The terminal device measures downlink measurement data on 5 time-frequency resources at time point 1 and time point 2 (first measurement data). When the terminal device / network device generates the second measurement data, for the time point with lower importance (for example, time point 1) among time point 1 and time point 2, the 5 time-frequency resources measured at the time point are input into the AI / ML model to obtain downlink measurement data on another 5 time-frequency resources output by the AI / ML model (second measurement data). For the time point with higher importance (for example, time point 2) among time point 1 and time point 2, the 5 time-frequency resources measured at the time point are input into the AI / ML model to obtain downlink measurement data on another 10 time-frequency resources output by the AI / ML model (second measurement data). Subsequently, the network device can perform the CA / DC configuration operation on the terminal device according to the downlink measurement data on 10 time-frequency resources corresponding to time point 1 and the downlink measurement data on 15 time-frequency resources corresponding to time point 2.

[0177] In some embodiments, the density of the distribution of the second measurement data in the time domain is inversely related to the interval between the time point corresponding to the second measurement data and the time point at which the terminal device accesses the network device.

[0178] In the embodiments of the present application, the closer the measurement data to the time point at which the terminal device accesses the network device, the higher the importance of the measurement data for the configuration of the terminal device by the network device. Therefore, the closer the measurement data to the time point at which the terminal device accesses the network device, the higher the amount of second measurement data in the measurement data, so that as much second measurement data as possible can be generated at important time points to ensure the accuracy of the subsequent configuration of the terminal device by the network device.

[0179] Still taking the above example of three time points in time domain, in which the time points are time point 1, time point 2 and time point 3 in the order from front to back, the terminal device is in the idle state / activation state at the time point 1 and the time point 2, and the time point 1 and the time point 2 correspond to measurement data (each time point has respective first measurement data and second measurement data), the terminal device accesses the network device at the time point 3, in the time point 1 and the time point 2, the time point 2 is a time point of higher importance for the configuration of the network device to the terminal device, and the data amount of the second measurement data corresponding to the time point 2 can be greater than the data amount of the second measurement data corresponding to the time point 1.

[0180] Based on the above embodiment shown in FIG. 5, in some embodiments, the inference process of the AI / ML model can be performed at the UE side (UE side model), wherein the UE can obtain the following information as input for model inference:

[0181] I. DL measurement information (corresponding to the above first measurement data);

[0182] Wherein, the network device can configure the following DL advance measurement configuration (corresponding to the above first measurement configuration):

[0183] a) Advance measurement related configuration, including frequency information of measurement, measurement time interval configuration, etc.

[0184] b) At least the proportion of results to be measured or the proportion of predictable measurement results, that is, in the results reported by the UE, what percentage of the results are measured, and what percentage of the results are predicted;

[0185] c) Energy consumption / memory resources saved by the UE compared to direct measurement / signaling overhead saved on the air interface (proportion / parameters).

[0186] II. Speed, location related information, and / or predicted path related information (corresponding to the above auxiliary information), which can be determined in the following ways:

[0187] Can be reflected by RSRP change / RSRP value;

[0188] Can be obtained through APP information;

[0189] Can be reflected by sensing (sensor) information and positioning information of the UE device.

[0190] III. LOS / NLOS scenario information (corresponding to the above auxiliary information).

[0191] For the model inference process, the output information is: predicted measurement result information (corresponding to the above-mentioned second measurement data), which can be non-uniform in time domain, for example, the measurement result near the access time is more important, and the UE can output more predicted results at more important time (the predicted results are more dense in the time domain corresponding to the important time).

[0192] Illustratively, please refer to FIG. 6, which shows a framework diagram of UE-side AI / ML model inference according to the present application. As shown in FIG. 6, the UE-side AI / ML model inference scheme can include the following stages:

[0193] Step S1, the network device 610 sends the first measurement configuration to the terminal device 620, which is used to configure the frequency domain information and time interval of downlink measurement, and further includes the result proportion, the predictable measurement result proportion, the energy consumption / memory resource / signaling overhead saved compared with direct measurement, and other information.

[0194] Step S2, the terminal device 620 performs downlink measurement in the idle state / inactive state according to the first measurement configuration, obtains the first measurement data, and acquires the corresponding auxiliary information.

[0195] For example, in FIG. 6, the terminal device 620 performs downlink measurement on part of the time-frequency resources (i.e. the black-filled time-frequency resources in FIG. 6) in a time-frequency interval 630 to obtain the first measurement data.

[0196] Step S3, before / during / after the terminal device 620 accesses the network device 610, the terminal device 620 performs AI / ML model inference according to the acquired auxiliary information and the first measurement data to obtain the second measurement data.

[0197] For example, in FIG. 6, the terminal device 620 obtains the second measurement data on other time-frequency resources (i.e. the time-frequency resources without filling in FIG. 6) in the time-frequency interval 630 through AI / ML model inference.

[0198] Step S4, the terminal device 620 reports the first measurement data and the second measurement data to the network device 610, so that the network device 610 performs corresponding configuration on the terminal device 620 according to these measurement data, such as performing CA / DC related configuration on the terminal device 620.

[0199] Based on the above-mentioned embodiment shown in FIG. 5, in some embodiments, the inference process of the AI / ML model can be performed on the network side (NW side model), wherein the network needs to obtain the following information from the UE side as the input of the model inference:

[0200] I. A small amount of DL measurement information (corresponding to the first measurement data described above) can be carried by logged measurement information reported by the UE after entering the connected state;

[0201] II. Speed, location-related information, and / or predicted path-related information (corresponding to the auxiliary information described above) can be determined in the following ways:

[0202] RSRP changes / RSRP values can be used to reflect;

[0203] APP information can be obtained;

[0204] Sensing (sensor) information and positioning information of the UE device can be used to reflect.

[0205] III. LOS / NLOS scenario information (corresponding to the auxiliary information described above).

[0206] For the model inference process, the output information is predicted measurement result information (corresponding to the second measurement data described above). The predicted measurement result information can be non-uniform in the time domain, for example, measurement results near the access time are more important, and the network device can output more predicted results at more important time points when making predictions (the predicted results are more dense in the time domain corresponding to the important time points).

[0207] For illustration, please refer to FIG. 7, which shows a framework diagram of network-side AI / ML model inference according to the present application. As shown in FIG. 7, the network-side AI / ML model inference scheme can include the following stages:

[0208] Step S1: The network device 710 sends a first measurement configuration to the terminal device 720, which is used to configure the frequency domain information and time interval of downlink measurement, and further includes the proportion of measurement results, the proportion of predictable measurement results, and the energy consumption / memory resources / signaling overhead saved compared to direct measurement.

[0209] Step S2: The terminal device 720 performs downlink measurement in the idle state / inactive state according to the first measurement configuration, obtains first measurement data, and acquires corresponding auxiliary information.

[0210] For example, in FIG. 7, the terminal device 720 performs downlink measurement on part of the time-frequency resources (i.e., the black-filled time-frequency resources in FIG. 7) in a time-frequency interval 730 to obtain first measurement data.

[0211] Step S3, during the process that the terminal device 720 accesses the network device 710 / after the terminal device 720 accesses the network device 710, the terminal device 720 reports first measurement data and auxiliary information to the network device.

[0212] Step S4, the network device 710 performs AI / ML model inference to obtain second measurement data according to the auxiliary information and the first measurement data reported by the terminal device.

[0213] For example, in FIG. 7, the network device 710 obtains, through AI / ML model inference, the second measurement data on other time-frequency resources (i.e., the time-frequency resources without filling in FIG. 7) in the time-frequency interval 730.

[0214] Then, the network device 710 can perform corresponding configuration on the terminal device 720 according to the measurement data, such as performing CA / DC related configuration on the terminal device 720.

[0215] In the above embodiment, the second measurement data is generated by an artificial intelligence AI / machine learning ML model. The AI / ML model for generating the second measurement data can be trained by pre-collected measurement data, wherein the measurement data can also be collected by the network device instructing the terminal device.

[0216] Please refer to FIG. 8, which shows a flowchart of a wireless communication method provided by an embodiment of the present application, which can be executed by the terminal device and the network device interaction, wherein the terminal device can be the terminal device 120 in the foregoing network architecture, or the terminal device in other network architectures, and the network device can be the network device 110, the satellite 130 or the base station 140 in the foregoing network architecture, or the network device in other network architectures, which are not limited by the present application. The method can include at least part of the following steps:

[0217] Step 810: the network device sends a second measurement configuration to the terminal device; correspondingly, the terminal device receives the second measurement configuration sent by the network device.

[0218] The above-mentioned second measurement configuration is configuration information for instructing the terminal device to measure the training data of the AI / ML model in the idle state or the inactive state.

[0219] In some embodiments, the terminal device can receive the second measurement configuration information sent by the network device in the connected state, for example, the terminal device can receive the second measurement configuration sent by the network device through RRC signaling, medium access control-control element (MAC CE), downlink control information (DCI), etc. in the connected state.

[0220] In some embodiments, the terminal device can also receive the second measurement configuration sent by the network device through the RRC Release message when accessing the network last time.

[0221] In some embodiments, the terminal device can receive the second measurement configuration information sent by the network device before accessing the network device or during the process of accessing the network device, for example, the terminal device can receive the second measurement configuration sent by the network device through system message broadcast before accessing the network device, and for another example, the terminal device can receive the second measurement configuration sent by the network device through the downlink random access message during the process of accessing the network device.

[0222] Step 820: The terminal device measures to obtain a measurement data sample according to the second measurement configuration; the measurement data sample is used for training the AI / ML model.

[0223] The terminal device can measure to obtain a measurement data sample according to the second measurement configuration in the idle state or the inactive state. Alternatively, the terminal device can also measure to obtain a measurement data sample according to the second measurement configuration in the connected state.

[0224] In the training of the AI / ML model, the above measurement data sample can include a first measurement data sample and a second measurement data sample, wherein the first measurement data sample can be data input into the AI / ML model in the training process of the AI / ML model; the second measurement data sample can be actual measurement data corresponding to a training prediction result, wherein the training prediction result is an output result predicted by the AI / ML model according to the first measurement data sample; in the training process, the AI / ML model can be updated in parameters through a supervised learning manner or a reinforcement learning manner according to the difference between the second measurement data sample and the training prediction result. For example, in the supervised learning manner, the loss function value of the loss function can be calculated according to the difference between the second measurement data sample and the training prediction result, and the parameters of the AI / ML model can be updated through the loss function value, and in the reinforcement learning manner, the reward value of the reward function can be calculated according to the difference between the second measurement data sample and the training prediction result, and the parameters of the AI / ML model can be updated through the reward value.

[0225] Optionally, the density of distribution of the training prediction results in the time domain is associated with an interval between the time corresponding to the training prediction result and the time when the terminal device accesses the network device.

[0226] In some embodiments, the density of distribution of the training prediction results in the time domain is inversely related to the interval between the time corresponding to the training prediction result and the time when the terminal device accesses the network device.

[0227] Optionally, the measurement data samples can further include third measurement data samples for verifying the accuracy of the AI / ML model trained to a certain stage.

[0228] In the scheme shown in the embodiments of the present application, the terminal device can actually measure the training data for training the AI / ML model in the idle state or the inactive state based on the configuration of the network device, so as to train the AI / ML model by using the training data, thereby ensuring the flexibility and controllability of the training data acquisition process of the AI / ML model and ensuring the training effect of the subsequent AI / ML model.

[0229] In some embodiments, the second measurement configuration includes one or more of the following configurations: frequency domain information of the measurement, and time interval of the measurement.

[0230] In the above embodiments, the frequency domain information of the measurement is used to indicate which frequency domain the terminal device performs downlink measurement on the reference information.

[0231] The time interval of the measurement can refer to the time interval between two adjacent downlink measurements performed by the terminal device.

[0232] In some embodiments, the frequency domain information of the measurement in the second measurement configuration can refer to the frequency domain resource corresponding to the complete downlink measurement data required by the network device for managing the terminal device.

[0233] For example, the frequency domain resource corresponding to the complete downlink measurement data required by the network device for managing the terminal device includes a plurality of frequency bands, and the frequency domain information of the measurement can indicate the plurality of frequency bands. The terminal device can perform downlink measurement on the plurality of frequency bands indicated by the frequency domain information of the measurement.

[0234] For example, the frequency domain resource corresponding to the complete downlink measurement data required by the network device for managing the terminal device includes at least 10 frequency bands, and the frequency domain information of the measurement can indicate 10 or more frequency bands. The terminal device can perform downlink measurement on all or part (here, the part needs to be more than 10 frequency bands) of the 10 or more frequency bands indicated by the frequency domain information of the measurement.

[0235] Through the scheme shown in the above embodiments of the present application, the network device can configure the terminal device to perform downlink measurement on which frequency domain resources and how long to perform downlink measurement once every time, thereby ensuring the controllability of the downlink measurement operation performed by the terminal device when collecting training data.

[0236] In some embodiments, the second measurement configuration can further include second data quantity configuration information for indicating data quantities of the first measurement data samples and the second measurement data samples in the measurement data samples.

[0237] The terminal device can determine, according to the above-mentioned second data quantity configuration information, which / many time-frequency resources on which downlink measurement data in the measurement data samples obtained by measurement are the first measurement data samples and which / many time-frequency resources on which downlink measurement data are the second measurement data samples.

[0238] For example, assuming that the complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, the network device can indicate, through the second data quantity configuration information, that 5 time-frequency resources on which downlink measurement data in the measurement data samples are the first measurement data samples, and the remaining measurement data can be the second measurement data samples; accordingly, in a measurement process, the terminal device can perform downlink measurement and stop measurement when at least 10 time-frequency resources on which downlink measurement data are obtained, and 5 time-frequency resources on which downlink measurement data are the first measurement data samples, and the remaining time-frequency resources on which downlink measurement data are the second measurement data samples, so as to perform subsequent model training, or the first measurement data samples and the second measurement data samples are reported respectively.

[0239] In the embodiments of the present application, the network device can also provide the terminal device with related information of data quantities of the first measurement data samples and the second measurement data samples respectively, and the terminal device can determine the division mode of the first measurement data samples and the second measurement data samples in the measurement data samples according to the second data quantity configuration information in the second measurement configuration, thereby ensuring the flexibility of the terminal device in dividing the measurement data samples when collecting training data.

[0240] In some embodiments, the second data quantity configuration information includes one or more of the following information:

[0241] 1) second ratio information for indicating a ratio relationship between the data quantity of the first measurement data samples and the data quantity of the second measurement data samples.

[0242] The data amount of the first measurement data sample and the data amount of the second measurement data sample can be indicated by a proportional relationship between the data amount of the first measurement data sample and the data amount of the second measurement data sample. For example, assuming that complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, and the second proportion information is 5:5, the terminal device can determine, according to the second proportion information, that the first measurement data sample includes or at least includes downlink measurement data on 5 time-frequency resources.

[0243] 2) second resource saving information, used to indicate resources saved by the terminal device in the case of generating the second measurement data sample by the first measurement data sample.

[0244] The data amount of the first measurement data sample and the data amount of the second measurement data sample can also be indirectly indicated by configuring resources to be saved by the terminal device. The more resources to be saved by the terminal device, the lower the data amount of the first measurement data sample and the higher the data amount of the second measurement data sample. Conversely, the less resources to be saved by the terminal device, the higher the data amount of the first measurement data sample and the lower the data amount of the second measurement data sample.

[0245] The resources to be saved by the terminal device can be represented by a resource saving level. For example, assuming that the resource saving level has three levels of high, medium and low, the resource saving level being high indicates that the terminal device needs to save the most resources (for example, needs to reduce downlink measurement as much as possible to save resources), the resource saving level being medium indicates that the terminal device needs to save the medium resources, and the resource saving level being low indicates that the terminal device needs to save the least resources (for example, needs to appropriately increase downlink measurement to ensure the accuracy of measurement data). Assuming that complete downlink measurement data required by the network device for managing the terminal device includes downlink measurement data on at least 10 time-frequency resources, when the first resource saving information indicates that the resource saving level is high, the terminal device can determine to perform downlink measurement on a small number of time-frequency resources (for example, 3 time-frequency resources) to obtain the first measurement data sample, and perform downlink measurement on other time-frequency resources (for example, 7 time-frequency resources) to obtain the second measurement data sample. When the first resource saving information indicates that the resource saving level is medium, the terminal device can determine to perform downlink measurement on half of the time-frequency resources (for example, 5 time-frequency resources) to obtain the first measurement data sample, and perform downlink measurement on the other half of the time-frequency resources to obtain the second measurement data sample. When the first resource saving information indicates that the resource saving level is low, the terminal device can determine to perform downlink measurement on most of the time-frequency resources (for example, 7 time-frequency resources) to obtain the first measurement data sample, and perform downlink measurement on other time-frequency resources (for example, 3 time-frequency resources) to obtain the second measurement data sample.

[0246] In the embodiments of the present application, the terminal device can indirectly indicate the terminal device to determine the downlink measurement data obtained by performing downlink measurement on which time-frequency resources as the first measurement data sample / second measurement data sample through a proportional relationship or resources required to be saved by the terminal device, so that the terminal device can more flexibly divide the measurement data samples according to the actual needs.

[0247] In some embodiments, the above method further includes: the terminal device training the AI / ML model according to the measurement data samples.

[0248] In the embodiments of the present application, the terminal device can input the first measurement data sample in the measurement data samples into the AI / ML model, and perform parameter updating on the AI / ML model according to the difference between the result output by the AI / ML model and the second measurement data sample, to realize the training process of the AI / ML model.

[0249] Optionally, the terminal device can train multiple different AI / ML models according to different measurement data samples, for example, the terminal device can train AI / ML models suitable for different speeds, position change rates, intervals to which measurement values belong, and / or communication scenarios according to measurement data samples in different speeds, position change rates, intervals to which measurement values belong, and / or communication scenarios.

[0250] In the embodiments of the present application, the training process of the AI / ML model can be performed by the terminal device, so as to reduce the computing pressure of the network device, and the terminal device does not need to report the measurement data samples to the network device, so as to save the signaling resources between the terminal device and the network device.

[0251] In some embodiments, the terminal device can train the AI / ML model according to the measurement data samples and the auxiliary information samples.

[0252] The data type of the above auxiliary information sample is the same as that of the auxiliary information in the above embodiments. That is, the auxiliary information sample here is auxiliary information associated / corresponding to the measurement data sample in the time domain.

[0253] For example, the terminal device can input the first measurement data sample and the auxiliary information into the above AI / ML model together, and perform parameter updating on the AI / ML model according to the difference between the result output by the AI / ML model and the second measurement data sample, to realize the training process of the AI / ML model.

[0254] For another example, the terminal device can screen the first measurement data sample by the auxiliary information sample, and input the screened first measurement data sample to the AI / ML model. For example, the terminal device can determine, in combination with the auxiliary information sample, which measurement data in the current first measurement data sample is suitable for training the AI / ML model, and input the part of the first measurement data sample suitable for training the AI / ML model to the AI / ML model.

[0255] For example, the terminal device can be pre-configured with a correspondence between the auxiliary information sample and the time-frequency resource / data type / reference signal type suitable for training the AI / ML model, and the terminal device can determine, according to the current auxiliary information sample, the time-frequency resource / data type / reference signal type suitable for training the AI / ML model, and screen the measurement data corresponding to the time-frequency resource / data type / reference signal type suitable for training the AI / ML model from the first measurement data sample as the input of the AI / ML model.

[0256] The auxiliary information sample can be corresponding to a specified type of information in a certain time domain in the terminal device, and the time domain corresponding to the auxiliary information sample is associated with the time domain corresponding to the first measurement data sample. Optionally, the time domain association can be the same time domain, overlapping time domains, or a specified offset between time domains, etc.

[0257] In the embodiments of the present application, the terminal device can also refer to the auxiliary information sample other than the first measurement data sample when training the AI / ML model, thereby expanding the basis for training the AI / ML model and improving the accuracy of AI / ML model training.

[0258] In some embodiments, the method further includes: the terminal device reports the measurement data sample to the network device. Correspondingly, the network device receives the measurement data sample reported by the terminal device; and trains the AI / ML model according to the measurement data sample.

[0259] In the embodiments of the present application, the training process of the AI / ML model can also be performed on the network side, at this time, the terminal device needs to report the measurement data sample to the network device, for example, the terminal device can report the measurement data sample to the network device after measuring the measurement data sample; wherein the terminal device can report the measurement data sample to the network device through the uplink shared channel, or the measurement data sample can also be reported to the network device by the terminal device through the logged measurement information.

[0260] In the embodiments of the present application, the training process of the AI / ML model can be performed by the network device, thereby reducing the computing pressure of the terminal device and further improving the resource saving effect of the terminal device.

[0261] In some embodiments, the above method further includes: the terminal device reports the auxiliary information sample to the network device. Correspondingly, the network device receives the auxiliary information sample reported by the terminal device; and trains the AI / ML model according to the measurement data sample and the auxiliary information sample.

[0262] In the embodiments of the present application, in addition to reporting the measurement data sample, the terminal device also reports the auxiliary information corresponding to the measurement data sample (such as the auxiliary information associated with the measurement data sample in the time domain).

[0263] The measurement data sample and the auxiliary information sample can be reported by the terminal device to the network device through the same uplink channel / signal, or the measurement data sample and the auxiliary information sample can be reported by the terminal device to the network device through different uplink channels / signals.

[0264] For example, the network device can input the first measurement data sample and the auxiliary information into the AI / ML model together, and update the parameters of the AI / ML model according to the difference between the result output by the AI / ML model and the second measurement data sample, to realize the training process of the AI / ML model.

[0265] For another example, the network device can filter the first measurement data sample through the auxiliary information sample, and input the filtered first measurement data sample into the AI / ML model. For example, the network device can determine which measurement data in the current first measurement data sample is suitable for training the AI / ML model in combination with the auxiliary information sample, and input the part of the first measurement data sample suitable for training the AI / ML model into the AI / ML model.

[0266] For example, the network device can be pre-configured with a corresponding relationship between the auxiliary information sample and the time-frequency resource / data type / reference signal type suitable for training the AI / ML model, and can determine the time-frequency resource / data type / reference signal type suitable for training the AI / ML model according to the current auxiliary information sample, and filter the measurement data corresponding to the time-frequency resource / data type / reference signal type suitable for training the AI / ML model from the first measurement data sample as the input of the AI / ML model.

[0267] In the embodiments of the present application, the network device can also refer to the auxiliary information samples other than the measurement data samples when training the AI / ML model, thereby expanding the basis for training the AI / ML model and improving the accuracy of training the AI / ML model.

[0268] Based on the embodiment shown in FIG. 8, in some embodiments, the training process of the AI / ML model can be performed on the UE side, wherein the UE can obtain the following information for model training:

[0269] I. The UE needs to collect the following information from the network side (corresponding to the second measurement configuration) for downlink measurement:

[0270] a) Advance measurement related configuration, including frequency information of measurement, measurement time interval configuration, etc.;

[0271] b) At least the proportion of measured results or the proportion of predictable measurement results, that is, in the results reported by the UE, what percentage of the results are measured, and what percentage of the results are predicted;

[0272] c) Energy consumption / saved memory resources / signaling overhead saved on the air interface (proportion / parameters) saved by the UE compared with direct measurement.

[0273] II. The UE can obtain the following information by itself:

[0274] 1) DL measurement information (corresponding to the measurement data sample);

[0275] 2) Speed, location related information, and / or predicted path related information (corresponding to the auxiliary information sample), which can be determined in the following ways:

[0276] It can be reflected by RSRP change / RSRP value;

[0277] It can be obtained through APP information;

[0278] It can be reflected by sensing (sensor) information and positioning information of the UE device.

[0279] 3) LOS / NLOS scenario information (corresponding to the auxiliary information sample).

[0280] The model training process is as follows:

[0281] 1) Output predicted measurement result information, which can be non-uniform in time domain, for example, the measurement result near the access time is more important, and the UE can output more predicted results at more important time points when making prediction;

[0282] 2) Compare the predicted measurement result information with the actual measurement value and adjust the model parameters.

[0283] Based on the embodiment shown in FIG. 8, in some embodiments, the training process of the AI / ML model can be performed at the network side, where the network device can obtain the following information for model training:

[0284] I. A small amount of sparse DL measurement information (corresponding to the first measurement data sample), such as logged measurement information reported after entering the connected state.

[0285] II. Speed, location-related information, and / or predicted path-related information (corresponding to the auxiliary information sample), which can be determined in the following ways:

[0286] It can be reflected by RSRP change / RSRP value;

[0287] It can be obtained through APP information;

[0288] It can be reflected by sensing (sensor) information, positioning information, etc. of the UE device.

[0289] III. LOS / NLOS scenario information (corresponding to the auxiliary information sample).

[0290] The model training process is as follows:

[0291] 1) Output the predicted measurement result information, which can be non-uniform in the time domain, for example, the measurement result near the access time is more important, and the UE can output more predicted results at more important time points when making predictions;

[0292] 2) The UE needs to report the actual measurement information (corresponding to the second measurement data sample), compare the predicted measurement result information with the actual measurement value, and adjust the model parameters.

[0293] In the above embodiment, the second measurement data is generated by an artificial intelligence AI / machine learning ML model. The management process of the AI / ML model can be performed by the terminal device.

[0294] Please refer to FIG. 9, which shows a flowchart of a wireless communication method according to an embodiment of the present application. The method can be performed by the terminal device and the network device, where the terminal device can be the terminal device 120 in the foregoing network architecture, or a terminal device in other network architectures, and the network device can be the network device 110, satellite 130, or base station 140 in the foregoing network architecture, or a network device in other network architectures, which are not limited in the present application. The method can include at least part of the following steps:

[0295] Step 910: The network device sends model management condition information to the terminal device; the model management condition information is used to indicate a condition for the terminal device to perform a management operation on the AI / ML model; correspondingly, the terminal device receives the model management condition information sent by the network device.

[0296] In some embodiments, the network device can send the model management condition information to the terminal device when the terminal device is in a connected state, for example, the terminal device can receive the model management condition information sent by the network device through RRC signaling, medium access control-control element (MAC CE), downlink control information (DCI), etc. in the connected state.

[0297] In some embodiments, the terminal device can also receive the model management condition information sent by the network device through the RRC Release message when accessing the network last time.

[0298] In some embodiments, the terminal device can receive the model management condition information sent by the network device before accessing the network device, or during the process of accessing the network device, for example, the terminal device can receive the model management condition information sent by the network device through system message broadcast before accessing the network device, and for another example, the terminal device can receive the model management condition information sent by the network device through the downlink random access message during the process of accessing the network device.

[0299] Step 920: In a case where the condition corresponding to the model management condition information is met, the terminal device performs a management operation on the AI / ML model.

[0300] The management operation includes one or more of the following operations:

[0301] Enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0302] In the embodiments of the present application, the network device can configure the terminal device with the condition of model management to indicate the terminal device to perform the management of enabling, switching, and / or disabling the AI / ML model in what case, thereby guaranteeing the flexibility and rationality of the AI / ML model application and the accuracy of the predicted measurement data through the AI / ML model.

[0303] In the embodiments of the present application, the terminal device can perform the management operation on the AI / ML model according to the model management information.

[0304] In some embodiments, the model management information includes one or more of the following: downlink measurement results of the terminal device on a current cell and / or a neighboring cell; speed information of the terminal device; location information of the terminal device; a communication scenario corresponding to the terminal device.

[0305] In the embodiments of the present application, the downlink measurement results of the terminal device on the current cell and / or the neighboring cell can affect the use of the AI / ML model; for example, in the case that part of the downlink measurement results are missing in the downlink measurement results of the current cell and / or the neighboring cell, the AI / ML model can be enabled; for another example, in the case that the values of the downlink measurement results of the current cell and / or the neighboring cell do not match the currently used AI / ML model, the AI / ML model can be switched.

[0306] The speed information of the terminal device can affect the use of the AI / ML model; for example, in the case that the moving speed of the terminal device does not match the currently used AI / ML model, the AI / ML model can be switched; for another example, in the case that the moving speed of the terminal device is fast, the AI / ML model can be disabled; for another example, in the case that the moving speed of the terminal device is slow, the AI / ML model can be enabled.

[0307] The location information of the terminal device can affect the use of the AI / ML model; for example, in the case that the location of the terminal device does not match the currently used AI / ML model, the AI / ML model can be switched; for another example, in the case that the location of the terminal device is within a specified range, the AI / ML model can be enabled; for another example, in the case that the location of the terminal device is outside the specified range, the AI / ML model can be disabled. The specified range can be pre-configured to the terminal device by the network device.

[0308] The communication scenario corresponding to the terminal device can affect the use of the AI / ML model; for example, in the case that the terminal device is in a LOS communication scenario, the AI / ML model can be enabled; for another example, in the case that the terminal device is in a NLOS communication scenario, the AI / ML model can be disabled.

[0309] In the embodiments of the present application, the terminal device can manage the enabling, switching and / or disabling of the AI / ML model according to its own downlink measurement results, speed, location, communication scenario, etc., which can ensure the flexibility and rationality of the AI / ML model application, and further ensure the accuracy of the predicted measurement data through the AI / ML model.

[0310] In some embodiments, the model management condition information includes one or more of the following:

[0311] a speed threshold of the terminal device; a location change threshold of the terminal device; a downlink measurement result threshold of the terminal device; a communication scenario; and a ratio threshold between the first measurement data and the second measurement data.

[0312] Optionally, the speed threshold of the terminal device in the model management condition information can be used to indicate that the terminal device performs the management operation of enabling, switching and / or disabling of the AI / ML model in which / which range of speed.

[0313] Optionally, the location change threshold of the terminal device in the model management condition information can be used to indicate that the terminal device performs the management operation of enabling, switching and / or disabling of the AI / ML model in which / which range of location change.

[0314] Optionally, the downlink measurement result threshold of the terminal device in the model management condition information can be used to indicate that the terminal device performs the management operation of enabling, switching and / or disabling of the AI / ML model in which / which range of measurement value.

[0315] Optionally, the communication scenario in the model management condition information can be used to indicate that the terminal device performs the management operation of enabling, switching and / or disabling of the AI / ML model in which scenario.

[0316] Optionally, the ratio threshold between the first measurement data and the second measurement data in the model management condition information can be used to indicate that the terminal device performs the management operation of enabling, switching and / or disabling of the AI / ML model in which / which range of ratio between the first measurement data and the second measurement data, such as switching to a more suitable AI / ML model when the ratio between the first measurement data and the second measurement data exceeds / is lower than a certain ratio.

[0317] In the above-mentioned scheme of the embodiments of the present application, the network device can control the management behavior of the terminal device on the AI / ML model through the speed threshold, the location change threshold, the downlink measurement result threshold, the communication scenario, the ratio threshold between the measurement result and the prediction result, etc., to ensure the rationality and accuracy of the AI / ML model management.

[0318] In some embodiments, the above-mentioned method further comprises: the terminal device reporting the operation result of the management operation to the network device. Correspondingly, the network device receives the operation result of the management operation reported by the terminal device.

[0319] For example, the terminal device can report the operation result of the above-mentioned management operation through RRC signaling, MAC CE or DCI, etc.

[0320] The management result of the management operation can include a management mode, whether the management is successful, and a state of the AI / ML model after management (such as an AI / ML model that has been enabled, an AI / ML model that is currently enabled, an AI / ML model that has been disabled, and the like).

[0321] In the scheme shown in the above embodiments of the present application, the terminal device can report the operation result of the management operation of the model to the network device, so that the network device can learn the state of the current AI / ML model in time and ensure the synchronization of information between the network device and the terminal device.

[0322] Based on the embodiment shown in FIG. 9, the network device can configure the conditions for the UE to perform model management (such as switching models, falling back to a non-AI mode, using an AI mode, and the like). These conditions can include:

[0323] 1) a speed / position change threshold, which can be an absolute value of the speed / position or a change value of the speed / position;

[0324] 2) a DL (RSRP / RSRQ / SINR) measurement threshold;

[0325] 3) a LOS / NLOS scenario, such as an AI mode available in a LOS scenario;

[0326] 4) a prediction ratio threshold.

[0327] After successfully accessing the network device, the UE can report the management result to the network device, that is, the model used during access / whether the model is used.

[0328] In the above embodiment, the second measurement data is generated by an artificial intelligence AI / machine learning ML model. The management process of the AI / ML model can be performed by the network device.

[0329] Referring to FIG. 10, a flowchart of a wireless communication method is shown, which can be performed by the terminal device and the network device. The terminal device can be the terminal device 120 in the network architecture, or a terminal device in another network architecture. The network device can be the network device 110, the satellite 130, or the base station 140 in the network architecture, or a network device in another network architecture. The method can include at least some of the following steps:

[0330] In step 1010, the terminal device reports model management information to the network device. Correspondingly, the network device receives the model management information reported by the terminal device.

[0331] For example, the terminal device can report the model management information through RRC signaling, MAC CE, or DCI.

[0332] Step 1020: The network device performs a management operation on the AI / ML model according to the model management information.

[0333] The management operation includes one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0334] The above management information is obtained by the terminal device and is used to determine whether to start, close, or switch the AI / ML model.

[0335] Step 1030: The network device sends the operation result of the management operation to the terminal device; correspondingly, the terminal device receives the operation result of the management operation.

[0336] The management result of the above management operation can include: management method, whether the management is successful, and the state of the AI / ML model after management (such as the AI / ML model has been enabled, the AI / ML model currently enabled, the AI / ML model has been disabled, etc.).

[0337] In the embodiments of the present application, the network device can receive the model management information reported by the terminal device, and perform the management of enabling, switching, and / or disabling the AI / ML model according to the model management information, thereby ensuring the flexibility and rationality of the AI / ML model application, and ensuring the accuracy of the predicted measurement data through the AI / ML model.

[0338] In some embodiments, the above model management information includes one or more of the following information: downlink measurement result of the terminal device on the current cell and / or neighboring cell; speed information of the terminal device; location information of the terminal device; and communication scenario corresponding to the terminal device.

[0339] In the embodiments of the present application, the downlink measurement result of the terminal device on the current cell and / or neighboring cell can affect the use of the AI / ML model; for example, if some of the downlink measurement results are missing in the downlink measurement result of the current cell and / or neighboring cell, it can indicate that the AI / ML model is enabled; for another example, if the numerical value of the downlink measurement result of the current cell and / or neighboring cell does not match the currently used AI / ML model, it can indicate that the AI / ML model is switched.

[0340] The speed information of the aforementioned terminal devices can affect the use of AI / ML models. For example, if the moving speed of the terminal device does not match the currently used AI / ML model, it can indicate to switch the AI / ML model; if the moving speed of the terminal device is relatively fast, it can indicate to disable the AI / ML model; if the moving speed of the terminal device is relatively slow, it can indicate to enable the AI / ML model.

[0341] The location information of the aforementioned terminal devices can affect the use of AI / ML models. For example, if the location of the terminal device does not match the currently used AI / ML model, it can instruct the user to switch AI / ML models. Alternatively, if the terminal device's location is within a specified range, it can instruct the user to enable the AI / ML model. Furthermore, if the terminal device's location is outside the specified range, it can instruct the user to disable the AI / ML model. The specified range can be pre-configured for the terminal devices by the network equipment.

[0342] The communication scenarios corresponding to the aforementioned terminal devices can affect the use of AI / ML models; for example, if the terminal device is in a LOS communication scenario, it can be instructed to enable the AI / ML model; and if the terminal device is in a NLOS communication scenario, it can be instructed to disable the AI / ML model.

[0343] In this embodiment, the network device can manage the activation, switching, and / or deactivation of AI / ML models based on downlink measurement results, speed, location, communication scenarios, etc. on the terminal device side. This ensures the flexibility and rationality of AI / ML model application, thereby guaranteeing the accuracy of measurement data predicted by AI / ML models.

[0344] In some embodiments, the method further includes: the network device configuring management information reporting conditions to the terminal device; the management information reporting conditions are used to indicate the conditions under which the terminal device reports model management information to the network device; correspondingly, the terminal device receives the management information reporting conditions configured by the network device; wherein, the terminal device reports model management information to the network device when the conditions corresponding to the management information reporting conditions are met.

[0345] In some embodiments, the network device can send management information reporting condition information to the terminal device when the terminal device is in a connected state. For example, the terminal device can receive management information reporting condition information sent by the network device in the connected state through RRC signaling, Medium Access Control-Control Element (MAC CE), Downlink Control Information (DCI), etc.

[0346] In some embodiments, the terminal device may also receive management information reporting condition information sent by the network device via an RRC Release message when it last accessed the network.

[0347] In some embodiments, the terminal device may receive management information reporting condition information sent by the network device before accessing the network device, or during the process of accessing the network device. For example, the terminal device may receive management information reporting condition information sent by the network device through system message broadcast before accessing the network device, or the terminal device may receive management information reporting condition information sent by the network device through downlink random access messages during the process of accessing the network device.

[0348] In this embodiment of the application, the network device can instruct the terminal device under what circumstances to report management information by reporting management information to the terminal device, thereby avoiding meaningless reporting of management information and further saving the terminal device's energy consumption, memory resources and signaling resources.

[0349] In some embodiments, the management information reporting condition information includes one or more of the following:

[0350] The speed threshold of the terminal device; the position change threshold of the terminal device; the downlink measurement result threshold of the terminal device; the communication scenario; and the ratio threshold between the first measurement data and the second measurement data.

[0351] Optionally, the speed threshold of the terminal device in the above-mentioned management information reporting conditions can be used to indicate which / which speed ranges the terminal device may need to perform management operations to enable, switch and / or disable the AI / ML model.

[0352] Optionally, the location change threshold of the terminal device in the above-mentioned management information reporting conditions can be used to indicate which / which location change ranges the terminal device may need to perform management operations to enable, switch and / or disable the AI / ML model.

[0353] Optionally, the downlink measurement result threshold of the terminal device in the above-mentioned management information reporting conditions information can be used to indicate which / which measurement value ranges the terminal device may need to perform management operations to enable, switch and / or disable the AI / ML model.

[0354] Optionally, the communication scenarios in the above-mentioned management information reporting conditions can be used to indicate in which scenarios the terminal device may need to perform management operations to enable, switch and / or disable the AI / ML model.

[0355] Optionally, the ratio threshold between the first measurement data and the second measurement data in the above-mentioned management information reporting conditions can be used to indicate which ratio range between the first measurement data and the second measurement data the terminal device may need to perform management operations such as enabling, switching and / or disabling the AI / ML model. For example, when the ratio between the first measurement data and the second measurement data exceeds / below a certain ratio, it may be necessary to switch to a more suitable AI / ML model.

[0356] In the solutions shown in the above embodiments of this application, network devices can control terminal devices to report management information through information such as speed threshold, location change threshold, downlink measurement result threshold, communication scenario, and ratio threshold between measurement result and prediction result, so as to manage AI / ML models and ensure the rationality and accuracy of AI / ML model management.

[0357] In some embodiments, a network device may send the operation result of a management operation to a terminal device via a broadcast message; correspondingly, the terminal device may receive the operation result of the management operation sent by the network device via a broadcast message.

[0358] Alternatively, network devices can send the results of management operations to terminal devices via unicast messages; correspondingly, terminal devices can receive the results of management operations sent by network devices via unicast messages.

[0359] In some embodiments, a unicast message includes one or more of the following: a Dedicated Radio Resource Control (RRC) message; a reconfiguration message; or an RRC release message.

[0360] Based on the embodiment shown in Figure 10 above, the network device can configure the conditions for the UE to report model management information. The reporting conditions for model management information (such as switching models, falling back to non-AI mode, using AI mode, etc.) may include:

[0361] 1) Velocity / position change threshold;

[0362] 2) DL (RSRP / RSRQ / SINR) measurement threshold;

[0363] 3) LOS / NLOS scenarios;

[0364] 4) Predict the proportion threshold.

[0365] When the above conditions are met, the UE reports the following model management information to the network after establishing a connection:

[0366] 1) DL measurement results (which may include results from this cell and / or neighboring cells);

[0367] 2) Speed ​​and position information;

[0368] 3) The current scenario is either LOS or NLOS.

[0369] The network device performs model management operations based on the above model management information and sends the model management results to the UE in the cell. For example, the model management results can be sent via broadcast (SIB) or unicast (dedicated RRC messages, such as reconfiguration messages or RRC release messages).

[0370] The embodiments described above in this application use AI-assisted methods to predict measurement results, which can save UE power consumption, UE memory, air interface signaling overhead and resources in the advance measurement mechanism, and can also solve the problem that the UE cannot obtain measurement results at certain times.

[0371] The above embodiments of this application provide different schemes and designs in which the network side and the UE side act as the execution entities for model training, inference and management, respectively, during the life cycle of AI / ML models.

[0372] The model training, inference, and management solutions provided in the above embodiments of this application can be used individually or in combination.

[0373] Please refer to Figure 11, which shows a block diagram of a wireless communication device according to an embodiment of this application. This wireless communication device has the functions performed by a terminal device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10. As shown in Figure 11, the device may include:

[0374] Receiver module 1101 is used to receive the first measurement configuration sent by the network device;

[0375] The measurement module 1102 is used to measure and obtain first measurement data according to the first measurement configuration in an idle state or an inactive state; the first measurement data is used to generate second measurement data.

[0376] In some embodiments, the first measurement configuration includes one or more of the following: frequency domain information of the measurement, and the measurement time interval.

[0377] In some embodiments, the first measurement configuration further includes: first data volume configuration information, used to indicate the data volume of the first measurement data and the data volume of the second measurement data.

[0378] In some embodiments, the first data volume configuration information includes one or more of the following:

[0379] The first ratio information is used to indicate the proportional relationship between the amount of data in the first measurement data and the amount of data in the second measurement data;

[0380] First resource saving information is used to indicate the resources saved by the terminal device when the second measurement data is generated from the first measurement data.

[0381] In some embodiments, the resources saved by the terminal device include one or more of the following: energy consumption saved by the terminal device; memory resources saved by the terminal device; and signaling overhead saved by the terminal device.

[0382] In some embodiments, the apparatus further includes:

[0383] The generation module is used to generate the second measurement data based on the first measurement data.

[0384] In some embodiments, the generation module is configured to generate the second measurement data based on the first measurement data and auxiliary information;

[0385] The auxiliary information is information used to assist in generating the second measurement data.

[0386] In some embodiments, the apparatus further includes:

[0387] The sending module is used to report the first measurement data to the network device.

[0388] In some embodiments, the sending module is further configured to report auxiliary information to the network device;

[0389] The auxiliary information is information used to assist in generating the second measurement data.

[0390] In some embodiments, the auxiliary information includes one or more of the following:

[0391] Mobility status information is used to indicate the mobility status of the terminal device;

[0392] Scene information is used to indicate the communication scene of the terminal device.

[0393] In some embodiments, the mobility status information includes one or more of the following: speed information; location information; and path information.

[0394] In some embodiments, the mobility status information is determined by one or more of the following: the reference signal received power (RSRP) measured by the terminal device; information about the application in the terminal device; sensor information of the terminal device; and positioning information of the terminal device.

[0395] In some embodiments, the second measurement data is generated by an artificial intelligence (AI) / machine learning (ML) model, and the receiving module 1101 is further configured to receive a second measurement configuration sent by a network device;

[0396] The measurement module 1102 is further configured to obtain measurement data samples according to the second measurement configuration; the measurement data samples are used to train the AI / ML model.

[0397] In some embodiments, the second measurement configuration includes one or more of the following: frequency domain information of the measurement, and the measurement time interval.

[0398] In some embodiments, the second measurement configuration further includes: second data volume configuration information, used to indicate the data volume of the first measurement data sample and the second measurement data sample in the measurement data samples;

[0399] Wherein, the first measurement data sample is the data input to the AI / ML model during the training process of the AI / ML model; the second measurement data sample is the actual measurement data corresponding to the training prediction result, and the training prediction result is the output result predicted by the AI / ML model based on the first measurement data sample.

[0400] In some embodiments, the second data volume configuration information includes one or more of the following:

[0401] The second ratio information is used to indicate the proportional relationship between the amount of data in the first measurement data sample and the amount of data in the second measurement data sample;

[0402] The second resource-saving information is used to indicate the resources saved by the terminal device when the second measurement data sample is generated from the first measurement data sample.

[0403] In some embodiments, the apparatus further includes a model training module for training the AI / ML model based on measurement data samples.

[0404] In some embodiments, the model training module is used to train an AI / ML model based on measurement data samples and auxiliary information samples.

[0405] In some embodiments, the apparatus further includes a transmitting module for reporting the measurement data sample to the network device.

[0406] In some embodiments, the sending module is further configured to report auxiliary information samples to the network device.

[0407] In some embodiments, the second measurement data is generated by an AI / ML model, and the receiving module 1101 is further configured to receive model management condition information sent by the network device;

[0408] The management module shall perform management operations on the AI / ML model when the conditions corresponding to the model management condition information are met; wherein the management operations include one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0409] In some embodiments, the model management condition information includes one or more of the following: the speed threshold of the terminal device; the position change threshold of the terminal device; the downlink measurement result threshold of the terminal device; the communication scenario; and the ratio threshold between the first measurement data and the second measurement data.

[0410] In some embodiments, the apparatus further includes a sending module for reporting the operation result of the management operation to the network device.

[0411] In some embodiments, the second measurement data is generated by an AI / ML model, and the apparatus further includes: a sending module for reporting model management information to the network device, the model management information being used by the network device to perform management operations on the AI / ML model;

[0412] The receiving module 1101 is further configured to receive the operation result of the management operation sent by the network device; wherein the management operation includes one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0413] In some embodiments, the receiving module 1101 is further configured to receive management information reporting condition information configured by the network device;

[0414] The sending module is used to report the model management information to the network device when the conditions corresponding to the management information reporting conditions are met.

[0415] In some embodiments, the management information reporting condition information includes one or more of the following: the speed threshold of the terminal device; the position change threshold of the terminal device; the downlink measurement result threshold of the terminal device; the communication scenario; and the ratio threshold between the first measurement data and the second measurement data.

[0416] In some embodiments, the model management information includes one or more of the following: downlink measurement results of the terminal device for the current cell and / or neighboring cells; speed information of the terminal device; location information of the terminal device; and the communication scenario corresponding to the terminal device.

[0417] In some embodiments, the receiving module 1101 is configured to receive the operation result of the management operation sent by the network device via a broadcast message; or, to receive the operation result of the management operation sent by the network device via a unicast message.

[0418] In some embodiments, the unicast message includes one or more of the following: a Dedicated Radio Resource Control (RRC) message; a reconfiguration message; or an RRC release message.

[0419] In some embodiments, the density of the second measurement data in the time domain is associated with the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device.

[0420] In some embodiments, the density of the second measurement data in the time domain is inversely correlated with the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device.

[0421] Please refer to Figure 12, which shows a block diagram of a wireless communication device according to an embodiment of this application. This wireless communication device has the functions performed by a network device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10. As shown in Figure 12, the device may include:

[0422] The sending module 1201 is used to send a first measurement configuration to the terminal device; the first measurement configuration is used to instruct the terminal device to measure first measurement data in an idle state or an inactive state; the first measurement data is used to generate second measurement data.

[0423] In some embodiments, the first measurement configuration includes one or more of the following: frequency domain information of the measurement, and the measurement time interval.

[0424] In some embodiments, the first measurement configuration further includes: first data volume configuration information, used to indicate the data volume of the first measurement data and the data volume of the second measurement data.

[0425] In some embodiments, the first data volume configuration information includes one or more of the following:

[0426] The first ratio information is used to indicate the proportional relationship between the amount of data in the first measurement data and the amount of data in the second measurement data;

[0427] First resource saving information is used to indicate the resources saved by the terminal device when the second measurement data is generated from the first measurement data.

[0428] In some embodiments, the resources saved by the terminal device include one or more of the following: energy consumption saved by the terminal device; memory resources saved by the terminal device; and signaling overhead saved by the terminal device.

[0429] In some embodiments, the apparatus further includes:

[0430] The receiving module is used to receive the first measurement data reported by the terminal device;

[0431] The generation module is used to generate the second measurement data based on the first measurement data.

[0432] In some embodiments, the apparatus further includes:

[0433] The receiving module is further configured to receive auxiliary information reported by the terminal device; wherein the auxiliary information is information used to assist in generating the second measurement data;

[0434] The generation module is used to generate the second measurement data based on the first measurement data and auxiliary information.

[0435] In some embodiments, the auxiliary information includes one or more of the following: mobility status information, used to indicate the mobility status of the terminal device; and scenario information, used to indicate the communication scenario of the terminal device.

[0436] In some embodiments, the mobility status information includes one or more of the following: speed information; location information; and path information.

[0437] In some embodiments, the mobility status information is determined by one or more of the following: the reference signal received power (RSRP) measured by the terminal device; information about the application in the terminal device; sensor information of the terminal device; and positioning information of the terminal device.

[0438] In some embodiments, the second measurement data is generated by an artificial intelligence (AI) / machine learning (ML) model, and the sending module 1201 is further configured to send a second measurement configuration to the terminal device; the second measurement configuration is used to instruct the terminal device to measure and obtain measurement data samples according to the second measurement configuration; the measurement data samples are used to train the AI / ML model.

[0439] In some embodiments, the second measurement configuration includes one or more of the following: frequency domain information of the measurement, and the measurement time interval.

[0440] In some embodiments, the second measurement configuration further includes: second data volume configuration information, used to indicate the data volume of the first measurement data sample and the second measurement data sample in the measurement data samples;

[0441] Wherein, the first measurement data sample is the data input to the AI / ML model during the training process of the AI / ML model; the second measurement data sample is the actual measurement data corresponding to the training prediction result, and the training prediction result is the output result predicted by the AI / ML model based on the first measurement data sample.

[0442] In some embodiments, the second data volume configuration information includes one or more of the following: second ratio information, used to indicate the ratio between the data volume of the first measurement data sample and the data volume of the second measurement data sample; and second resource saving information, used to indicate the resources saved by the terminal device when the second measurement data sample is generated from the first measurement data sample.

[0443] In some embodiments, the apparatus further includes:

[0444] The receiving module is used to receive the measurement data samples reported by the terminal device;

[0445] The model training module is used to train the AI / ML model based on the measurement data samples.

[0446] In some embodiments, the receiving module is further configured to receive auxiliary information samples reported by the terminal device;

[0447] The model training module is used to train the AI / ML model based on the measurement data samples and auxiliary information samples.

[0448] In some embodiments, the second measurement data is generated by an AI / ML model, and the sending module 1201 is further configured to send model management condition information to the terminal device; the model management condition information is used to instruct the terminal device to perform management operations on the AI / ML model; wherein, the management operation includes one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0449] In some embodiments, the model management condition information includes one or more of the following: the speed threshold of the terminal device; the position change threshold of the terminal device; the downlink measurement result threshold of the terminal device; the communication scenario; and the ratio threshold between the first measurement data and the second measurement data.

[0450] In some embodiments, the apparatus further includes a receiving module for receiving the operation result of the management operation reported by the terminal device.

[0451] In some embodiments, the second measurement data is generated by an AI / ML model, and the apparatus further includes:

[0452] The receiving module is used to receive model management information reported by the terminal device;

[0453] The management module is used to perform management operations on the AI / ML model based on the model management information.

[0454] The sending module 1201 is also used to send the operation result of the management operation to the terminal device;

[0455] The management operations include one or more of the following: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

[0456] In some embodiments, the sending module 1201 is further configured to send management information reporting condition information to the terminal device; the management information reporting condition information is used to instruct the terminal device to report the model management information to the network device under certain conditions.

[0457] In some embodiments, the management information reporting condition information includes one or more of the following: the speed threshold of the terminal device; the position change threshold of the terminal device; the downlink measurement result threshold of the terminal device; the communication scenario; and the ratio threshold between the first measurement data and the second measurement data.

[0458] In some embodiments, the model management information includes one or more of the following: downlink measurement results of the terminal device for the current cell and / or neighboring cells; speed information of the terminal device; location information of the terminal device; and the communication scenario corresponding to the terminal device.

[0459] In some embodiments, the sending module 1201 is configured to send the operation result of the management operation to the terminal device via a broadcast message; or, send the operation result of the management operation to the terminal device via a unicast message.

[0460] In some embodiments, the unicast message includes one or more of the following: a Dedicated Radio Resource Control (RRC) message; a reconfiguration message; or an RRC release message.

[0461] In some embodiments, the density of the second measurement data in the time domain is associated with the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device.

[0462] In some embodiments, the density of the second measurement data in the time domain is inversely correlated with the interval between the time corresponding to the second measurement data and the time when the terminal device accesses the network device.

[0463] It should be noted that the device provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules according to actual needs, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0464] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0465] Please refer to Figure 13, which shows a schematic diagram of the structure of a communication device 1300 provided in one embodiment of this application. The communication device 1300 may include: a processor 1301, a receiver 1302, a transmitter 1303, a memory 1304, and a bus 1305.

[0466] The processor 1301 includes one or more processing cores, and the processor 1301 executes various functional applications and information processing by running software programs and modules.

[0467] The receiver 1302 and transmitter 1303 can be implemented as a communication component, which can be a communication chip. This communication chip can also be called a transceiver. The memory 1304 is connected to the processor 1301 via a bus 1305. The memory 1304 can be used to store computer programs, and the processor 1301 uses these computer programs to execute the various steps in the above method embodiments.

[0468] Furthermore, the memory 1304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, including but not limited to: magnetic disks or optical disks, electrically erasable programmable read-only memory, erasable programmable read-only memory, static on-demand memory, read-only memory, magnetic memory, flash memory, and programmable read-only memory.

[0469] In one exemplary embodiment, when the communication device 1300 is implemented as the aforementioned terminal device, the receiver 1302 and the processor 1301 execute the computer program to enable the communication device to implement the various steps performed by the terminal device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10.

[0470] In one exemplary embodiment, when the communication device 1300 is implemented as the network device described above, the transmitter 1303 and the processor 1301 execute the computer program to cause the communication device to implement the various steps performed by the network device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10.

[0471] This application also provides a computer-readable storage medium storing a computer program, which is loaded and executed by a processor to implement all or part of the steps performed by a terminal device or network device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10.

[0472] This application also provides a chip including an integrated circuit and firmware disposed in the integrated circuit, the chip being used to operate in a communication device to cause the communication device to perform all or part of the steps performed by the terminal device or network device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10 above.

[0473] This application also provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a communication device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the communication device to perform all or part of the steps in the methods shown in any of Figures 3 to 5 and Figures 8 to 10, as performed by a terminal device or a network device.

[0474] This application also provides a computer program executed by a processor of a communication device to implement all or part of the steps performed by a terminal device or a network device in any of the methods shown in Figures 3 to 5 and Figures 8 to 10 above.

[0475] Those skilled in the art will recognize that the functions described in the embodiments of this application in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0476] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of wireless communication, the method comprising: The method is performed by a terminal device, and the method comprises: receiving a first measurement configuration sent by a network device; in an idle state or an inactive state, measuring first measurement data according to the first measurement configuration; the first measurement data is used to generate second measurement data.

2. The method of claim 1, wherein, The first measurement configuration comprises one or more of the following configurations: frequency domain information of measurement, and time interval of measurement.

3. The method according to claim 1 or 2, characterized in that, The first measurement configuration further comprises: first data amount configuration information used to indicate a data amount of the first measurement data and a data amount of the second measurement data.

4. The method of claim 3, wherein, The first data amount configuration information comprises one or more of the following information: first proportion information used to indicate a proportional relationship between the data amount of the first measurement data and the data amount of the second measurement data; first resource saving information used to indicate resources saved by the terminal device in a case where the second measurement data is generated by the first measurement data.

5. The method of claim 4, wherein, The resources saved by the terminal device comprise one or more of the following information: energy consumption saved by the terminal device; memory resources saved by the terminal device; and signaling overhead saved by the terminal device.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: generating the second measurement data according to the first measurement data.

7. The method of claim 6, wherein, The generating of the second measurement data according to the first measurement data comprises generating the second measurement data according to the first measurement data and auxiliary information; The auxiliary information is information used to assist in generating the second measurement data.

8. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: reporting the first measurement data to the network device.

9. The method of claim 8, wherein, The method further comprises: reporting auxiliary information to the network device; The auxiliary information is information used to assist in generating the second measurement data.

10. The method according to claim 7 or 9, characterized in that, The auxiliary information comprises one or more of the following information: movement state information used to indicate a movement state of the terminal device; and scene information used to indicate a communication scene of the terminal device.

11. The method of claim 10, wherein, The movement state information comprises one or more of the following information: speed information; position information; and path information.

12. The method according to claim 10 or 11, characterized in that, The movement state information is determined by one or more of the following information: reference signal received power (RSRP) measured by the terminal device; information of an application program in the terminal device; sensor information of the terminal device; and positioning information of the terminal device.

13. The method according to any one of claims 1 to 12, characterized in that, The second measurement data is generated by an artificial intelligence (AI) / machine learning (ML) model, and the method further comprises: receiving a second measurement configuration sent by a network device; and measuring measurement data samples according to the second measurement configuration; the measurement data samples are used to train the AI / ML model.

14. The method of claim 13, wherein, The second measurement configuration comprises one or more of the following configurations: frequency domain information of measurement, and time interval of measurement.

15. The method of claim 14, wherein, The second measurement configuration further comprises: Second data quantity configuration information, used to indicate data quantities of a first measurement data sample and a second measurement data sample in the measurement data samples; wherein, the first measurement data sample is data input to the AI / ML model in a training process of the AI / ML model; the second measurement data sample is actual measurement data corresponding to a training prediction result, which is an output result predicted by the AI / ML model according to the first measurement data sample.

16. The method of claim 15, wherein, The second data quantity configuration information comprises one or more of the following information: second ratio information, used to indicate a ratio relationship between the data quantity of the first measurement data sample and the data quantity of the second measurement data sample; Second resource saving information, used to indicate resources saved by the terminal device in a case where the second measurement data sample is generated by the first measurement data sample.

17. The method of any one of claims 13 to 16, wherein, The method further comprises: Training the AI / ML model according to the measurement data samples.

18. The method of claim 17, wherein, The training of the AI / ML model according to the measurement data samples comprises training the AI / ML model according to the measurement data samples and auxiliary information samples.

19. The method of any one of claims 13 to 16, wherein, The method further comprises: Reporting the measurement data samples to the network device.

20. The method of claim 19, wherein, The method further comprises: reporting auxiliary information samples to the network device.

21. The method of any one of claims 1 to 20, wherein, The second measurement data is generated by an AI / ML model, and the method further comprises: receiving model management condition information sent by the network device; and performing a management operation on the AI / ML model in a case where a condition corresponding to the model management condition information is met. The management operation comprises one or more of the following operations: Enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

22. The method of claim 21, wherein, The model management condition information comprises one or more of the following information: A speed threshold of the terminal device, a location change threshold of the terminal device, a downlink measurement result threshold of the terminal device, a communication scenario, and a ratio threshold between the first measurement data and the second measurement data.

23. The method of claim 21 or 22, wherein, The method further comprises: Reporting an operation result of the management operation to the network device.

24. The method of any one of claims 1 to 20, wherein, The second measurement data is generated by an AI / ML model, and the method further comprises: reporting model management information to the network device, the model management information being used by the network device to perform a management operation on the AI / ML model; and receiving an operation result of the management operation sent by the network device; The management operation comprises one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

25. The method of claim 24, wherein, The method further comprises: Receiving management information reporting condition information configured by the network device; The reporting of the model management information to the network device comprises: Reporting the model management information to the network device in a case where a condition corresponding to the management information reporting condition information is met.

26. The method of claim 25, wherein, The management information reporting condition information comprises one or more of the following: a speed threshold of the terminal device; a position change threshold of the terminal device; a downlink measurement result threshold of the terminal device; a communication scenario; and a proportion threshold between the first measurement data and the second measurement data.

27. The method of any one of claims 24 to 26, wherein, The model management information comprises one or more of the following: a downlink measurement result of the terminal device on a current cell and / or a neighboring cell; speed information of the terminal device; position information of the terminal device; a communication scenario corresponding to the terminal device.

28. The method of any one of claims 24 to 27, wherein, The receiving of the operation result of the management operation sent by the network device comprises: receiving the operation result of the management operation sent by the network device through a broadcast message; or, receiving the operation result of the management operation sent by the network device through a unicast message.

29. The method of claim 28, wherein, The unicast message comprises one or more of the following: a dedicated radio resource control (RRC) message; a reconfiguration message; an RRC release message.

30. The method of any one of claims 1 to 29, wherein, The intensive degree of distribution of the second measurement data in the time domain is associated with an interval between a time corresponding to the second measurement data and a time when the terminal device accesses the network device.

31. The method of claim 30, wherein, The intensive degree of distribution of the second measurement data in the time domain is inversely related to an interval between a time corresponding to the second measurement data and a time when the terminal device accesses the network device.

32. A method of wireless communication, the method comprising: The method is performed by a network device, and the method comprises: sending a first measurement configuration to a terminal device; the first measurement configuration is used to instruct the terminal device to measure to obtain first measurement data in an idle state or an inactive state; and the first measurement data is used to generate second measurement data.

33. The method of claim 32, wherein, The first measurement configuration comprises one or more of the following configurations: frequency domain information of measurement, and time interval of measurement.

34. The method of claim 32 or 33, wherein, The first measurement configuration further comprises: first data amount configuration information used to indicate a data amount of the first measurement data and a data amount of the second measurement data.

35. The method of claim 34, wherein, The first data amount configuration information comprises one or more of the following information: first proportion information used to indicate a proportional relationship between the data amount of the first measurement data and the data amount of the second measurement data; and first resource saving information used to indicate resources saved by the terminal device in the case of generating the second measurement data from the first measurement data.

36. The method of claim 35, wherein, The resources saved by the terminal device comprise one or more of the following information: energy consumption saved by the terminal device; memory resources saved by the terminal device; and signaling overhead saved by the terminal device.

37. The method of any one of claims 32 to 36, wherein, The method further comprises: receiving the first measurement data reported by the terminal device; generating the second measurement data according to the first measurement data.

38. The method of claim 37, wherein, The method further comprises: receiving auxiliary information reported by the terminal device; wherein the auxiliary information is information used to assist in generating the second measurement data; The generating of the second measurement data according to the first measurement data comprises: generating the second measurement data according to the first measurement data and auxiliary information.

39. The method of claim 38, wherein, The assistance information comprises one or more of the following: mobility state information, indicating a mobility state of the terminal device; and scenario information, indicating a communication scenario of the terminal device.

40. The method of claim 39, wherein, The mobility state information comprises one or more of the following: speed information; position information; and path information.

41. The method of claim 39 or 40, wherein, The mobility state information is determined by one or more of the following: reference signal received power (RSRP) measured by the terminal device; information of an application program in the terminal device; sensor information of the terminal device; and positioning information of the terminal device.

42. The method of any one of claims 32 to 41, wherein, The second measurement data is generated by an artificial intelligence (AI) / machine learning (ML) model, and the method further comprises: sending, to the terminal device, second measurement configuration; the second measurement configuration is used to instruct the terminal device to measure measurement data samples according to the second measurement configuration; and the measurement data samples are used to train the AI / ML model.

43. The method of claim 42, wherein, The second measurement configuration comprises one or more of the following: frequency domain information of measurement, and time interval of measurement.

44. The method of claim 43, wherein, The second measurement configuration further comprises: second data quantity configuration information, used to indicate data quantities of first measurement data samples and second measurement data samples in the measurement data samples; the first measurement data samples are data input into the AI / ML model in a training process of the AI / ML model; and the second measurement data samples are actual measurement data corresponding to a training prediction result, which is an output result predicted by the AI / ML model according to the first measurement data samples.

45. The method of claim 44, wherein, The second data quantity configuration information comprises one or more of the following: second ratio information, used to indicate a ratio relationship between the data quantity of the first measurement data samples and the data quantity of the second measurement data samples; and second resource saving information, used to indicate resources saved by the terminal device in a case where the second measurement data samples are generated by using the first measurement data samples. The method further comprises:

46. The method of any one of claims 42 to 45, wherein, receiving the measurement data samples reported by the terminal device; and training the AI / ML model according to the measurement data samples. The method further comprises:

47. The method of claim 46, wherein, receiving assistance information samples reported by the terminal device; and The training of the AI / ML model according to the measurement data samples comprises: training the AI / ML model according to the measurement data samples and the assistance information samples. The second measurement data is generated by the AI / ML model, and the method further comprises: sending, to the terminal device, model management condition information; the model management condition information is used to indicate a condition for the terminal device to perform a management operation on the AI / ML model; 48. The method of any one of claims 32 to 47, wherein, The management operation comprises one or more of the following: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model. The model management condition information comprises one or more of the following:

49. The method of claim 48, wherein, ​ a speed threshold of the terminal device, a location change threshold of the terminal device, a downlink measurement result threshold of the terminal device, a communication scenario, and a ratio threshold between the first measurement data and the second measurement data.

50. The method of claim 48 or 49, wherein, The method further includes: receiving an operation result of the management operation reported by the terminal device.

51. The method of any one of claims 32 to 47, wherein, The second measurement data is generated by an AI / ML model, and the method further includes: receiving model management information reported by the terminal device; performing a management operation on the AI / ML model according to the model management information; sending an operation result of the management operation to the terminal device; The management operation includes one or more of the following operations: enabling the AI / ML model, switching the AI / ML model, and disabling the AI / ML model.

52. The method of claim 51, wherein, The method further includes: configuring management information reporting condition information to the terminal device; the management information reporting condition information is used to indicate a condition for the terminal device to report the model management information to the network device. The management information reporting condition information includes one or more of the following information: a speed threshold of the terminal device, a location change threshold of the terminal device, a downlink measurement result threshold of the terminal device, a communication scenario, and a ratio threshold between the first measurement data and the second measurement data.

53. The method of claim 52, wherein, The model management information includes one or more of the following information: a downlink measurement result of the terminal device on a current cell and / or a neighboring cell, speed information of the terminal device, location information of the terminal device, and a communication scenario corresponding to the terminal device.

54. The method of any one of claims 51 to 53, wherein, The sending of the operation result of the management operation to the terminal device includes:

55. The method of any one of claims 51 to 54, wherein, sending the operation result of the management operation to the terminal device through a broadcast message; or, sending the operation result of the management operation to the terminal device through a unicast message. The unicast message includes one or more of the following ways:

56. The method of claim 55, wherein, a dedicated radio resource control (RRC) message, a reconfiguration message, and an RRC release message. The density of distribution of the second measurement data in the time domain is associated with an interval between a time corresponding to the second measurement data and a time when the terminal device accesses the network device.

57. The method of any one of claims 32 to 56, wherein, The density of distribution of the second measurement data in the time domain is inversely related to an interval between a time corresponding to the second measurement data and a time when the terminal device accesses the network device.

58. The method of claim 57, wherein, The apparatus includes:

59. A wireless communication apparatus, characterized by: a receiving module configured to receive a first measurement configuration sent by a network device; a measuring module configured to measure first measurement data in an idle state or an inactive state according to the first measurement configuration; the first measurement data is used to generate second measurement data. The apparatus includes:

60. A wireless communication apparatus, characterized by: a sending module configured to send a first measurement configuration to a terminal device; the first measurement configuration is used to instruct the terminal device to measure first measurement data in an idle state or an inactive state; the first measurement data is used to generate second measurement data. The terminal device includes a processor, a memory, and a transceiver; 61. A communications device, characterized by ​ The memory stores a computer program, and the processor executes the computer program, so that the communication device implements the wireless communication method according to any one of claims 1 to 58.

62. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is used for being executed by the processor of the communication device, so that the communication device implements the wireless communication method according to any one of claims 1 to 58.

63. A chip, comprising: The chip includes an integrated circuit and a firmware arranged in the integrated circuit, and the chip is used for running in the communication device, so that the communication device executes the wireless communication method according to any one of claims 1 to 58.

64. A computer program product, characterised in that, The computer program product includes computer instructions stored in a computer readable storage medium; the processor of the communication device reads the computer instructions from the computer readable storage medium and executes the computer instructions, so that the communication device executes the wireless communication method according to any one of claims 1 to 58.

65. A computer program characterised in that, The computer program is executed by the processor of the communication device, so that the communication device implements the wireless communication method according to any one of claims 1 to 58.

Images