Wireless measurement method, cell reselection method, devices and storage medium

Abstract

A wireless measurement method, a cell reselection method, devices, and a storage medium, relating to the technical field of communications. The wireless measurement method comprises: on the basis of an AI model, determining related information of wireless measurement relaxation (520). The wireless measurement method uses an AI model to perform inference prediction on wireless measurement, so as to directly obtain related information of wireless measurement relaxation, thereby effectively reducing the complexity of determining relaxed wireless measurement by terminal devices, saving energy consumption of terminal devices, and effectively ensuring the accuracy of wireless measurement.

Description

Wireless measurement methods, cell reselection methods, equipment and storage media Technical Field

[0001] This application relates to the field of communication technology, and in particular to a wireless measurement method, a cell reselection method, a device, and a storage medium. Background Technology

[0002] Terminal devices can perform wireless measurements on the serving cell and neighboring cells, and report the measurement results to network devices so that network devices can optimize the allocation of wireless resources and cell handover for terminal devices.

[0003] To reduce power consumption caused by continuous wireless measurements by terminal devices, network devices are equipped with a series of judgment criteria to help terminal devices determine when to perform wireless measurements.

[0004] However, evaluating wireless measurements based on multiple criteria is quite complex. Summary of the Invention

[0005] This application provides a wireless measurement method, a cell reselection method, a device, and a storage medium. The technical solutions provided by this application are as follows.

[0006] According to one aspect of the embodiments of this application, a wireless measurement method is provided, the method being executed by a terminal device, the method comprising:

[0007] Based on the AI ​​(Artificial Intelligence) model, relevant information for wireless measurement of relaxation is determined.

[0008] According to one aspect of the embodiments of this application, a cell reselection method is provided, the method being executed by a terminal device, the method comprising:

[0009] Based on the AI ​​model, the target cell for reselection is determined.

[0010] According to one aspect of the embodiments of this application, a terminal device is provided, the terminal device comprising:

[0011] The processing module is used to determine relevant information for wirelessly measuring relaxation based on an AI model.

[0012] According to one aspect of the embodiments of this application, a terminal device is provided, the terminal device comprising:

[0013] The processing module is used to determine the target cell for reselection based on an AI model.

[0014] According to one aspect of the embodiments of this application, a terminal device is provided, the terminal device including a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the above-described wireless measurement method and / or cell reselection method.

[0015] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for execution by a processor to implement the above-described wireless measurement method and / or cell reselection method.

[0016] According to one aspect of the embodiments of this application, a chip is provided, the chip including programmable logic circuits and / or program instructions, which, when the chip is running, are used to implement the above-described wireless measurement method and / or cell reselection method.

[0017] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium, wherein a processor reads from the computer-readable storage medium and executes the computer instructions to implement the above-described wireless measurement method and / or cell reselection method.

[0018] The technical solutions provided in this application embodiment may have the following beneficial effects:

[0019] By using AI models to infer and predict wireless measurements, relevant information on wireless measurement relaxation can be directly obtained, effectively reducing the complexity of determining the relaxation of wireless measurements by terminal devices. This saves energy consumption of terminal devices and effectively ensures the accuracy of wireless measurements.

[0020] By using AI models to infer and predict cell reselection, the target cell to which the device will be reselected can be directly obtained. This effectively reduces the complexity of cell reselection for terminal devices, and also improves the success rate of random access and reduces the latency of random access. Attached Figure Description

[0021] Figure 1 is a schematic diagram of a network architecture provided in one embodiment of this application;

[0022] Figure 2 is a schematic diagram of the working principle of LP-WUS provided in an embodiment of this application;

[0023] Figure 3 is a schematic diagram of target cell selection provided in an embodiment of this application;

[0024] Figure 4 is a schematic diagram of the functional framework of an AI / ML (Machine Learning) model provided in an embodiment of this application;

[0025] Figure 5 is a flowchart of a wireless measurement method provided in an embodiment of this application;

[0026] Figure 6 is a flowchart of a wireless measurement method provided in another embodiment of this application;

[0027] Figure 7 is a flowchart of a wireless measurement method provided in another embodiment of this application;

[0028] Figure 8 is a flowchart of a cell reselection method provided in an embodiment of this application;

[0029] Figure 9 is a flowchart of a cell reselection method provided in another embodiment of this application;

[0030] Figure 10 is a flowchart of a cell reselection method provided in another embodiment of this application;

[0031] Figure 11 is a block diagram of a terminal device provided in an embodiment of this application;

[0032] Figure 12 is a block diagram of a terminal device provided in another embodiment of this application;

[0033] Figure 13 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0035] The technical solutions of this application embodiment can be applied to various communication systems, such as: Global System for Mobile Communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, evolution of NR system, LTE-based access to unlicensed spectrum (LTE-U) system, NR-based access to unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), and Wireless Fidelity (WF). Fidelity (WiFi), 5th-Generation (5G) systems, B5G (Beyound 5G) systems, 6th-Generation (6G) systems, or other communication systems.

[0036] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0037] The communication system in this application embodiment can be applied to carrier aggregation (CA) scenarios, dual connectivity (DC) scenarios, and standalone (SA) network deployment scenarios.

[0038] The communication system in this application embodiment can be applied to unlicensed spectrum, wherein unlicensed spectrum can also be considered as shared spectrum; or, the communication system in this application embodiment can also be applied to licensed spectrum, wherein licensed spectrum can also be considered as non-shared spectrum.

[0039] The embodiments of this application can be applied to both non-terrestrial networks (NTN) and terrestrial networks (TN). NTN typically uses satellite communication to provide communication services to terrestrial users. Currently, NTN systems include NR-NTN and IoT-NTN systems, and other NTN systems may be included in the future.

[0040] Please refer to Figure 1, which shows a schematic diagram of a network architecture 100 provided in one embodiment of this application. The network architecture 100 may include: a terminal device 10, an access network device 20, and a core network element 30.

[0041] Terminal device 10 can refer to UE (User Equipment), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, wireless communication device, user agent, or user equipment. In some embodiments, terminal device 10 can also be a cellular phone, cordless phone, SIP (Session Initiation Protocol) phone, WLL (Wireless Local Loop) station, PDA (Personal Digital Assistant), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, vehicle-mounted device, wearable device, terminal device in 5GS (5th Generation System), or terminal device in the future evolved PLMN (Public Land Mobile Network), etc., and this application embodiment is not limited thereto. For ease of description, the devices mentioned above are collectively referred to as terminal devices. The number of terminal devices 10 is usually multiple, and one or more terminal devices 10 can be distributed within the cell managed by each access network device 20. Terminal equipment can also be simply referred to as terminal or UE, the meaning of which can be understood by those skilled in the art.

[0042] Access network device 20 is a device deployed in an access network to provide wireless communication functionality to terminal device 10. Access network device 20 may include various forms of macro base stations, micro base stations, relay stations, access points, etc. In systems employing different wireless access technologies, the name of the device with access network device functionality may differ; for example, in a 5G NR system, it is called gNodeB or gNB. As communication technologies evolve, the name "access network device" may change. For ease of description, in this embodiment, the aforementioned devices providing wireless communication functionality to terminal device 10 are collectively referred to as access network devices. In some embodiments, a communication relationship can be established between terminal device 10 and core network element 30 through access network device 20. For example, in an LTE (Long Term Evolution) system, access network device 20 may be one or more eNodeBs in an EUTRAN (Evolved Universal Terrestrial Radio Access Network) or EUTRAN; in a 5G NR system, access network device 20 may be one or more gNBs in a RAN (Radio Access Network). In the embodiments of this application, unless otherwise specified, the term "network device" refers to access network device 20, such as a base station.

[0043] Core network element 30 is a network element deployed in the core network. Its main functions are to provide user connectivity, manage users, and bear services, serving as an interface to external networks. For example, core network elements in a 5G NR system may include AMF (Access and Mobility Management Function) entities, UPF (User Plane Function) entities, and SMF (Session Management Function) entities.

[0044] In some embodiments, the access network device 20 and the core network element 30 communicate with each other via some air interface technology, such as the NG interface in a 5G NR system. The access network device 20 and the terminal device 10 communicate with each other via some air interface technology, such as the Uu interface.

[0045] The "5G NR system" in this application embodiment can also be referred to as a 5G system or an NR system, but those skilled in the art will understand its meaning. The technical solutions described in this application embodiment can be applied to LTE systems, 5G NR systems, and subsequent evolution systems of 5G NR systems (such as B5G (Beyond 5G, a fifth-generation mobile communication technology) systems, 6G systems (6th Generation System, a sixth-generation mobile communication system)), and other communication systems such as NB-IoT (Narrow Band Internet of Things) systems. This application does not limit these applications.

[0046] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) on the carrier used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0047] Before introducing the technical solution of this application, some related technical knowledge involved in this application will be introduced and explained. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0048] Currently, with people's pursuit of speed, latency, high-speed mobility, and energy efficiency, as well as the diversity and complexity of services in future life, the 3GPP (3rd Generation Partnership Project) international standards organization has begun to develop 5G. The main application scenarios of 5G are: Enhanced Mobile Broadband (eMBB), Ultra Reliable Low Latency Communications (URLLC), and Massive Machine Type Communication (mMTC).

[0049] eMBB still aims to provide users with multimedia content, services, and data, and its demand is growing rapidly. On the other hand, because eMBB may be deployed in different scenarios, such as indoors, urban areas, and rural areas, its capabilities and needs vary considerably. Therefore, generalizations cannot be made; a detailed analysis based on the specific deployment scenario is necessary. Typical applications of URLLC include industrial automation, power automation, remote medical operations (surgery), and traffic safety assurance. Typical characteristics of mMTC include high connection density, small data volume, latency-insensitive services, low module cost, and long lifespan.

[0050] NR can also be deployed independently. In 5G network environments, to reduce air interface signaling and quickly restore radio connections, thereby achieving the goal of rapidly restoring data services, a new RRC (Radio Resource Control) state is defined, namely the RRC_INACTIVE state. This state is different from the RRC_IDLE and RRC_CONNECTED states.

[0051] RRC_IDLE: RRC idle state. Mobility is based on UE-based cell selection and reselection. Paging is initiated by the CN (Core Network), and the paging area is configured by the CN. There is no UE AS (Access Stratum) context on the base station side. There is no RRC connection.

[0052] RRC_CONNECTED: RRC connected state. An RRC connection exists, and the base station and UE share a UE AS context. The network side knows the UE's location at the cell level. Mobility is controlled by the network side. Unicast data can be transmitted between the UE and the base station.

[0053] RRC_INACTIVE: RRC inactive state. Mobility is based on UE cell selection and reselection, there is a connection between CN and NR, the UE AS context exists on a certain base station, paging is triggered by RAN (Radio Access Network), the RAN-based paging area is managed by RAN, and the network side knows the UE's location at the RAN-based paging area level.

[0054] I. RRM Measurement of NR UE

[0055] Terminal devices in both RRC connected and disconnected states need to perform RRM measurements on the serving cell and other neighboring cells based on network configuration to support mobility operations, such as handover in RRC connected state, cell reselection in RRC idle state or RRC inactive state, etc.

[0056] The UE's measurements of the serving cell are ongoing.

[0057] For energy-saving considerations of terminal equipment, for UEs with RRC_IDLE or RRC_INACTIVE, when the UE has a good quality channel in the serving cell, the UE may not initiate RRM measurements for neighboring cells with the same frequency or with the same or lower priority but different frequency / technology frequencies. For high-priority different frequency / technology frequencies, relaxed RRM measurements can be performed. Specifically:

[0058] For the same frequency point, if the Srxlev (Serving cell Received Signal Level) measured by the serving cell is higher than S... IntraSearchP Furthermore, Squal (Serving cell Received Signal Quality) is higher than S IntraSearchQ Then the UE can disable measurements for all co-frequency neighboring cells.

[0059] For low-priority or equal-priority NR inter-frequency or inter-technology frequency points, if the Srxlev measured by the serving cell is higher than S... nonIntraSearchP And Squal is higher than S nonIntraSearchQ Then the UE can disable the measurement of all low-priority or equal-priority NR inter-frequency points or inter-technology points.

[0060] For high-priority NR inter-frequency or inter-technology frequency points, if the Srxlev measured by the serving cell is higher than S... nonIntraSearchP And Squal is higher than S nonIntraSearchQ Then the UE can perform relaxed measurements for high-priority NR frequency points or different technology frequency points. In this case, for each high-priority frequency point, the measurement interval relaxation is Thigher_priority_search = (60*N) / (60*N). layers )s, where N layers This represents the number of high-priority frequencies for network broadcasting.

[0061] Wherein, parameter S IntraSearchP S IntraSearchQ S nonIntraSearchP and S nonIntraSearchQ Configuration is performed via the network through SIB2 (System Information Block).

[0062] For UEs in RRC connected state, the base station can configure s-measure criteria for the UE through UE-specific RRC signaling. When the UE meets the s-measure criteria (i.e., the RSRP (Reference Signal Received Power) of the UE on the PCell (Primary Cell) is higher than a certain threshold), the UE can avoid performing RRM measurements for neighboring cells, thereby achieving the purpose of energy saving for terminal equipment.

[0063] II. Relaxation of RRM Measurement for Disconnected UEs

[0064] Release 16 introduces a neighboring cell measurement relaxation mechanism for non-connected UEs to further meet the power saving needs of terminal devices.

[0065] To support relaxed neighbor cell measurements, the low mobility criterion and the not-at-cell-edge criterion are introduced. Both criteria are based on measurements of the UE on the serving cell. The definitions of the low mobility criterion and the not-at-cell-edge criterion in the standard are as follows:

[0066] 1. The "low mobility" principle

[0067] According to this guideline, network devices will be configured to evaluate RSRP changes for a duration T. SearchDeltaP and RSRP change threshold S SearchDeltaP When a period of time T SearchDeltaP The change in RSRP of the internal UE on the serving cell is less than S SearchDeltaP If the UE is considered to meet the "low mobility" criterion during a given time period T, then the UE is considered to satisfy the criterion. That is, during a given time period T... SearchDeltaP Within, it satisfies: (SrxlevRef–Srxlev) SearchDeltaP (1)

[0068] Wherein, Srxlev is the current Srxlev measurement value of the serving cell, and SrxlevRef is the reference Srxlev value of the serving cell.

[0069] When the UE selects or reselects to a new cell; or...

[0070] If (Srxlev-SrxlevRef)>0; or,

[0071] If the UE is not in the continuous T SearchDeltaP The formula (1) is satisfied within the time limit:

[0072] ​The UE sets SrxlevRef to the current Srxlev measurement value of the serving cell;

[0073] After completing cell selection / reselection, the UE needs to wait for at least a certain period of time T. SearchDeltaP Perform normal RRM measurements internally.

[0074] 2. The "not-at-cell-edge" rule

[0075] In accordance with this guideline, network devices will be configured with an RSRP threshold S. SearchThresholdP Additionally, an RSRQ (Reference Signal Received Quality) threshold S can be configured. SearchThresholdQ If the RSRP of the UE on the serving cell is greater than the RSRP threshold, and the RSRQ of the UE on the serving cell is greater than the RSRQ threshold when the network is configured with an RSRQ threshold, then the UE is considered to meet the "not-at-cell-edge" criterion.

[0076] The network device notifies the UE via system broadcast whether the RRM measurement relaxation function can be enabled. When enabling the RRM measurement relaxation function, the network device needs to configure at least one RRM measurement relaxation criterion. Depending on the configuration, there may be four scenarios.

[0077] Case 1: If the network device is only configured with the low mobility criterion, then when the UE meets the low mobility criterion, the UE will initiate relaxed RRM measurement for neighboring cells.

[0078] Case 2: If the network device is only configured with the not-at-cell-edge criterion, then when the UE meets the not-at-cell-edge criterion, the UE performs relaxed RRM measurement for neighboring cells.

[0079] Case 3: The network device is configured with both the low mobility criterion and the not-at-cell-edge criterion, and the network device is not configured with the parameter combineRelaxedMeasCondition. In this case, when the UE meets at least one of these two criteria, the UE initiates relaxed RRM measurement for the neighboring cell.

[0080] Case 4: The network device is configured with both the low mobility criterion and the not-at-cell-edge criterion, and the network is configured with the parameter combineRelaxedMeasCondition. In this case, when the UE meets both criteria, the UE initiates relaxed RRM measurement for neighboring cells.

[0081] The following two RRM measurement relaxation methods are defined for non-connected UEs:

[0082] Method 1: When the UE only meets the low mobility criterion or the not-at-cell-edge criterion, for same-frequency measurement, NR inter-frequency measurement and inter-technology inter-frequency measurement, the measurement interval is relaxed to 3 times the normal measurement interval.

[0083] Method 2: When the UE simultaneously meets the low mobility criterion and the not-at-cell-edge criterion, the measurement interval can be relaxed to 1 hour for intra-frequency measurement, NR inter-frequency measurement, and inter-technology inter-frequency measurement.

[0084] Furthermore, for high-priority frequencies, `highPriorityMeasRelax` is introduced. This parameter indicates whether the network device allows the UE to relax the measurement interval for high-priority frequencies to a value exceeding `Thigher_priority_search` (except when the UE simultaneously meets the low mobility criterion and the not-at-cell-edge criterion). In other words, `highPriorityMeasRelax` is only used to control the network device when it is configured with the low mobility criterion, the UE meets the low mobility criterion, and the UE's measurement results in the serving cell satisfy `Srxlev` greater than `SnonIntraSearchP` and `Squal` greater than `SnonIntraSearchQ`. In this case, if the network device is configured with `highPriorityMeasRelax`, the UE's measurement interval for high-priority frequencies can be relaxed to `K2*Thigher_priority_search`, where `K2` is 60; otherwise (if the network device is not configured with `highPriorityMeasRelax`), the UE's measurement interval for high-priority frequencies is `Thigher_priority_search`.

[0085] III. Relaxation of RedCap UE's RRM Measurement

[0086] The main focus is on relaxing the RRM measurement of RedCap (Reduced Capability) stationary terminal devices. To this end, the stationary criterion is introduced, which is exactly the same as the method for judging low mobility mentioned above.

[0087] For connected UEs, the network device configures the stationary criterion via broadcast messages. When the network device configures both the low mobility criterion and the stationary criterion, the network sets different thresholds for these two criteria. Furthermore, if the network device needs to configure RRM relaxation criteria for connected UEs, the stationary criterion is mandatory, while the aforementioned not celledge criterion is optional.

[0088] For connected UEs, network devices configure RRM measurement relaxation criteria (i.e., stationary criteria) via UE-specific RRC signaling. When a UE first meets the RRM measurement relaxation criteria based on an assessment, or when the UE's status regarding whether it meets the RRM measurement relaxation criteria changes, the UE informs the network whether it meets the RRM measurement relaxation criteria through UE auxiliary information reporting. How to relax RRM measurements subsequently depends entirely on the base station implementation (e.g., the base station can delete some measurement frequencies for the UE), and there are no specifications in the standard.

[0089] IV. LP-WUR (Low-Power Wake-Up Receiver) / LP-WUS (Low-Power Wake-Up Signal) Projects

[0090] LP-WUS was introduced in related technologies. LP-WUS uses a lower-power receiver for reception, meaning it does not use a master receiver. As shown in sub-figures (a) and (b) of Figure 2, after a non-connected UE receives LP-WUS, it activates the master receiver to listen for paging messages, thus achieving energy saving. After a connected UE receives LP-WUS, it wakes up the master receiver to listen for PDCCH (Physical Downlink Control Channel).

[0091] Currently, the primary tasks of a UE in RRC_IDLE or RRC_INACTIVE mode are listening for paging and performing RRM measurements. The introduction of LP-WUS eliminates the need for the UE to listen for paging at every PO (Paging Occasion). However, based on the standard-defined measurement requirements for disconnected UEs, the UE still needs to wake up at every DRX (Discontinuous Reception) cycle to perform serving cell measurements. Frequently activating the primary receiver will significantly reduce the UE's energy efficiency. To enable the UE's primary receiver to remain off or in deep sleep for longer periods without impacting UE mobility, the design goal for the low-power receiver is ultimately defined as: the low-power receiver must be capable of measuring the serving cell. Based on current standardization progress, communication systems include the following two scenarios to mitigate the RRM measurement burden on the primary receiver:

[0092] Case 1: The UE's primary receiver does not perform measurements for the serving cell or for neighboring cells. Measurements for the serving cell are completely offloaded from the primary receiver to the low-power receiver.

[0093] Case 2: The UE's primary receiver performs relaxed RRM measurements on the serving cell and neighboring cells. The UE's low-power receiver also performs measurements on the serving cell.

[0094] Regarding the criterion of serving cell offloading in Case 1 (i.e., the MR (Main Receiver) does not perform serving cell measurements), the following conclusion can be drawn:

[0095] 1. The entry condition for serving cell offloading is defined as follows: at least the RSRP measured on the serving cell by MR is higher than a certain RSRP threshold, and the measurement results on LR (Low-Power Receiver) can also be considered.

[0096] 2. The departure conditions for serving cell offloading are based on LR measurements.

[0097] V. Re-election of Community

[0098] Cell reselection refers to the process by which a UE, in idle mode, monitors the signal quality of neighboring cells and the current cell to select the best cell to provide service signals. When the signal quality and level of a neighboring cell meet the S criterion and a certain reselection decision criterion (R criterion), the terminal device will connect to and camp on that cell.

[0099] After the UE successfully camps, it will continue to perform measurements in this cell. The RRC layer calculates Srxlev (S criterion) based on the RSRP measurement results and compares it with S. Intrasearch (Same-frequency measurement start threshold) and S nonintrasearch The comparison of (inter-frequency / inter-system measurement start threshold) serves as the criterion for deciding whether to start neighbor cell measurements.

[0100] Measurement configuration

[0101] - Configure per-frequency SMTC (Synchronization Signal / Physical Broadcast Channel Block Measurement Timing Configuration) to assist UE measurements for both Intra-frequency (same-frequency measurement) and inter-frequency (different-frequency measurement) measurements, thereby achieving UE power saving.

[0102] • Acquisition of cell signal quality

[0103] - The system broadcasts parameters N and thresholds per frequency to select the best beam.

[0104] - The signal quality of the best top N beams that meet the threshold is linearly averaged.

[0105] -If there is no parameter N and threshold for broadcast per frequency, then the signal quality of the best beam in the cell is the cell signal quality.

[0106] • Target cell selection (R criterion)

[0107] - The candidate cells are controlled by rangeToBestCell, that is, among all candidate cells within the rangeToBestCell of the signal quality difference from the best cell, the cell with the most beams that meet the threshold is selected as the target cell. R s =Q meas,s +Q hyst -Q offsettemp R n =Q meas,n -Q offset –Q offsettemp

[0108] Figure 3 illustrates a target cell selection method according to an embodiment of this application. Within a range configured by the network in dB, the highest cell quality includes cell 1, cell 2, and cell 3. Cell 1 includes z beams with good signal quality, cell 2 includes x beams with good signal quality, and cell 3 includes y beams with good signal quality. The cell with the most beams of good signal quality from cell 1, cell 2, and cell 3 is selected as the target cell.

[0109] • Frequency Priority: To achieve load balancing across different frequency points, the network side can set different priorities for each frequency. UEs preferentially camp on higher-priority frequencies. Frequency priority can be obtained from system broadcasts, dedicated signaling (RRC Release), or inherited from other RATs (Radio Access Technologies).

[0110] Priority Configuration: Both cell reselection priority and sub-priority are used to jointly indicate the final cell reselection frequency priority; cell reselection priority ranges from 0 to 7, and sub-priority ranges from {0.2, 0.4, 0.6, 0.8}, indicating a total of 40 frequency priorities. Sub-priority is only used for NR and LTE frequencies.

[0111] • Dedicated priority configuration release conditions: state transition, PLMN (Public Land Mobile Network) selection, timer timeout triggering dedicated priority configuration.

[0112] • Priority usage:

[0113] - If there is a dedicated configuration, there is no need to broadcast the configuration.

[0114] - Reside in any cell status, configured via broadcast.

[0115] - If no priority is configured, it will default to the lowest priority.

[0116] - Frequency priorities will not be configured between RATs.

[0117] All parameters related to UE measurement behavior constraints in the IDLE state are derived from system broadcast messages. The following assumes that all relevant parameters are configured. If not configured, the relevant constraints do not exist.

[0118] 1. For the initiation of co-frequency measurement, when the serving cell Srxlev > S IntraSearchP Moreover, the service area Squal>S IntraSearchQ If the frequency is not specified, then neighboring cell measurement is not initiated; otherwise, neighboring cell measurement is initiated. Wherein, S IntraSearchP and S IntraSearchQ It is a preset threshold for same-frequency measurements.

[0119] 2. For inter-frequency measurements of the same or lower priority, when the serving cell's Srxlev > S nonIntraSearchP Moreover, the service area Squal>S nonIntraSearchQ If the condition is met, then inter-frequency measurements of the same or lower priority will not be initiated; otherwise, they will be initiated. Wherein, S... nonIntraSearchP and S nonIntraSearchQ It is a preset threshold for cross-frequency measurements.

[0120] 3. For high-priority inter-frequency measurements, always initiate the measurement for that frequency.

[0121] Cell reselection behavior is based on the measurement results of neighboring cells.

[0122] 1. For cell reselection of cells with the same frequency and cells with the same priority but different frequencies, the R criterion (ordered according to RSRP) must be met. The signal quality of the new cell is better than that of the current cell and lasts for a specified duration. The UE stays in the original cell for no less than 1 second.

[0123] 2. For high-priority cells to perform reselection, the signal quality of the high-priority cell must be higher than a certain threshold and continue for a specified time, and the UE must remain in the original cell for no less than 1 second.

[0124] 3. For low-priority cells to perform reselection, there must be no high-priority cells, cells of the same priority must meet the requirements, the signal quality of the original cell must be below a certain threshold, the signal quality of the low-priority cell must be above a certain threshold and last for a certain period of time, and the UE must stay in the original cell for no less than 1 second.

[0125] VI. AI Model Framework

[0126] Figure 4 illustrates a schematic diagram of the functional framework of an AI / ML (Machine Learning) model provided in one embodiment of this application. After the model is trained and deployed, model inference can be performed. Model inference involves obtaining the model's output result after providing a specific model input, which is typically a prediction result. The AI / ML model performing model inference is periodically monitored and managed based on the monitoring results. Model management includes activating the model or switching to a better-performing model when its performance is poor or unsuitable. Data collection is unavoidable in model training, inference, and model management. Data collection can be performed in real time or based on storage (logging).

[0127] To save power consumption in terminal devices, various RRM measurement relaxation mechanisms have been introduced in different versions of NR evolution. Currently, the standard supports multiple different RRM measurement relaxation criteria, and the protocol also defines different RRM measurement relaxation requirements for different scenarios. On the one hand, the base station needs to configure various RRM measurement relaxation criteria; on the other hand, the UE also needs to evaluate these multiple measurement relaxation thresholds, which brings high complexity to the base station implementation and UE behavior.

[0128] For UEs in IDLE / INACTIVE state, cell reselection is performed based on the channel quality of the serving cell and neighboring cells, combined with the R criterion. Cell reselection only considers whether the UE's channel quality is good enough, but does not take into account the actual load of each cell. This may result in the UE reselecting to a cell with high load, causing access to fail during the initial access attempt. However, considering the impact of cell load in cell reselection would make the process more complex.

[0129] In 6G, simplifying the measurement relaxation mechanism and cell reselection mechanism to achieve power saving for terminal devices without affecting mobility management performance is one of the directions that 6G can explore.

[0130] Please refer to Figure 5, which shows a flowchart of a wireless measurement method provided in one embodiment of this application. This method can be applied to a terminal device in the network architecture shown in Figure 1. The method may include the following step 520.

[0131] Step 520: Based on the AI ​​model, determine relevant information for wirelessly measuring relaxation.

[0132] AI models have the ability to infer and predict wireless measurements through artificial intelligence or machine learning to determine relevant information about wireless measurement relaxation. In some embodiments, AI models are also referred to as AI / ML models. Wireless measurement refers to the process by which terminal devices or network devices evaluate the wireless network environment. In some embodiments, wireless measurement is used to achieve at least one of the following functions: resource scheduling, wireless resource management, network optimization, mobility management, etc. Other functions can also be achieved based on wireless measurement, which are not limited in this application embodiment.

[0133] Wireless measurement relaxation, also known as relaxed wireless measurement, refers to a wireless measurement that reduces its frequency or severity. In some embodiments, wireless measurement relaxation includes increasing the measurement interval of the wireless measurement. The measurement interval of a wireless measurement refers to the time interval between two consecutive wireless measurements. Information related to wireless measurement relaxation is used to indicate the frequency or severity of the wireless measurement relaxation and whether wireless measurement relaxation is performed. In some embodiments, the information related to wireless measurement relaxation includes at least one of the following: increased measurement interval, measurement relaxation factor, measurement relaxation indication, etc., and may also include other relevant information, which is not limited in this application embodiment. An increased measurement interval refers to the amount by which the measurement interval of the wireless measurement after relaxation is increased relative to the wireless measurement before relaxation. The measurement relaxation factor is used to indicate the degree of increase in the measurement interval of the wireless measurement relaxation relative to the normal wireless measurement. The measurement relaxation indication is used to indicate whether normal wireless measurement is performed or wireless measurement relaxation is performed. Normal wireless measurement refers to performing wireless measurement at a preset measurement interval. In some embodiments, the preset measurement interval is specified by network device configuration or related protocols.

[0134] In some embodiments, wireless measurements include at least two of the following types: RRM measurement, RLM (Radio Link Monitoring) measurement, and BFD (Beam Failure Detection) measurement.

[0135] RRM measurement refers to the process by which a terminal device measures the quality of reference signals transmitted on the spectrum resources of the serving cell and neighboring cells. In some embodiments, the measurement results of RRM measurement include, but are not limited to, at least one of the following: RSRP, RSRQ, RSSI (Received Signal Strength Indicator), SINR (Signal to Interference plus Noise Ratio), etc., and may also include other content related to RRM measurement, which is not limited in this application embodiment. In some embodiments, RRM measurement includes at least one of the following types: same-frequency measurement, different-frequency measurement, and different-technology measurement. For any one of the multiple serving carriers of the terminal device, same-frequency measurement refers to the terminal device measuring a cell on the same carrier frequency as the serving carrier. For any one of the multiple serving carriers of the terminal device, different-frequency measurement refers to the terminal device measuring a cell on a different carrier frequency than the serving carrier. For any one of the multiple serving carriers of the terminal device, different-technology measurement refers to the terminal device measuring a cell using a different Radio Access Technology (RAT) than the serving carrier. In some embodiments, the wireless access technology may include, but is not limited to, at least one of the following: LTE, 5G NR, 6G, B5G, WCDMA (Wideband Code Division Multiple Access), GSM (Global System for Mobile Communications), etc., and may also include other wireless access technologies, which are not limited in this application embodiment. RRM measurement for neighboring cells, also known as neighbor cell measurement, refers to the process of measuring cells adjacent to the serving cell.

[0136] In some embodiments, connected-state RRM measurements and disconnected-state RRM measurements correspond to the same AI model; or, connected-state RRM measurements and disconnected-state RRM measurements correspond to different AI models.

[0137] Connected-mode RRM measurement refers to RRM measurements performed when the terminal device is in a connected state. In some embodiments, connected state refers to RRC connected state. When the terminal device is in RRC connected state, it means that a communication connection has been established between the terminal device and the network device, enabling data transmission, signaling exchange, and radio resource allocation. Disconnected-mode RRM measurement refers to RRM measurements performed when the terminal device is in a disconnected state. In some embodiments, the terminal device is in a disconnected state. Disconnected state means that no active communication connection has been established with the network device. In some embodiments, the terminal device is in RCC idle state or RCC inactive state. When the terminal device is in a disconnected state, it means that a stable communication connection has not yet been established between the terminal device and the network device, and it cannot or can only perform some functions of data transmission, signaling exchange, and radio resource allocation.

[0138] When connected-state RRM measurements and disconnected-state RRM measurements correspond to the same AI model, the AI ​​model has the ability to infer and predict connected-state and disconnected-state RRM measurements.

[0139] When connected-state RRM measurements and disconnected-state RRM measurements correspond to different AI models, the AI ​​model corresponding to connected-state RRM measurements has the ability to infer and predict connected-state RRM measurements, while the AI ​​model corresponding to disconnected-state RRM measurements has the ability to infer and predict disconnected-state RRM measurements.

[0140] The above approach uses a single AI model to infer and predict RRM measurements in both connected and disconnected states. This allows terminal and network devices to maintain only one AI model for RRM measurements in different states, avoiding increased complexity caused by multiple AI model version updates. By using different AI models to infer and predict RRM measurements in both connected and disconnected states, and training corresponding AI models to meet the needs of RRM measurements in different states, the accuracy and generalization ability of the AI ​​models in different scenarios can be effectively improved.

[0141] RLM measurement refers to the process of monitoring the link quality of the downlink wireless link between a terminal device and a network device. In some embodiments, the measurement results of RLM measurement include at least one of the following: Bit Error Rate (BLER), Reference Signal Type, In-Sync Indicator (IS), Out-of-Sync Indicator (OoS), etc., and may also include other measurement results, which are not limited in this application embodiment. The Bit Error Rate is the ratio of the number of transmission errors in the received reference signal to the total number of transmissions. The Reference Signal Type is used to indicate the type of reference signal used to perform the RLM measurement. In some embodiments, the reference signal type used for RLM measurement includes SSB (Synchronization Signal Block) and CSI-RS (Channel State Information Reference Signal), and may also include other reference signals used for RLM measurement, which are not limited in this application embodiment. The In-Sync Indicator is used to indicate that the downlink wireless link between the terminal device and the network device is in a synchronized state. When the link quality of the downlink wireless link between the terminal device and the network device is higher than the synchronization threshold, the In-Sync Indicator is reported. In some embodiments, the synchronization threshold is specified by the network device configuration or related protocols, and this application embodiment does not limit this. A loss-of-synchronization state indication is used to indicate that the downlink radio link between the terminal device and the network device is in a loss-of-synchronization state. When the link quality of the downlink radio link between the terminal device and the network device is lower than a predefined loss-of-synchronization threshold, a loss-of-synchronization state indication is reported. In some embodiments, the loss-of-synchronization threshold is specified by the network device configuration or related protocols, and this application embodiment does not limit this.

[0142] BFD measurement is a mechanism for detecting downlink beam link quality by monitoring the currently used beam to determine whether beam failure has occurred. Optionally, beam failure includes severe signal attenuation or interruption. In some embodiments, the measurement results of BFD measurement include beam failure indication or candidate beam information, and may also include other measurement results, which are not limited in this application embodiment. Beam failure indication is used to indicate that the link quality of the currently serving beam cannot maintain reliable communication. Candidate beam information is used to indicate available candidate beams. In some embodiments, candidate beam information may include at least one of the following: candidate beam identification information, candidate beam signal quality parameters, reference signal type, etc., and may also include other information, which are not limited in this application embodiment. In some embodiments, the signal quality parameters of the candidate beam may be the candidate beam's RSRP or the candidate beam's RSRQ.

[0143] In some embodiments, input information is fed into an AI model, which then outputs corresponding output information. The input information is measurement data related to wireless measurement. The output information refers to information related to wireless measurement relaxation obtained through inference and prediction by the AI ​​model based on the input information.

[0144] In some embodiments, different types of wireless measurements correspond to the same AI model; or, different types of wireless measurements correspond to different AI models. In some embodiments, for the three different types of wireless measurements described above, the AI ​​models corresponding to the different types of wireless measurements include at least one of the following:

[0145] Scenario 1: RRM measurement, RLM measurement, and BDF measurement correspond to the same AI model. That is, this AI model has the ability to infer and predict the RRM, RLM, and BDF measurements. In some embodiments, the input information corresponding to the RRM, RLM, and BDF measurements is input into this AI model, and the AI ​​model outputs the respective output results for the RRM, RLM, and BDF measurements.

[0146] Scenario 2: RRM and RLM measurements correspond to the same AI model, while BDF measurements correspond to a different AI model. That is, the AI ​​models corresponding to RRM and RLM measurements have the ability to perform inference and prediction for RRM and RLM measurements, while the AI ​​model corresponding to BDF measurements only has the ability to perform inference and prediction for BDF measurements. In some embodiments, the input information corresponding to RRM and RLM measurements is input into the AI ​​models corresponding to RRM and RLM measurements, and the AI ​​models corresponding to RRM and RLM measurements output the corresponding output information; similarly, the input information corresponding to BDF measurements is input into the AI ​​model corresponding to BDF measurements, and the AI ​​model corresponding to BDF measurements outputs the corresponding output information.

[0147] Scenario 3: RRM and BDF measurements correspond to the same AI model, while RLM measurements correspond to a different AI model. That is, the AI ​​models corresponding to RRM and BDF measurements have the ability to perform inference and prediction for RRM and BDF measurements, while the AI ​​model corresponding to RLM measurements only has the ability to perform inference and prediction for RLM measurements. In some embodiments, the input information corresponding to RRM and BDF measurements is input into the AI ​​models corresponding to RRM and BDF measurements, and the AI ​​models corresponding to RRM and BDF measurements output the corresponding output information; the input information corresponding to RLM measurements is input into the AI ​​model corresponding to RLM measurements, and the AI ​​model corresponding to RLM measurements outputs the corresponding output information.

[0148] Scenario 4: RRM measurement corresponds to one AI model, while RLM measurement and BDF measurement correspond to another different AI model. That is, the AI ​​model corresponding to RRM measurement only has the ability to perform inference and prediction for RRM measurement, while the AI ​​models corresponding to RLM measurement and BDF measurement have the ability to perform inference and prediction for RLM measurement and BDF measurement respectively. In some embodiments, the input information corresponding to RRM measurement is input into the AI ​​model corresponding to RRM measurement, and the AI ​​model corresponding to RRM measurement outputs the output information corresponding to RRM measurement; the input information corresponding to RLM measurement and BDF measurement is input into the AI ​​models corresponding to RLM measurement and BDF measurement respectively, and the AI ​​models corresponding to RLM measurement and BDF measurement output the output information corresponding to RLM measurement and BDF measurement respectively.

[0149] Scenario 5: RRM measurement, RLM measurement, and BDF measurement each correspond to different AI models. That is, the AI ​​model corresponding to RRM measurement only has the ability to infer and predict RRM measurements, the AI ​​model corresponding to RLM measurement only has the ability to infer and predict RLM measurements, and the AI ​​model corresponding to BDF measurement only has the ability to infer and predict BDF measurements. In some embodiments, the input information corresponding to RRM measurement is input into the AI ​​model corresponding to RRM measurement, and the AI ​​model corresponding to RRM measurement outputs the corresponding RRM measurement output information; the input information corresponding to RLM measurement is input into the AI ​​model corresponding to RLM measurement, and the AI ​​model corresponding to RLM measurement outputs the corresponding RLM measurement output information; the input information corresponding to BDF measurement is input into the AI ​​model corresponding to BDF measurement, and the AI ​​model corresponding to BDF measurement outputs the corresponding BDF measurement output information.

[0150] In some embodiments, where different types of wireless measurements correspond to different AI models, the different AI models can be obtained by training models with the same or different model structures using training data corresponding to different types of wireless measurements. This application does not limit this.

[0151] In some embodiments, as shown in FIG6, step 510 is included before step 520.

[0152] Step 510: Receive the first information sent by the network device. The first information is used to determine the AI ​​model.

[0153] In some embodiments, the network device sends first information to the terminal device. Correspondingly, the terminal device receives the first information sent by the network device. In some embodiments, the network device trains an AI model based on training data from wireless measurements to obtain a trained AI model; the network device sends the first information to the terminal device, the first information being used to determine the trained AI model. The training samples used for AI training include data related to wireless measurements and sample labels. The data related to wireless measurements may include the input information of the AI ​​model described above.

[0154] In some embodiments, the first information includes at least one of the following: location information, model type, model parameters, AI model, etc., and may also include other information, which is not limited in this application embodiment. Location information is used to indicate the location where the AI ​​model is stored. Model parameters are used to define and influence the behavior of the AI ​​model. Optionally, model parameters may include trainable parameters and hyperparameters. In some embodiments, model parameters may be the model parameters of the initial deployment or the updated model parameters. The AI ​​model in the first information refers to the complete AI model. Updated model parameters are the model parameters of the AI ​​model after retraining and adjusting the AI ​​model based on new training samples.

[0155] In some embodiments, as shown in FIG7, step 530 is further included after step 520.

[0156] Step 530: Perform wireless measurement based on the relevant information of wireless measurement relaxation.

[0157] In some embodiments, wireless measurements are performed on the serving cell and neighboring cells based on information related to wireless measurement relaxation.

[0158] The technical solution provided in this application uses an AI model to perform inference and prediction on wireless measurements, directly obtaining relevant information on wireless measurement relaxation. This effectively reduces the complexity of the terminal device in determining the relaxation of wireless measurements, saving energy consumption of the terminal device while effectively ensuring the accuracy of wireless measurements.

[0159] The following describes the input information for the AI ​​model.

[0160] In some embodiments, the input information for the AI ​​model includes at least one of the following.

[0161] (1) Measurement results of terminal equipment in the serving cell.

[0162] The serving cell is the cell currently providing service to the terminal device. In some embodiments, the terminal device obtains measurement results for the serving cell by performing radio measurements on the serving cell. In some embodiments, the measurement results for the serving cell may include at least one of the following: measurement results of RRM measurement, measurement results of RLM measurement, and measurement results of BDF measurement, etc., and may also include measurement results of other radio measurements, which are not limited in this application embodiment.

[0163] In some embodiments, the measurement result of the terminal device in the serving cell is the measurement result obtained from the terminal device's most recent wireless measurement of the serving cell.

[0164] The above method allows the AI ​​model to understand the current signal strength, interference status, link quality, and other information in real time by using measurement results from the serving cell, thereby helping the AI ​​model determine whether to relax wireless measurement.

[0165] (2) Measurement results of the terminal equipment in neighboring cells.

[0166] A neighboring cell refers to a cell adjacent to the serving cell. In some embodiments, the frequency of the serving cell and the frequency of the neighboring cell may be the same or different. In some embodiments, the terminal device obtains measurement results for the neighboring cell by performing radio measurements on the neighboring cell. In some embodiments, the measurement results for the neighboring cell may include at least one of the following: measurement results of RRM measurement, measurement results of RLM measurement, and measurement results of BDF measurement, etc., and may also include measurement results of other radio measurements, which are not limited in this application embodiment.

[0167] In some embodiments, the measurement results of the terminal device in the neighboring cell are obtained from the most recent wireless measurement performed by the terminal device on the neighboring cell.

[0168] In some embodiments, the cells adjacent to the serving cell include multiple cells. In some embodiments, the number of measurement results of the terminal device in the neighboring cells is multiple. In other words, the input information includes the measurement results of the terminal device in multiple neighboring cells.

[0169] The above method, by inputting the measurement results of the terminal device in the neighboring cell into the AI ​​model, enables the AI ​​model to understand the signal quality of the neighboring cell. The AI ​​model can then assess possible signal switching or interference, thereby making a more accurate judgment.

[0170] (3) Measurement results of one or more receivers of the terminal equipment in the serving cell.

[0171] A receiver is a component in a terminal device used to receive wireless signals. In some embodiments, the terminal device includes at least two receivers. In some embodiments, the receivers are used to perform wireless measurements on a serving cell and / or neighboring cells. In some embodiments, for the at least two receivers of the terminal device, different receivers may obtain different measurement results when performing wireless measurements on the same cell. In some embodiments, different receivers may perform wireless measurements on different cells or on the same cell.

[0172] When the input information includes measurement results from a receiver of the terminal device in the serving cell, the receiver can be any receiver of the terminal device or a designated receiver. In some embodiments, the designated receiver is set by the network device or the terminal device, or depends on the implementation of the AI ​​model; this application embodiment does not limit this. In some embodiments, the designated receiver is the MR of the terminal device.

[0173] When the input information includes measurement results from multiple receivers of the terminal device in the serving cell, the multiple receivers may be some or all of the receivers of the terminal device. In some embodiments, the measurement results from the multiple receivers of the terminal device in the serving cell are the measurement results obtained from the most recent radio measurements performed by the multiple receivers for the neighboring cells.

[0174] The above method, by using measurement results from one or more receivers, can provide more accurate signal coverage and interference analysis, helping AI models to judge the effectiveness of different receivers in performing wireless measurements in the serving cell.

[0175] In some embodiments, the plurality of receivers includes a first receiver and a second receiver, wherein the power consumption of the first receiver is less than that of the second receiver.

[0176] In some embodiments, the first receiver and the second receiver are any two different receivers among the at least two receivers described above. In some embodiments, the terminal device has two receivers, including a first receiver and a second receiver. Both the first receiver and the second receiver have wireless measurement capabilities. In some embodiments, the first receiver performs wireless measurements on at least one cell. In some embodiments, the second receiver performs wireless measurements on at least one cell. In some embodiments, the at least one cell includes a serving cell and / or at least one neighboring cell.

[0177] In some embodiments, for at least two receivers included in a terminal device, the power consumption of different receivers differs. In some embodiments, the difference in power consumption of different receivers is related to at least one of the following factors: function, operating frequency band, operating mode, receiving antenna, etc., and may also be related to other factors, which are not limited in this application embodiment. The complexity of the receiver's function determines its processing capability and workload. For example, the first receiver is used to listen for the DRX wake-up signal to wake up the second receiver, which is used to listen for downlink signals. The signal characteristics of different frequency bands (such as frequency range and bandwidth) affect the signal amplification and processing requirements of the receiver. The receiver's operating mode determines its operation. For example, when the receiver is in continuous operating mode, its power consumption is higher. For example, when the receiver is in intermittent operating mode, its power consumption is lower. The second receiver supports complex signal processing, such as channel demodulation, multi-carrier aggregation, MIMO (Multiple Input Multiple Output), etc. The first receiver supports simple signal processing, such as assisting the second receiver in receiving signals, performing intermittent tasks, channel measurement, etc. A receiver's receiving antenna is used to capture electromagnetic waves and convert them into electrical signals. The better the performance of the receiver's receiving antenna, the less power the receiver consumes when processing wireless signals. Conversely, the worse the performance of the receiver's receiving antenna, the more power the receiver consumes when processing wireless signals.

[0178] In some embodiments, the first receiver is an LR and the second receiver is an MR.

[0179] For example, the second receiver is MR and the first receiver is LR. LR intermittently wakes up to listen for wake-up signals sent by the network device. Upon receiving a wake-up signal, MR is woken up to listen for downlink signals sent by the network device.

[0180] (4) Measurement results of one or more receivers of the terminal equipment in neighboring cells.

[0181] When the input information includes measurement results from a receiver of a terminal device in neighboring cells, the receiver can be any receiver of the terminal device or a designated receiver. In some embodiments, the designated receiver is set by the network device or the terminal device, or depends on the implementation of the AI ​​model; this application embodiment does not limit this. In some embodiments, the designated receiver is the MR of the terminal device. In some embodiments, the measurement results from a receiver of the terminal device in neighboring cells are the measurement results obtained from the most recent wireless measurements performed by that receiver for each neighboring cell.

[0182] When the input information includes measurement results from multiple receivers of the terminal device in neighboring cells, the multiple receivers may be some or all of the receivers of the terminal device. In some embodiments, the measurement results from the multiple receivers of the terminal device in neighboring cells are the measurement results obtained from the most recent wireless measurement performed by each of the multiple receivers for the neighboring cells.

[0183] In some embodiments, the input information includes measurement results from one or more receivers of the terminal device in multiple neighboring cells.

[0184] The above method, by using measurement results from one or more receivers, can provide more accurate signal coverage and interference analysis, helping AI models to judge the effectiveness of different receivers in wireless measurements in neighboring cells.

[0185] (5) Whether the terminal device has enabled relaxed wireless measurement.

[0186] If the terminal device recently performed a relaxed wireless measurement, it is determined that the terminal device has currently enabled relaxed wireless measurement; or, if the terminal device meets the conditions for relaxed wireless measurement, it is determined that the terminal device has currently enabled relaxed wireless measurement; or, if the network device instructs the terminal device to enable relaxed wireless measurement, it is determined that the terminal device has currently enabled relaxed wireless measurement.

[0187] The above method helps the AI ​​model determine whether to continue increasing the measurement interval of wireless measurements or restore the normal measurement interval by inputting whether relaxed wireless measurement is currently enabled.

[0188] (6) If the terminal device has currently enabled relaxed wireless measurement, the relevant information on the currently used wireless measurement relaxation.

[0189] The information related to the current wireless measurement relaxation is used to indicate the degree of frequency reduction or relaxation of the current wireless measurement. In some embodiments, the information related to the current wireless measurement relaxation includes at least one of the following: the measurement interval of the current wireless measurement, the currently increased measurement interval, the current measurement relaxation factor, etc., and may also include other information, which is not limited in this application embodiment.

[0190] The above method, by inputting relevant information about the current wireless measurement relaxation into the AI ​​model, helps the AI ​​model determine whether it is necessary to continue increasing the measurement interval of wireless measurements or to restore the normal measurement interval.

[0191] (7) RRC status of terminal equipment.

[0192] The RRC state of a terminal device refers to the current communication connection state between the terminal device and the network device. In some embodiments, the RRC state of the terminal device includes at least one of the following: RRC connected state, RRC idle state, and RRC inactive state.

[0193] The above method, by inputting the RRC status of the terminal device into the AI ​​model, can help the AI ​​model understand the current network requirements of the terminal device, thereby optimizing the timing and strategy of wireless measurement.

[0194] (8) Identification information of the serving cell of the terminal device.

[0195] The serving cell identification information is used to uniquely identify the serving cell. The serving cell identification information of the terminal device is used to uniquely identify the cell currently serving the terminal device. In some embodiments, the serving cell identification information can be implemented in any of the following ways: PCI (Physical Cell Identity), CGI (Cell Global Identity), NCI (NR Cell Identity), GCI (Global Cell Identity), etc., and may also include other methods, which are not limited in this application embodiment.

[0196] The above method, by inputting the identification information of the serving cell into the AI ​​model, can help the AI ​​model locate the cell where the terminal device is located, thereby optimizing the signal quality measurement of that cell.

[0197] (9) The type of serving cell of the terminal device.

[0198] In some embodiments, the serving cell type of the terminal device includes TN and NTN, and may also include other serving cell types, which are not limited in this application embodiment.

[0199] The above method, by inputting the type of serving cell into the AI ​​model, helps the AI ​​model evaluate the quality and stability of the serving cell, thereby reasonably adjusting the measurement strategy.

[0200] (10) Identification information of neighboring cells of the terminal device.

[0201] The neighboring cell identification information is used to uniquely identify neighboring cells. The neighboring cell identification information of the terminal device is used to uniquely identify the neighboring cells corresponding to the serving cell of the terminal device. In some embodiments, the neighboring cell identification information can be implemented in any of the following ways: PCI, CGI, NCI, GCI, etc., and may also include other methods, which are not limited in this application embodiment.

[0202] In some embodiments, the identification information of neighboring cells of the terminal device is used to indicate the neighboring cells in the input information (4).

[0203] The above method provides the AI ​​model with the specific location and identification of neighboring cells by inputting the identification information of neighboring cells, thus helping to determine the network status of neighboring cells of the terminal device.

[0204] (11) The type of neighboring cell of the terminal device.

[0205] In some embodiments, the types of neighboring cells of the terminal device include TN and NTN, and may also include other types of neighboring cells, which are not limited in this application embodiment.

[0206] The above method, by inputting the type of neighboring cells into the AI ​​model, helps the AI ​​model evaluate the quality and stability of neighboring cells, thereby reasonably adjusting the measurement strategy.

[0207] The following describes the output information of the AI ​​model.

[0208] In some embodiments, the output information of the AI ​​model includes at least one of the following.

[0209] (1) Measurement relaxation factor for the service cell.

[0210] The measurement relaxation factor is used to determine the measurement interval. The measurement relaxation factor for the serving cell is used to determine whether to perform relaxed radio measurements for the serving cell and / or the measurement interval for relaxed radio measurements of the serving cell. The measurement relaxation factor for the serving cell in the output information is a predicted value obtained by the AI ​​model after inference and prediction of the serving cell based on the input information.

[0211] In some embodiments, the measurement interval is determined based on a measurement relaxation factor and a normal measurement interval, which is the measurement interval when wireless measurement is not enabled. In some embodiments, the normal measurement interval is set by the network device or the terminal device or depends on the implementation of the AI ​​model; this application embodiment does not limit this.

[0212] In some embodiments, the measurement relaxation factor is a scaling factor relative to the normal measurement interval; the product of the measurement relaxation factor and the normal measurement interval is determined as the measurement interval for relaxed wireless measurements. In some embodiments, the measurement relaxation factor ranges from greater than or equal to 1. When the measurement relaxation factor is equal to 1, it indicates that relaxed wireless measurements are not performed. When the measurement relaxation factor is k, it indicates that the measurement interval is increased to k times the normal measurement interval, where k is greater than 1. When the measurement relaxation factor is infinity, infinitesimal, or 0, it indicates that wireless measurements are not performed.

[0213] In some embodiments, the measurement relaxation factor is an increase relative to the normal measurement interval; the sum of the measurement relaxation factor and the normal measurement interval is determined as the measurement interval for relaxed wireless measurements. In some embodiments, the measurement relaxation factor ranges from greater than to equal to 0. When the measurement relaxation factor is equal to 0, it indicates that relaxed wireless measurements are not performed. When the measurement relaxation factor is i, it indicates that the measurement interval has increased by i, where i is greater than 0. When the measurement relaxation factor is infinitely large or infinitely small, it indicates that wireless measurements are not performed.

[0214] The above method allows for adjustment of the measurement interval in wireless measurements by adjusting the measurement relaxation factor, which helps to flexibly adjust the measurement interval in wireless measurements and reduce the power consumption of terminal devices.

[0215] (2) Measurement relaxation factor for neighboring cells.

[0216] The measurement relaxation factor for neighboring cells is used to determine whether to perform relaxed radio measurements for neighboring cells and / or the measurement interval for relaxed radio measurements for neighboring cells. In some embodiments, the measurement relaxation factors for different neighboring cells may be the same or different. In some embodiments, the measurement relaxation factors for different frequency points may be the same or different. The measurement relaxation factor for neighboring cells in the output information is a predicted value obtained by the AI ​​model after inference and prediction of neighboring cells based on the input information.

[0217] In some embodiments, different frequency points or different neighboring cells correspond to different measurement relaxation factors.

[0218] A frequency point is used to indicate frequency domain resources in wireless communication. For example, a frequency point is the center frequency assigned to a carrier. In some embodiments, different frequency point priorities correspond to different measurement relaxation factors. Frequency point priority is used to indicate the importance of the corresponding frequency point. For example, the higher the frequency point priority, the smaller the corresponding measurement relaxation factor; the lower the frequency point priority, the larger the corresponding measurement relaxation factor.

[0219] In some embodiments, different cell priorities correspond to different measurement relaxation factors. Cell priority is used to indicate the importance of the corresponding neighboring cells. For example, the higher the cell priority of a neighboring cell, the smaller the corresponding measurement relaxation factor; the lower the cell priority of a neighboring cell, the larger the corresponding measurement relaxation factor.

[0220] The above method, by setting different measurement relaxation factors or measurement intervals for different frequency points and neighboring cells, helps to adapt to different scenarios and can also effectively reduce the power consumption of terminal devices performing wireless measurements.

[0221] (3) Measurement relaxation factor of one or more receivers of the terminal equipment for the serving cell.

[0222] The AI ​​model infers and predicts the radio measurements of one or more receivers of the terminal device for the serving cell based on the input information, and obtains the measurement relaxation factor of one or more receivers of the terminal device for the serving cell.

[0223] Based on the measurement relaxation factor of one or more receivers of the terminal device for the serving cell, the radio measurements for the serving cell are adjusted for each of the receivers, or for one or more receivers.

[0224] (4) Measurement relaxation factor for neighboring cells by one or more receivers of the terminal equipment.

[0225] Similar to the output information (3), the AI ​​model infers and predicts the radio measurements of one or more receivers of the terminal device for neighboring cells based on the input information, and obtains the measurement relaxation factor of one or more receivers of the terminal device for neighboring cells. Based on the measurement relaxation factor of one or more receivers of the terminal device for neighboring cells, the radio measurements for neighboring cells are adjusted for one or more receivers.

[0226] (5) Measurement interval for the serving cell.

[0227] In other words, the measurement interval for the serving cell is predicted directly through AI model inference. When the measurement interval for the serving cell in the output information is greater than the normal measurement interval, relaxed radio measurements are performed for the serving cell. When the measurement interval for the serving cell in the output information is equal to the normal measurement interval, normal radio measurements are performed for the serving cell.

[0228] (6) Measurement interval for neighboring cells.

[0229] Similar to output information (5), the measurement interval of neighboring cells is directly predicted through AI model reasoning. When the measurement interval for neighboring cells in the output information is greater than the normal measurement interval, relaxed wireless measurement is performed for the neighboring cells. When the measurement interval for neighboring cells in the output information is equal to the normal measurement interval, normal wireless measurement is performed for the neighboring cells.

[0230] In some embodiments, the measurement intervals for different neighboring cells may be the same or different. In some embodiments, the measurement intervals for different frequency points may be the same or different.

[0231] In some embodiments, different frequency points or different neighboring cells correspond to different measurement intervals.

[0232] In some embodiments, different frequency priorities correspond to different measurement intervals. For example, the higher the frequency priority of a frequency point, the smaller the corresponding measurement interval; conversely, the lower the frequency priority of a frequency point, the larger the corresponding measurement interval.

[0233] In some embodiments, different cell priorities correspond to different measurement intervals. Cell priority is used to indicate the importance of the corresponding neighboring cells. For example, the higher the cell priority of a neighboring cell, the smaller the corresponding measurement interval; the lower the cell priority of a neighboring cell, the larger the corresponding measurement interval.

[0234] (7) Measurement intervals for the serving cell by one or more receivers of the terminal equipment.

[0235] The measurement intervals for the serving cell by one or more receivers of the terminal device are directly predicted through AI model inference. Based on the measurement intervals for the serving cell by one or more receivers of the terminal device, the radio measurements for the serving cell by one or more receivers of the terminal device are adjusted.

[0236] (8) Measurement intervals of one or more receivers of the terminal equipment for neighboring cells.

[0237] The measurement intervals for neighboring cells by one or more receivers of a terminal device are directly predicted through AI model inference. Based on the measurement intervals for neighboring cells by one or more receivers of the terminal device, the radio measurements for neighboring cells by one or more receivers of the terminal device are adjusted.

[0238] The following describes the monitoring process for AI models used in wireless measurements.

[0239] In some embodiments, a second piece of information sent by a network device is received, the second piece of information being used to monitor the AI ​​model.

[0240] The second information is configuration information used to monitor the AI ​​model. This second information indicates the method of monitoring the AI ​​model. Monitoring the AI ​​model refers to the process of monitoring and tracking the AI ​​model during its deployment and operation. In some embodiments, at least one of the following aspects of the AI ​​model is monitored: performance monitoring, data monitoring, resource monitoring, etc., and other aspects may also be included, which are not limited in this application embodiment. Performance monitoring refers to monitoring the effectiveness of the AI ​​model in inference prediction for wireless measurements. Data monitoring refers to monitoring the input information of the AI ​​model. System monitoring refers to monitoring the generalization and computing resources of the AI ​​model.

[0241] In some embodiments, the second information is used to determine the first criterion, which is used to activate and / or deactivate the use of the AI ​​model.

[0242] The first criterion is used to measure the performance of wireless measurements performed based on an AI model. The first criterion is the criterion for triggering the activation and / or deactivation of the AI ​​model for wireless measurements. In some embodiments, the AI ​​model corresponds to disconnected RRM measurements and is used to infer and predict whether to enable relaxed RRM measurements for disconnected RRM measurements.

[0243] Activating the use of the AI ​​model refers to enabling the AI ​​model to perform inference and prediction for wireless measurements. In some embodiments, the process of activating the AI ​​model includes at least one of the following: loading the AI ​​model, initializing the AI ​​model, performing inference and prediction through the AI ​​model, etc., and may also include other operations, which are not limited in this application embodiment. Deactivating the use of the AI ​​model refers to disabling the AI ​​model to perform inference and prediction for wireless measurements. In some embodiments, the process of deactivating the AI ​​model includes at least one of the following: unloading the AI ​​model, stopping or disabling the AI ​​model from performing inference and prediction, etc., and may also include other operations, which are not limited in this application embodiment.

[0244] The above method uses the first criterion to determine whether to use an AI model to assist the terminal device in performing wireless measurements. Using an AI model to assist the terminal device in performing wireless predictions at the appropriate time helps to save computing resources.

[0245] In some embodiments, the conditions that trigger monitoring of the AI ​​model include at least one of the following.

[0246] Triggering condition 1: The terminal device has obtained the AI ​​model, but has not activated the use of the AI ​​model.

[0247] In other words, after the terminal device executes step 520 and has obtained the AI ​​model based on the first information, but has not yet used the AI ​​model to make inferences and predictions for wireless measurements, the terminal device is triggered to monitor the AI ​​model.

[0248] The above method monitors acquired but not activated AI models to determine their operating status and performance, avoiding the use of inappropriate AI models for wireless measurement and preventing unnecessary waste of resources.

[0249] Triggering condition 2: The terminal device has activated the use of the AI ​​model and meets the periodic monitoring timing.

[0250] The use of an activated AI model indicates that the terminal device uses the AI ​​model to infer and predict wireless measurements, and performs wireless measurements based on the output information of the AI ​​model. In some embodiments, the terminal device monitors the AI ​​model based on a monitoring period. The monitoring period indicates the time interval between two consecutive monitoring of the AI ​​model. The monitoring timing refers to the specific point in time when the terminal device monitors the AI ​​model.

[0251] The above method, by periodically monitoring the AI ​​model, determines the AI ​​model's inference and prediction capabilities, thereby ensuring the stability of the AI ​​model.

[0252] In some embodiments, the conditions for satisfying the first criterion include at least one of the following.

[0253] Condition 1: The difference between the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model and the measurement result obtained by performing wireless measurement without the output information of the AI ​​model is less than or no greater than the first threshold value.

[0254] In some embodiments, the first threshold value is set by the network device or the terminal device or depends on the implementation of the AI ​​model, and this application embodiment does not limit this.

[0255] In some embodiments, the measurement result obtained by wireless measurement not based on the output information of the AI ​​model is the measurement result obtained from the most recent wireless measurement performed before the wireless measurement was performed based on the output information of the AI ​​model. In some embodiments, the content included in the measurement result obtained by wireless measurement performed based on the output information of the AI ​​model is consistent with the content included in the measurement result obtained by wireless measurement not based on the output information of the AI ​​model.

[0256] For example, the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model includes the measurement value corresponding to measurement result 1 and the measurement value corresponding to measurement result 2. The measurement result obtained by performing wireless measurement without the output information of the AI ​​model also includes the measurement value corresponding to measurement result 1 and the measurement value corresponding to measurement result 2. The first threshold includes first threshold 1 and first threshold 2. The measurement result obtained by performing wireless measurement based on the output information of the AI ​​model, including the measurement value corresponding to measurement result 1, is less than or not greater than the first threshold. Furthermore, the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model, including the measurement value corresponding to measurement result 2, is less than or not greater than the first threshold.

[0257] In some embodiments, wireless measurement is performed based on the output information of the AI ​​model to obtain the measurement result corresponding to the AI ​​model. The measurement result corresponding to the AI ​​model is the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model. Based on the normal measurement result, wireless measurement is performed to obtain the measurement result corresponding to the normal wireless measurement. The measurement result corresponding to the normal wireless measurement is the difference between the measurement result obtained by performing wireless measurement without the output information of the AI ​​model and the measurement result corresponding to the normal wireless measurement, which is less than or not greater than a first threshold value. If the difference between the measurement result corresponding to the AI ​​model and the measurement result corresponding to the normal wireless measurement is less than or not greater than the first threshold value, it is determined that condition 1 is satisfied. If the difference between the measurement result corresponding to the AI ​​model and the measurement result corresponding to the normal wireless measurement is greater than or greater than or not less than the first threshold value, it is determined that condition 1 is not satisfied.

[0258] In some embodiments, if the output information of the AI ​​model indicates that relaxed wireless measurements should not be performed, it is determined that condition 1 is not met.

[0259] The above method determines the inference and prediction effect of the AI ​​model for wireless measurement by comparing the measurement results of wireless measurement based on the AI ​​model with those without the model. Based on the magnitude of the measurement error, it decides whether to enable the AI ​​model for wireless measurement, thus avoiding the additional computational overhead caused by the continuous operation of the AI ​​model.

[0260] Condition 2: When performing wireless measurements based on the output information of the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when performing wireless measurements without based on the output information of the AI ​​model is less than or no greater than the second threshold value.

[0261] Initial access refers to the process by which a terminal device establishes a communication connection during its first connection. Random access success rate measures the probability that a terminal device successfully completes the random access process. In some embodiments, the second threshold value is set by the network device or the terminal device, or depends on the implementation of the AI ​​model; this application does not limit this.

[0262] In some embodiments, the random access success rate of the terminal device initiating initial access is calculated when wireless measurement is performed based on the output information of the AI ​​model, and the random access success rate of the terminal device initiating initial access is calculated when wireless measurement is performed without the output information of the AI ​​model. In some embodiments, when wireless measurement is performed based on the output information of the AI ​​model, the random access success rate of the terminal device initiating initial access is obtained by statistically analyzing N instances of the terminal device initiating initial access when wireless measurement is performed based on the output information of the AI ​​model; when wireless measurement is performed without the output information of the AI ​​model, the random access success rate of the terminal device initiating initial access is obtained by statistically analyzing N instances of the terminal device initiating initial access without the output information of the AI ​​model; where N is an integer greater than or not less than 2.

[0263] In some embodiments, the random access success rate can be calculated by the terminal device itself or by the network device. In some embodiments, when the random access success rate is calculated by the network device, the second information also includes the random access success rate of the terminal device initiating initial access when wireless measurement is performed based on the output information of the AI ​​model, and the random access success rate of the terminal device initiating initial access when wireless measurement is not performed based on the output information of the AI ​​model.

[0264] In some embodiments, if the difference between the random access success rate of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access success rate of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is less than or not greater than a second threshold, then condition 2 is determined to be satisfied; if the difference between the random access success rate of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access success rate of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is greater than or not less than a second threshold, then condition 2 is determined not to be satisfied.

[0265] In some embodiments, if the output information of the AI ​​model indicates that relaxed wireless measurement should not be performed, it is determined that condition 2 is not met.

[0266] The above method compares the random access success rate of wireless measurements based on AI models with that of wireless measurements without models to determine the optimization effect of AI models for random access, and decides whether to enable AI models for wireless measurements, thus avoiding additional computational overhead caused by the continuous operation of AI models.

[0267] Condition 3: When performing wireless measurements based on the output information of the AI ​​model, the difference between the random access delay of the terminal device initiating the initial access and the random access delay of the terminal device initiating the initial access when performing wireless measurements without based on the output information of the AI ​​model is less than or not greater than the third threshold value.

[0268] Random access latency refers to the time elapsed from when a terminal device initiates a random access request to when it successfully accesses the network. In some embodiments, the third threshold value is set by the network device or the terminal device, or depends on the implementation of the AI ​​model; this application does not limit this.

[0269] In some embodiments, the random access delay for initial access initiated by the terminal device when performing wireless measurements based on the output information of the AI ​​model, and the random access delay for initial access initiated by the terminal device when performing wireless measurements without based on the output information of the AI ​​model.

[0270] In some embodiments, when wireless measurements are performed based on the output information of the AI ​​model, the random access delay for the terminal device to initiate initial access is the random access delay of the most recent wireless measurement performed based on the output information of the AI ​​model; when wireless measurements are not performed based on the output information of the AI ​​model, the random access delay for the terminal device to initiate initial access is the random access delay of the most recent wireless measurement performed without the output information of the AI ​​model. In some embodiments, when wireless measurements are performed based on the output information of the AI ​​model, the random access delay for the terminal device to initiate initial access is obtained by averaging the random access delays for the terminal device to initiate initial access in M ​​wireless measurements performed without the output information of the AI ​​model; when wireless measurements are not performed based on the output information of the AI ​​model, the random access delay for the terminal device to initiate initial access is obtained by averaging the random access delays for the terminal device to initiate initial access in M ​​wireless measurements performed without the output information of the AI ​​model; where M is a positive integer greater than or not less than 2.

[0271] In some embodiments, the random access latency can be calculated by the terminal device itself or by the network device. In some embodiments, when the random access latency is calculated by the network device, the second information also includes the random access latency when the terminal device initiates initial access if wireless measurement is performed based on the output information of the AI ​​model, and the random access latency when the terminal device initiates initial access if wireless measurement is not performed based on the output information of the AI ​​model.

[0272] In some embodiments, if the difference between the random access delay of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access delay of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is less than or not greater than a third threshold, then condition 3 is determined to be satisfied; if the difference between the random access delay of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access delay of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is greater than or not less than a third threshold, then condition 3 is determined not to be satisfied.

[0273] In some embodiments, if the output information of the AI ​​model indicates that relaxed wireless measurement should not be performed, it is determined that condition 3 is not met.

[0274] The above method compares the random access latency of wireless measurements based on AI models with that of wireless measurements without models to determine the optimization effect of AI models for random access, and decides whether to enable AI models for wireless measurements, thus avoiding additional computational overhead caused by the continuous operation of AI models.

[0275] In some embodiments, the monitoring results based on the AI ​​model include the following two cases.

[0276] Scenario 1: If the monitoring results of the AI ​​model meet the first criterion, activate the use of AI model-based wireless measurement.

[0277] In other words, if the monitoring results of the AI ​​results meet at least one of the first criteria, it is determined that the output information based on the AI ​​model will be used to perform wireless measurements in the next wireless measurement.

[0278] Scenario 2: If the monitoring results of the AI ​​model do not meet the first criterion, deactivate the use of AI model-based wireless measurement and / or use non-AI model-based wireless measurement.

[0279] In other words, if the monitoring results of the AI ​​model do not meet any of the first criteria, it is determined that the output results based on the AI ​​model will not be used to perform wireless measurements in the next wireless measurement.

[0280] In some embodiments, if the terminal device meets the wireless measurement relaxation criteria, it is determined that a relaxed wireless measurement will be performed in the next wireless measurement; if the terminal device does not meet the wireless measurement relaxation criteria, it is determined that a normal relaxed measurement will be performed in the next wireless measurement. The wireless measurement relaxation criteria refer to the triggering conditions for the terminal device to perform a relaxed wireless measurement or not perform a wireless measurement. In some embodiments, the wireless measurement relaxation criteria are RRM relaxation criteria, which include low mobility criteria and non-cell edge criteria.

[0281] The above method activates or deactivates the AI ​​model based on the monitoring results of the AI ​​model, determines whether to enable the AI ​​model for wireless measurement, and avoids additional computing overhead caused by the continuous operation of the AI ​​model.

[0282] In some embodiments, a third message is sent to the network device, the third message indicating whether the monitoring results of the AI ​​model meet the first criterion.

[0283] In some embodiments, the network device determines whether to adjust the AI ​​model based on the monitoring results of the AI ​​model. In some embodiments, if the monitoring results of the AI ​​model indicate that the monitoring results of the AI ​​model do not meet the first criterion, the network device adjusts the AI ​​model to obtain an adjusted AI model.

[0284] In some embodiments, the network device sends fourth information to the terminal device, the fourth information being used to determine the updated AI model.

[0285] The above method, by feeding back the monitoring results of the AI ​​model to the network device, enables the network device to adjust the AI ​​model in a timely manner, thereby improving the performance and stability of the AI ​​model.

[0286] In some embodiments, the third information is sent in the form of small data transmission, or after the RRC connection is established or restored.

[0287] Small data transmission refers to the method of directly transmitting a small amount of data when the terminal device is in an RRC inactive state. In some embodiments, when the terminal device is in a disconnected state, the terminal device sends third information to the network device using small data transmission; or, when the terminal device switches from a disconnected state to a connected state, the terminal device sends third information to the network device.

[0288] The above method eliminates the need to establish an RRC connection in order to send third-party information, effectively reducing the signaling overhead of establishing an RRC connection and the overhead of RRC state switching.

[0289] Please refer to Figure 8, which shows a flowchart of a cell reselection method provided in one embodiment of this application. This method can be applied to a terminal device in the network architecture shown in Figure 1. The method may include the following step 820.

[0290] Step 820: Based on the AI ​​model, determine the target cell for reselection.

[0291] AI models have the ability to infer and predict cell reselection using artificial intelligence or machine learning to determine the target cell for reselection. Cell reselection refers to the process by which a terminal device selects a more suitable cell to camp on. The target cell for reselection is the cell that the terminal device will switch to, as predicted by the AI ​​model.

[0292] In some embodiments, the input information for the AI ​​model includes at least one of the following:

[0293] (1) Measurement results of terminal equipment in the serving cell.

[0294] (2) Measurement results of the terminal equipment in neighboring cells.

[0295] (3) Identification information of the serving cell of the terminal device.

[0296] (4) The type of serving cell of the terminal device.

[0297] (5) Identification information of neighboring cells of the terminal device.

[0298] (6) The type of neighboring cell of the terminal device.

[0299] It should be noted that the input information of the AI ​​model in the cell reselection method is consistent with the input information of some AI models in the above wireless measurement method. For relevant explanations, please refer to the corresponding parts in the embodiments of the above wireless measurement method. This application will not repeat them here.

[0300] In some embodiments, the output information of the AI ​​model includes at least one of the following:

[0301] (1) Whether the terminal device performs cell reselection.

[0302] In other words, the AI ​​model directly predicts whether a terminal device needs to perform cell reselection. When the AI ​​model determines, based on the input information, that the current serving cell quality is good, it determines that the terminal device does not need to perform cell reselection. When the AI ​​model determines, based on the input information, that the current serving cell quality is poor, it determines that the terminal device needs to perform cell reselection.

[0303] (2) The terminal device is reselected to the target cell.

[0304] In other words, the AI ​​model can directly predict whether the terminal device needs to perform cell reselection and determine the target cell for handover.

[0305] The above method, through AI models, directly determines whether a terminal device needs cell handover and which cell to hand over to, which helps improve the efficiency and accuracy of cell reselection for terminal devices.

[0306] In some embodiments, as shown in FIG9, step 810 is included before step 820.

[0307] Step 810: Receive the first information sent by the network device. The first information is used to determine the AI ​​model.

[0308] In some embodiments, the network device sends first information to the terminal device. Correspondingly, the terminal device receives the first information sent by the network device. In some embodiments, the network device trains an AI model based on training data from wireless measurements to obtain a trained AI model; the network device then sends the first information to the terminal device, the first information being used to determine the trained AI model. The training samples used for AI training include data related to cell reselection and sample labels.

[0309] In some embodiments, the first information includes at least one of the following: location information, model type, model parameters, AI model, etc., and may also include other information, which is not limited in this application embodiment.

[0310] In some embodiments, as shown in FIG10, step 830 is further included after step 820.

[0311] Step 830: Switch to the reselected target cell to stay in.

[0312] The technical solution provided in this application uses an AI model to perform inference and prediction on cell reselection, directly obtaining the target cell to which the cell is reselected. This effectively reduces the complexity of cell reselection performed by the terminal device, and also improves the random access success rate and reduces the random access latency of the terminal device.

[0313] The following describes the monitoring process for the AI ​​model used for cell reselection.

[0314] In some embodiments, a second piece of information sent by a network device is received, the second piece of information being used to monitor the AI ​​model.

[0315] The second information is configuration information used to monitor the AI ​​model. This second information indicates the method for monitoring the AI ​​model. Monitoring the AI ​​model refers to the process of monitoring and tracking the AI ​​model during its deployment and operation. In some embodiments, monitoring includes at least one of the following aspects: performance monitoring, data monitoring, resource monitoring, etc., and may also include other aspects, which are not limited in this application embodiment.

[0316] In some embodiments, the second information is used to determine a second criterion, which is used to activate and / or deactivate the use of the AI ​​model.

[0317] The second criterion is used to measure the performance of cell reselection based on AI models. The second criterion is the criterion for determining the activation and / or deactivation of the AI ​​model used for cell reselection.

[0318] Activating the use of the AI ​​model refers to enabling the AI ​​model to perform inference and prediction for cell reselection. In some embodiments, the process of activating the AI ​​model includes at least one of the following: loading the AI ​​model, initializing the AI ​​model, and performing inference and prediction through the AI ​​model, and may also include other operations, which are not limited in this application embodiment. Deactivating the use of the AI ​​model refers to disabling the AI ​​model to perform inference and prediction for cell reselection. In some embodiments, the process of deactivating the AI ​​model includes at least one of the following: unloading the AI ​​model, stopping or disabling the AI ​​model from performing inference and prediction, and may also include other operations, which are not limited in this application embodiment.

[0319] In some embodiments, the conditions that trigger monitoring of the AI ​​model include at least one of the following.

[0320] Triggering condition 1: The terminal device has obtained the AI ​​model, but has not activated the use of the AI ​​model.

[0321] Triggering condition 2: The terminal device has activated the use of the AI ​​model and meets the periodic monitoring timing.

[0322] It should be noted that the conditions for triggering the monitoring of the AI ​​model in the cell reselection method are the same as those for triggering the monitoring of the AI ​​model in the above wireless measurement method. For relevant explanations, please refer to the corresponding parts in the embodiments of the above wireless measurement method. This application will not repeat them here.

[0323] In some embodiments, the conditions for meeting the second criterion include at least one of the following.

[0324] Condition 1: When cell reselection is performed based on an AI model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when cell reselection is not performed based on an AI model is less than or no greater than the fourth threshold.

[0325] Condition 2: When cell reselection is performed based on an AI model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access when cell reselection is not performed based on an AI model is less than or no greater than the fifth threshold.

[0326] It should be noted that conditions 1 and 2 in the second criterion of the cell reselection method are similar to conditions 2 and 3 in the first criterion of the above-mentioned wireless measurement method. For relevant explanations, please refer to the corresponding parts in the embodiments of the above-mentioned wireless measurement method. The embodiments of this application will not be repeated here.

[0327] In some embodiments, the monitoring results based on the AI ​​model include the following two cases.

[0328] Scenario 1: If the monitoring results of the AI ​​model meet the second criterion, activate the cell reselection based on the AI ​​model.

[0329] In other words, if the monitoring results of the AI ​​meet at least one of the second criteria, it is determined whether to switch to the target cell for residence.

[0330] Scenario 2: If the monitoring results of the AI ​​model do not meet the second criterion, deactivate cell reselection based on the AI ​​model and / or use cell reselection not based on the AI ​​model.

[0331] In other words, if the monitoring results of the AI ​​model do not meet any of the first criteria, it is determined that the output results based on the AI ​​model will not be used to perform wireless measurements in the next wireless measurement.

[0332] In some embodiments, the target cell for reselection is determined based on cell reselection criteria.

[0333] In some embodiments, a third message is sent to the network device, the third message indicating whether the monitoring results of the AI ​​model meet the second criterion.

[0334] In some embodiments, the third information is sent in the form of small data transmission, or after the RRC connection is established or restored.

[0335] It should be noted that the method of sending the third information in the cell reselection method is consistent with the method of sending the third information in the above-mentioned wireless measurement method. For relevant explanations, please refer to the corresponding parts in the embodiments of the above-mentioned wireless measurement method. This application will not repeat them here.

[0336] The following are embodiments of the device described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the embodiments of the device described in this application, please refer to the embodiments of the method described in this application.

[0337] Please refer to Figure 11, which shows a block diagram of a terminal device provided in one embodiment of this application. This terminal device has the function of implementing the above-described wireless measurement method. As shown in Figure 11, the terminal device 1100 may include a processing module 1110.

[0338] Processing module 1110 is used to determine relevant information for wireless measurement relaxation based on an AI model.

[0339] In some embodiments, the input information of the AI ​​model includes at least one of the following: measurement results of the terminal device in the serving cell; measurement results of the terminal device in neighboring cells; measurement results of one or more receivers of the terminal device in the serving cell; measurement results of one or more receivers of the terminal device in neighboring cells; whether the terminal device has currently enabled relaxed radio measurement; if the terminal device has currently enabled relaxed radio measurement, relevant information on the currently used relaxed radio measurement; RRC status of the terminal device; identification information of the serving cell of the terminal device; type of the serving cell of the terminal device; identification information of the neighboring cells of the terminal device; type of the neighboring cells of the terminal device.

[0340] In some embodiments, the output information of the AI ​​model includes at least one of the following: a measurement relaxation factor for the serving cell; a measurement relaxation factor for neighboring cells; a measurement relaxation factor for the serving cell from one or more receivers of the terminal device; a measurement relaxation factor for neighboring cells from one or more receivers of the terminal device; a measurement interval for the serving cell; a measurement interval for neighboring cells; a measurement interval for the serving cell from one or more receivers of the terminal device; a measurement interval for neighboring cells from one or more receivers of the terminal device; wherein the measurement relaxation factor is used to determine the measurement interval.

[0341] In some embodiments, the measurement interval is determined based on the measurement relaxation factor and the normal measurement interval, which is the measurement interval when wireless measurement is not enabled.

[0342] In some embodiments, different frequency points or different neighboring cells correspond to different measurement relaxation factors and / or different measurement intervals.

[0343] In some embodiments, the plurality of receivers includes a first receiver and a second receiver, wherein the power consumption of the first receiver is less than the power consumption of the second receiver.

[0344] In some embodiments, the terminal device 1100 further includes a receiving module 1120 for receiving first information sent by a network device, the first information being used to determine the AI ​​model.

[0345] In some embodiments, the wireless measurement includes at least two of the following types: RRM measurement, RLM measurement, and BFD measurement; different types of wireless measurement correspond to the same AI model; or, different types of wireless measurement correspond to different AI models.

[0346] In some embodiments, connected-state RRM measurements and disconnected-state RRM measurements correspond to the same AI model; or, connected-state RRM measurements and disconnected-state RRM measurements correspond to different AI models.

[0347] In some embodiments, the receiving module 1120 is configured to receive second information sent by a network device, the second information being used to monitor the AI ​​model.

[0348] In some embodiments, the second information is used to determine a first criterion, which is used to activate and / or deactivate the use of the AI ​​model.

[0349] In some embodiments, the conditions for satisfying the first criterion include at least one of the following: the difference between the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model and the measurement result obtained by performing wireless measurement without the output information of the AI ​​model is less than or not greater than a first threshold; the difference between the random access success rate of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access success rate of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is less than or not greater than a second threshold; the difference between the random access latency of the terminal device initiating initial access when performing wireless measurement based on the output information of the AI ​​model and the random access latency of the terminal device initiating initial access when performing wireless measurement without the output information of the AI ​​model is less than or not greater than a third threshold.

[0350] In some embodiments, the processing module 1110 is further configured to activate the use of wireless measurement based on the AI ​​model if the monitoring result of the AI ​​model meets the first criterion; or, deactivate the use of wireless measurement based on the AI ​​model if the monitoring result of the AI ​​model does not meet the first criterion, and / or use wireless measurement not based on the AI ​​model.

[0351] In some embodiments, the terminal device 1100 further includes a sending module 1130 for sending third information to a network device, the third information being used to indicate whether the monitoring results of the AI ​​model meet the first criterion.

[0352] In some embodiments, the third information is sent in the form of small data transmission, or after an RRC connection is established or restored.

[0353] In some embodiments, the conditions for triggering monitoring of the AI ​​model include at least one of the following: the terminal device has acquired the AI ​​model but has not activated the use of the AI ​​model; or the terminal device has activated the use of the AI ​​model and meets the periodic monitoring timing.

[0354] The technical solution provided in this application uses an AI model to perform inference and prediction on wireless measurements, directly obtaining relevant information on wireless measurement relaxation. This effectively reduces the complexity of the terminal device in determining the relaxation of wireless measurements, saving energy consumption of the terminal device while effectively ensuring the accuracy of wireless measurements.

[0355] Please refer to Figure 12, which shows a block diagram of a terminal device provided in another embodiment of this application. This terminal device has the function of implementing the above-described cell reselection method. As shown in Figure 12, the terminal device 1200 may include a processing module 1210.

[0356] Processing module 1210 is used to determine the target cell for reselection based on an AI model.

[0357] In some embodiments, the input information of the AI ​​model includes at least one of the following: the measurement results of the terminal device in the serving cell; the measurement results of the terminal device in neighboring cells; the identification information of the serving cell of the terminal device; the type of the serving cell of the terminal device; the identification information of the neighboring cells of the terminal device; and the type of the neighboring cells of the terminal device.

[0358] In some embodiments, the output information of the AI ​​model includes at least one of the following: whether the terminal device performs cell reselection; the target cell to which the terminal device reselects.

[0359] In some embodiments, the terminal device 1200 further includes a receiving module 1220 for receiving first information sent by a network device, the first information being used to determine the AI ​​model.

[0360] In some embodiments, the terminal device 1200 further includes a receiving module 1220 for receiving second information sent by a network device, the second information being used to monitor the AI ​​model.

[0361] In some embodiments, the second information is used to determine a second criterion, which is used to activate and / or deactivate the use of the AI ​​model.

[0362] In some embodiments, the conditions for satisfying the second criterion include at least one of the following: when cell reselection is performed based on the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access without performing cell reselection based on the AI ​​model is less than or not greater than a fourth threshold; when cell reselection is performed based on the AI ​​model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access without performing cell reselection based on the AI ​​model is less than or not greater than a fifth threshold.

[0363] In some embodiments, the processing module 1210 is further configured to activate cell reselection based on the AI ​​model if the monitoring result of the AI ​​model meets the second criterion; or, deactivate cell reselection based on the AI ​​model if the monitoring result of the AI ​​model does not meet the second criterion, and / or, use cell reselection not based on the AI ​​model.

[0364] In some embodiments, the terminal device 1200 further includes a sending module 1230 for sending third information to a network device, the third information being used to indicate whether the monitoring results of the AI ​​model meet the second criterion.

[0365] In some embodiments, the third information is sent in the form of small data transmission, or after an RRC connection is established or restored.

[0366] In some embodiments, the conditions for triggering monitoring of the AI ​​model include at least one of the following: the terminal device has acquired the AI ​​model but has not activated the use of the AI ​​model; or the terminal device has activated the use of the AI ​​model and meets the periodic monitoring timing.

[0367] The technical solution provided in this application uses an AI model to perform inference and prediction on cell reselection, directly obtaining the target cell to which the cell is reselected. This effectively reduces the complexity of cell reselection performed by the terminal device, and also improves the random access success rate and reduces the random access latency of the terminal device.

[0368] It should be noted that the above embodiments only illustrate the division of the above functional modules when implementing the functions of the device. In actual applications, the above functions can be assigned to different functional modules according to actual needs, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0369] Regarding the devices in the above embodiments, the specific methods by which each module performs its operations have been described in detail in the embodiments related to the method, and will not be elaborated upon here. For details not described in detail in the device embodiments, please refer to the above method embodiments.

[0370] Please refer to Figure 13, which shows a schematic diagram of the structure of a terminal device provided in one embodiment of this application. The terminal device 1300 may include a processor 1301, a transceiver 1302, and a memory 1303. The transceiver 1302 is used to implement sending and / or receiving functions, such as implementing the functions of the aforementioned sending and / or receiving modules. The processor can be used to implement other processing functions or control sending and / or receiving, such as implementing the functions of the aforementioned processing modules.

[0371] The processor 1301 includes one or more processing cores. The processor 1301 executes various functional applications and information processing by running software programs and modules.

[0372] The transceiver 1302 may include a receiver and a transmitter. For example, the receiver and transmitter may be implemented as the same wireless communication component, which may include a wireless communication chip and a radio frequency antenna.

[0373] The memory 1303 can be connected to the processor 1301 and the transceiver 1302.

[0374] The memory 1303 can be used to store computer programs executed by the processor, and the processor 1301 is used to execute the computer program.

[0375] In some embodiments, the processor 1301 is used to determine relevant information about wireless measurement relaxation based on an AI model.

[0376] In some embodiments, the processor 1301 is used to determine the target cell for reselection based on an AI model.

[0377] For details not described in this embodiment, please refer to the embodiments above, which will not be repeated here.

[0378] Furthermore, the memory 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, statically accessible memory, read-only memory, magnetic memory, flash memory, and programmable read-only memory.

[0379] This application also provides a computer-readable storage medium storing a computer program for execution by a processor to implement the aforementioned wireless measurement method and / or cell reselection method. In some embodiments, the computer-readable storage medium may include ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives), or optical disc, etc. The random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0380] This application also provides a chip, which includes programmable logic circuits and / or program instructions, and when the chip is running, it is used to implement the above-mentioned wireless measurement method and / or cell reselection method.

[0381] This application also provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor reads and executes the computer instructions from the computer-readable storage medium to implement the above-described wireless measurement method and / or cell reselection method.

[0382] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0383] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0384] In some embodiments of this application, "predefined" can be achieved by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0385] In some embodiments of this application, the term "protocol" may refer to standard protocols in the field of communications, such as LTE protocols, NR protocols, and related protocols applied in future communication systems. This application does not limit the scope of these protocols.

[0386] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0387] In this article, "greater than or equal to" can mean greater than or equal to, and "less than or equal to" can mean less than or equal to.

[0388] Furthermore, the step numbers described herein are merely illustrative of one possible execution order between steps. In some other embodiments, the steps may not be executed in the order of their numbers, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0389] 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.

[0390] 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 wireless measurement method, characterized by, The method is executed by a terminal device, and the method includes: Based on an artificial intelligence (AI) model, relevant information for wireless measurement of relaxation is determined.

2. The method of claim 1, wherein, The input information of the AI ​​model includes at least one of the following: The measurement results of the terminal device in the serving cell; The measurement results of the terminal device in the neighboring cell; The measurement results of one or more receivers of the terminal device in the serving cell; The measurement results of one or more receivers of the terminal device in the neighboring cell; Is relaxed wireless measurement currently enabled on the terminal device? In the case where the terminal device has currently enabled relaxed wireless measurement, the relevant information of the currently used relaxed wireless measurement; The radio resource control (RRC) status of the terminal device; The identification information of the serving cell of the terminal device; The type of serving cell of the terminal device; The identification information of the neighboring cells of the terminal device; The type of neighboring cells of the terminal device.

3. The method according to claim 1 or 2, characterized in that, The output information of the AI ​​model includes at least one of the following: The relaxation factor for measurement of the service area; The relaxation factor for measuring neighboring cells; One or more receivers of the terminal device measure the relaxation factor for the serving cell; One or more receivers of the terminal device measure the relaxation factor for neighboring cells; Measurement intervals for the service cell; Measurement intervals for neighboring cells; The measurement interval of one or more receivers of the terminal device for the serving cell; One or more receivers of the terminal device measure the interval of neighboring cells; The measurement relaxation factor is used to determine the measurement interval.

4. The method of claim 3, wherein, The measurement interval is determined based on the measurement relaxation factor and the normal measurement interval, which is the measurement interval when wireless measurement is not enabled.

5. The method according to claim 3 or 4, characterized in that, Different frequency points or different neighboring cells correspond to different measurement relaxation factors and / or different measurement intervals.

6. The method according to any one of claims 2 to 5, characterized in that, The plurality of receivers includes a first receiver and a second receiver, wherein the power consumption of the first receiver is less than that of the second receiver.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The system receives first information sent by a network device, which is used to determine the AI ​​model.

8. The method according to any one of claims 1 to 7, characterized in that, The wireless measurements include at least two of the following types: Radio Resource Management (RRM) measurements, Radio Link Monitoring (RLM) measurements, and Beam Failure Discovery (BFD) measurements. Different types of wireless measurements correspond to the same AI model; or, Different types of wireless measurements correspond to different AI models.

9. The method according to any one of claims 1 to 8, characterized in that, RRM measurements in the connected state and RRM measurements in the disconnected state correspond to the same AI model; or, RRM measurements in connected states and RRM measurements in disconnected states correspond to different AI models.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: The system receives second information sent by a network device, which is used to monitor the AI ​​model.

11. The method of claim 10, wherein, The second information is used to determine the first criterion, which is used to activate and / or deactivate the use of the AI ​​model.

12. The method of claim 11, wherein, The conditions for satisfying the first criterion include at least one of the following: The difference between the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model and the measurement result obtained by performing wireless measurement without the output information of the AI ​​model is less than or not greater than a first threshold value. When wireless measurement is performed based on the output information of the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when wireless measurement is not performed based on the output information of the AI ​​model is less than or not greater than the second threshold value. When wireless measurement is performed based on the output information of the AI ​​model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access when wireless measurement is not performed based on the output information of the AI ​​model is less than or not greater than a third threshold value.

13. The method according to claim 11 or 12, characterized in that, The method further includes: If the monitoring results of the AI ​​model meet the first criterion, activate the use of wireless measurement based on the AI ​​model; or, If the monitoring result of the AI ​​model does not meet the first criterion, deactivate the use of wireless measurement based on the AI ​​model, and / or use wireless measurement not based on the AI ​​model.

14. The method according to any one of claims 11 to 13, characterized in that, The method further includes: A third message is sent to the network device, the third message indicating whether the monitoring results of the AI ​​model meet the first criterion.

15. The method of claim 14, wherein, The third information is sent using a small data transmission method, or after the RRC connection is established or restored.

16. The method according to any one of claims 10 to 15, characterized in that, The conditions that trigger monitoring of the AI ​​model include at least one of the following: The terminal device has acquired the AI ​​model, but has not activated its use. The terminal device has activated the use of the AI ​​model and meets the periodic monitoring requirements.

17. A cell reselection method, c h a r a c t e r i z e d b y, The method is executed by a terminal device, and the method includes: The target cell for reselection is determined based on an artificial intelligence (AI) model.

18. The method of claim 17, wherein, The input information of the AI ​​model includes at least one of the following: The measurement results of the terminal device in the serving cell; The measurement results of the terminal device in the neighboring cell; The identification information of the serving cell of the terminal device; The type of serving cell of the terminal device; The identification information of the neighboring cells of the terminal device; The type of neighboring cells of the terminal device.

19. The method of claim 17 or 18, wherein, The output information of the AI ​​model includes at least one of the following: Does the terminal device perform cell reselection? The terminal device is reselected to the target cell.

20. The method according to any one of claims 17 to 19, characterized in that, The method further includes: The system receives first information sent by a network device, which is used to determine the AI ​​model.

21. The method according to any one of claims 17 to 20, characterized in that, The method further includes: The system receives second information sent by a network device, which is used to monitor the AI ​​model.

22. The method of claim 21, wherein, The second information is used to determine the second criterion, which is used to activate and / or deactivate the use of the AI ​​model.

23. The method of claim 22, wherein, The conditions for satisfying the second criterion include at least one of the following: When cell reselection is performed based on the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when cell reselection is not performed based on the AI ​​model is less than or not greater than the fourth threshold value. When cell reselection is performed based on the AI ​​model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access when cell reselection is not performed based on the AI ​​model is less than or not greater than the fifth threshold value.

24. The method of claim 22 or 23, wherein, The method further includes: If the monitoring results of the AI ​​model meet the second criterion, activate cell reselection using the AI ​​model; or, If the monitoring result of the AI ​​model does not meet the second criterion, the cell reselection based on the AI ​​model is deactivated, and / or, cell reselection not based on the AI ​​model is used.

25. The method of any one of claims 22 to 24, wherein, The method further includes: A third message is sent to the network device, the third message indicating whether the monitoring results of the AI ​​model meet the second criterion.

26. The method of claim 25, wherein, The third information is sent using a small data transmission method, or after the RRC connection is established or restored.

27. The method of any one of claims 21 to 26, wherein, The conditions that trigger monitoring of the AI ​​model include at least one of the following: The terminal device has acquired the AI ​​model, but has not activated its use. The terminal device has activated the use of the AI ​​model and meets the periodic monitoring requirements.

28. A terminal device, comprising: The terminal device includes: The processing module is used to determine relevant information for wireless measurement relaxation based on an artificial intelligence (AI) model.

29. The terminal device of claim 28, wherein, The input information of the AI ​​model includes at least one of the following: The measurement results of the terminal device in the serving cell; The measurement results of the terminal device in the neighboring cell; The measurement results of one or more receivers of the terminal device in the serving cell; The measurement results of one or more receivers of the terminal device in the neighboring cell; Is relaxed wireless measurement currently enabled on the terminal device? In the case where the terminal device has currently enabled relaxed wireless measurement, the relevant information of the currently used relaxed wireless measurement; The radio resource control (RRC) status of the terminal device; The identification information of the serving cell of the terminal device; The type of serving cell of the terminal device; The identification information of the neighboring cells of the terminal device; The type of neighboring cells of the terminal device.

30. The terminal device according to claim 28 or 29, characterized by The output information of the AI ​​model includes at least one of the following: The relaxation factor for measurement of the service area; The relaxation factor for measuring neighboring cells; One or more receivers of the terminal device measure the relaxation factor for the serving cell; One or more receivers of the terminal device measure the relaxation factor for neighboring cells; Measurement intervals for the service cell; Measurement intervals for neighboring cells; The measurement interval of one or more receivers of the terminal device for the serving cell; One or more receivers of the terminal device measure the interval of neighboring cells; The measurement relaxation factor is used to determine the measurement interval.

31. The terminal device of claim 30, wherein, The measurement interval is determined based on the measurement relaxation factor and the normal measurement interval, which is the measurement interval when wireless measurement is not enabled.

32. The terminal device according to claim 30 or 31, characterized by Different frequency points or different neighboring cells correspond to different measurement relaxation factors and / or different measurement intervals.

33. The terminal device of any one of claims 29 to 32, wherein, The plurality of receivers includes a first receiver and a second receiver, wherein the power consumption of the first receiver is less than that of the second receiver.

34. The terminal device of any one of claims 28 to 33, wherein, The terminal device also includes: A receiving device is used to receive first information sent by a network device, the first information being used to determine the AI ​​model.

35. The terminal device of any one of claims 28 to 34, wherein, The wireless measurements include at least two of the following types: Radio Resource Management (RRM) measurements, Radio Link Monitoring (RLM) measurements, and Beam Failure Discovery (BFD) measurements. Different types of wireless measurements correspond to the same AI model; or, Different types of wireless measurements correspond to different AI models.

36. The terminal device according to any one of claims 28 to 35, characterized in that, RRM measurements in the connected state and RRM measurements in the disconnected state correspond to the same AI model; or, RRM measurements in connected states and RRM measurements in disconnected states correspond to different AI models.

37. The terminal device of any one of claims 28 to 36, wherein, The terminal device also includes: A receiving device is used to receive second information sent by a network device, the second information being used to monitor the AI ​​model.

38. The terminal device of claim 37, wherein, The second information is used to determine the first criterion, which is used to activate and / or deactivate the use of the AI ​​model.

39. The terminal device of claim 38, wherein, The conditions for satisfying the first criterion include at least one of the following: The difference between the measurement result obtained by performing wireless measurement based on the output information of the AI ​​model and the measurement result obtained by performing wireless measurement without the output information of the AI ​​model is less than or not greater than a first threshold value. When wireless measurement is performed based on the output information of the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when wireless measurement is not performed based on the output information of the AI ​​model is less than or not greater than the second threshold value. When wireless measurement is performed based on the output information of the AI ​​model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access when wireless measurement is not performed based on the output information of the AI ​​model is less than or not greater than a third threshold value.

40. The terminal device according to claim 38 or 39, characterized in that, The processing module is further configured to, if the monitoring result of the AI ​​model satisfies the first criterion, activate the use of wireless measurement based on the AI ​​model; or, The processing module is further configured to, if the monitoring result of the AI ​​model does not meet the first criterion, deactivate the use of wireless measurement based on the AI ​​model, and / or use wireless measurement not based on the AI ​​model.

41. The terminal device of any one of claims 38 to 40, wherein, The terminal device also includes: The sending module is used to send third information to the network device, the third information being used to indicate whether the monitoring results of the AI ​​model meet the first criterion.

42. The terminal device of claim 41, wherein, The third information is sent using a small data transmission method, or after the RRC connection is established or restored.

43. The terminal device according to any one of claims 37 to 42, characterized in that, The conditions that trigger monitoring of the AI ​​model include at least one of the following: The terminal device has acquired the AI ​​model, but has not activated its use. The terminal device has activated the use of the AI ​​model and meets the periodic monitoring requirements.

44. A terminal device, characterized in that, The terminal device includes: The processing module is used to determine the target cell for reselection based on an artificial intelligence (AI) model.

45. The terminal device according to claim 44, characterized in that, The input information of the AI ​​model includes at least one of the following: The measurement results of the terminal device in the serving cell; The measurement results of the terminal device in the neighboring cell; The identification information of the serving cell of the terminal device; The type of serving cell of the terminal device; The identification information of the neighboring cells of the terminal device; The type of neighboring cells of the terminal device.

46. ​​The terminal device according to claim 44 or 45, characterized in that, The output information of the AI ​​model includes at least one of the following: Does the terminal device perform cell reselection? The terminal device is reselected to the target cell.

47. The terminal device according to any one of claims 44 to 46, characterized in that, The terminal device also includes: A receiving module is used to receive first information sent by a network device, the first information being used to determine the AI ​​model.

48. The terminal device according to any one of claims 44 to 47, characterized in that, The terminal device also includes: The receiving module is used to receive second information sent by the network device, the second information being used to monitor the AI ​​model.

49. The terminal device according to claim 48, characterized in that, The second information is used to determine the second criterion, which is used to activate and / or deactivate the use of the AI ​​model.

50. The terminal device according to claim 49, characterized in that, The conditions for satisfying the second criterion include at least one of the following: When cell reselection is performed based on the AI ​​model, the difference between the random access success rate of the terminal device initiating initial access and the random access success rate of the terminal device initiating initial access when cell reselection is not performed based on the AI ​​model is less than or not greater than the fourth threshold value. When cell reselection is performed based on the AI ​​model, the difference between the random access delay of the terminal device initiating initial access and the random access delay of the terminal device initiating initial access when cell reselection is not performed based on the AI ​​model is less than or not greater than the fifth threshold value.

51. The terminal device according to claim 48 or 50, characterized in that, The processing module is further configured to activate cell reselection based on the AI ​​model if the monitoring result of the AI ​​model meets the second criterion; or, The processing module is further configured to, when the monitoring result of the AI ​​model does not meet the second criterion, deactivate cell reselection based on the AI ​​model, and / or use cell reselection not based on the AI ​​model.

52. The terminal device according to any one of claims 49 to 51, characterized in that, The terminal device also includes: The sending module is used to send third information to the network device, the third information being used to indicate whether the monitoring results of the AI ​​model meet the second criterion.

53. The terminal device according to claim 52, characterized in that, The third information is sent using a small data transmission method, or after the RRC connection is established or restored.

54. The terminal device according to any one of claims 48 to 53, characterized in that, The conditions that trigger monitoring of the AI ​​model include at least one of the following: The terminal device has acquired the AI ​​model, but has not activated its use. The terminal device has activated the use of the AI ​​model and meets the periodic monitoring requirements.

55. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the method as claimed in any one of claims 1 to 16, and / or to implement the method as claimed in any one of claims 17 to 27.

56. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that is executed by a processor to implement the method as claimed in any one of claims 1 to 16, and / or to implement the method as claimed in any one of claims 17 to 27.

57. A chip, characterized in that, The chip includes programmable logic circuitry and / or program instructions, which, when the chip is running, are used to implement the method as described in any one of claims 1 to 16, and / or to implement the method as described in any one of claims 17 to 27.

58. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, which a processor reads from and executes to implement the method as claimed in any one of claims 1 to 16, and / or the method as claimed in any one of claims 17 to 27.

Images