Radio measurement method, device, chip, and storage medium

Abstract

A radio measurement method, a device, a chip, and a storage medium, which relate to the technical field of communications. The method comprises: a terminal device receiving first information, which is used for determining information related to an AI model, wherein the AI model is used for assisting with RRM measurements. A network device sends first information to a terminal device, so as to indicate, to the terminal device, information related to an AI model, such that the terminal device can use the AI model to assist with RRM measurements, thereby reducing RRM measurements to be executed, and thus reducing the energy consumption of the terminal device caused by executing the RRM measurements.

Description

Wireless measurement methods, devices, chips and storage media Technical Field

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

[0002] Terminal devices can perform RRM (Radio Resource Management) 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 radio resources and cell handover for terminal devices.

[0003] To reduce the power consumption caused by continuous RRM measurements by terminal devices, network devices are configured with a series of judgment criteria to help terminal devices determine when to perform RRM 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, device, chip, and 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] Receive first information, which is used to determine relevant information of an AI (Artificial Intelligence) model, which is used to assist in RRM measurement.

[0008] According to one aspect of the embodiments of this application, a wireless measurement method is provided, the method being performed by a network device, the method comprising:

[0009] Send first information, which is used to determine relevant information about the AI ​​model, which is used for RRM measurement.

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

[0011] A receiving module is used to receive first information, which is related to an AI model, and the AI ​​model is used to assist in RRM measurement.

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

[0013] The sending module is used to send first information, which is used to determine relevant information of the AI ​​model, and the AI ​​model is used to assist in RRM measurement.

[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 cause the terminal device to perform the above-described wireless measurement method.

[0015] According to one aspect of the present application, a network device is provided, the network device including a processor and a memory, the memory storing a computer program, the processor executing the computer program to cause the network device to perform the above-described wireless measurement method.

[0016] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, the storage medium storing a computer program, the computer program being executed by a processor to implement the wireless measurement method on the terminal device side or the wireless measurement method on the network device side described above.

[0017] 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 wireless measurement method on the terminal device side or the wireless measurement method on the network device side described above.

[0018] 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 wireless measurement method on the terminal device side or the wireless measurement method on the network device side described above.

[0019] The technical solutions provided in this application embodiment may have the following beneficial effects:

[0020] Network devices send initial information to terminal devices, instructing them on relevant information about the AI ​​model. This allows terminal devices to use the AI ​​model to assist in RRM measurements, implementing some of the RRM measurement logic. This reduces the complexity of performing RRM measurements and also reduces the number of RRM measurements performed, thereby lowering the power consumption of the terminal device due to RRM measurement operations. 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 an RRM measurement model provided in one embodiment of this application;

[0023] Figure 3 is a schematic diagram of the functional framework of an AI / ML (Machine Learning) model provided in an embodiment of this application;

[0024] Figure 4 is a flowchart of a wireless measurement method provided in an embodiment of this application;

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

[0026] Figure 6 is a flowchart of validity verification provided in an embodiment of this application;

[0027] Figure 7 is a block diagram of a terminal device provided in an embodiment of this application;

[0028] Figure 8 is a block diagram of a network device provided in an embodiment of this application;

[0029] Figure 9 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0030] Figure 10 is a schematic diagram of the structure of a network device provided in one embodiment of this application. Detailed Implementation

[0031] 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.

[0032] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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 to these. 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] The relevant technologies involved in this application are described below. These 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.

[0046] I. Community Selection

[0047] When a UE selects a new PLMN or SNPN (Stand-alone Non-Public Network), it performs a cell selection process. If the UE has not stored previous frequency information, it triggers an initial cell selection process. During this initial process, the UE scans all NR band RF (Radio Frequency) channels to find a suitable cell. At each frequency, the UE searches only the strongest cell, and once a suitable cell is found, it selects it. If the UE has stored frequency information and cell parameters, it directly selects a suitable cell upon discovery. If no suitable cell is found, the UE triggers the initial cell selection process.

[0048] Cell selection S criterion meets the following conditions:

[0049] Srxlev>0 AND Squal>0

[0050] in:

[0051] Srxlev=Q rxlevmeas –(Q rxlevmin +Q rxlevminoffset )–P compensation -Qoffset temp

[0052] Squal = Q qualmeas –(Q qualmin +Q qualminoffset -Qoffset temp

[0053] Wherein, Srxlev (Serving cell Received Signal Level) indicates the serving cell's received signal strength, Squal (Serving cell Received Signal Quality) indicates the serving cell's received signal quality, and Q... rxlevmeas Q represents the RSRP (Reference Signal Received Power) value of the measured cell. rxlevmin Q represents the minimum received signal level of the cell. rxlevminoffset P represents the minimum received signal level offset of the cell. compensation Qoffset is used to penalize UEs that fail to reach the cell's maximum power. temp Q represents the temporary offset. qualmeas Q represents the RSRQ (Reference Signal Received Quality) value of the measured cell. qualmin Q represents the minimum received signal quality of the cell. qualminoffset This represents the offset of the minimum received signal quality.

[0054] II. Community Re-selection

[0055] The absolute priority of different NR frequencies or inter-RAT (Inter-Radio Access Technology) frequencies is sent to the UE via system information or an RRCRelease (Radio Resource Control Release) message, or inherited from another RAT (Radio Access Technology) during inter-RAT cell reselection. When the UE is in camped on any cell state, the UE should only apply the priority provided by the current cell through system messages. The UE retains priority information provided through dedicated signaling. When the UE is in normal camping state and only has dedicated frequency priorities other than the current frequency, the UE should consider the current frequency as the lowest priority. When the UE receives an RRCRelease message containing a depriority request, the UE should consider the current frequency and stored frequencies or all NR frequencies as the lowest priority frequencies.

[0056] When a UE enters a different RRC (Radio Resource Control) state, or its dedicated priority timer (T320) expires, or the RRC Release message received by the UE does not contain cellReselectionPriorities or a NAS (Non-Access Stratum) request to perform PLMN or SNPN selection, the UE should delete the priority provided via dedicated signaling. The UE cannot consider cells in the exclude-listed list as candidate cells for cell reselection. The UE should only consider cells in the allow-listed list as candidate cells for cell reselection.

[0057] 1. Measurement criteria for cell reselection

[0058] If the serving cell satisfies Srxlev>S IntraSearchP And Squal>S IntraSearchQ If the UE does not perform intra-frequency measurement, then the UE must perform intra-frequency measurement. Wherein, S IntraSearchP and S IntraSearchQThese are preset thresholds for intra-frequency measurements. For NTN earth-fixed cells, if the UE supports location-based measurements and SIB19 (System Information Block 19) broadcasts distanceThresh and referenceLocation, in addition to the above conditions, if the distance between the UE and the serving cell reference point is lower than distanceThresh, the UE may not perform intra-frequency cell measurements. Otherwise, the UE needs to perform intra-frequency measurements. For NTN earth-moving cells, if the UE supports location-based measurements and SIB19 broadcasts distanceThresh and movingReferenceLocation, in addition to the above conditions, if the distance between the UE and the serving cell reference point is lower than distanceThresh, the UE may not perform intra-frequency cell measurements. Otherwise, the UE needs to perform intra-frequency measurements.

[0059] For high-priority frequencies, the UE needs to perform inter-frequency or inter-RAT frequency measurements. For frequencies of the same or lower priority, when the serving cell satisfies Srxlev > S nonIntraSearchP And Squal>S nonIntraSearchQ At this time, the UE does not perform measurements on cells with the same or lower priority frequency points. Among them, S nonIntraSearchP and S nonIntraSearchQThis is a preset threshold for inter-frequency measurements. Otherwise, the UE needs to perform measurements on cells with the same or lower priority frequencies. For NTN earth-fixed cells, if the UE supports location-based measurements and SIB19 broadcasts distanceThresh and referenceLocation, in addition to meeting the above conditions, the UE may not perform measurements on cells with the same or lower priority frequencies if the distance between the UE and the serving cell reference point is less than distanceThresh. Otherwise, the UE needs to perform measurements on cells with the same or lower priority frequencies. For NTN earth-moving cells, if the UE supports location-based measurements and SIB19 broadcasts distanceThresh and movingReferenceLocation, in addition to meeting the above conditions, the UE may not perform measurements on cells with the same or lower priority frequencies if the distance between the UE and the serving cell reference point is less than distanceThresh. Otherwise, the UE needs to perform measurements on cells with the same or lower priority frequencies.

[0060] If relaxedMeasurement is configured in SIB2 and the UE supports measurement relaxation, the UE can perform measurement relaxation.

[0061] For UEs camped in NTN cells, if skipping TN measurements is supported, and the UE has already obtained location information and the system message broadcasts coverageAreaInfoList and tn-AreaIdList, the UE may not perform TN frequency measurements if it is not covered by the frequencies provided by tn-AreaIdList.

[0062] When the UE supports time-based measurements and t-service is broadcast in SIB19, the UE needs to perform in-frequency or inter-frequency measurements or inter-RAT measurements before t-service, regardless of the distance between the UE and the serving cell reference point or whether the serving cell satisfies Srxlev>S. IntraSearchP And Squal>S IntraSearchQ , or Srxlev>S nonIntraSearchP And Squal>S nonIntraSearchQ The UE needs to perform measurements on high-priority frequencies regardless of how much service time remains in the serving cell.

[0063] 2. NR Inter-frequency and Inter-RAT Cell Reselection Criteria

[0064] If the system message broadcasts threshServingLowQ (serving cell quality degradation threshold) and the UE has camped on the current serving cell for more than 1 second, the UE selects a higher priority cell if: the higher priority cell satisfies for a period of time Treselection RAT that Squal>Thresh X,HighQ . Otherwise, the UE selects a higher priority cell if: the higher priority cell satisfies for a period of time Treselection RAT that Srxlev>Thresh X,HighP and the UE has camped on the current serving cell for more than 1 second.

[0065] If the system message broadcasts threshServingLowQ and the UE has camped on the current serving cell for more than 1 second, the UE selects a lower priority cell if: the serving cell Squal<ThreshServing,LowQ and the lower priority cell satisfies for a period of time Treselection RAT that Squal>Thresh X,HighQ . Otherwise, the UE selects a lower priority cell if: the serving cell Srxlev<ThreshServing,LowP and the lower priority cell satisfies for a period of time Treselection RAT that Srxlev>Thresh X,LowP and the UE has camped on the current serving cell for more than 1 second. Wherein, ThreshServing,LowQ, ThreshServing,LowP, Thresh X,LowP and Thresh X,HighQ are preset thresholds.

[0066] When multiple cells satisfy the above criteria, the UE shall reselect a cell according to the following rules:

[0067] - If the highest priority frequency is an NR frequency, the best ranked cell on this frequency needs to satisfy the following intra-frequency cell reselection criteria.

[0068] - If the highest priority frequency is from another RAT, the best ranked cell on this frequency satisfies the criteria of that RAT.

[0069] 3. Cell reselection criteria for same priority or lower priority frequency points

[0070] The cell ranking criteria for the serving cell Rs and the neighbor cell Rn are defined as follows:

[0071] R s =Qmeas,s +Q hyst -Q offsettemp

[0072] R n =Q meas,n -Q offset -Q offsettemp

[0073] Among them, R s R is used to indicate the signal quality of the serving cell. n Q is used to indicate the signal quality of cells with the same frequency and different frequencies with the same priority. meas,s Q refers to the quality of the received signal in the serving cell. hyst This refers to cell reselection delay, Q offsettemp This refers to the compensation offset value, Q. meas,n This refers to the received signal quality of cells with the same frequency and different frequencies but the same priority, Q. offset It refers to the difference in received signal quality requirements between the serving cell and cells with the same frequency and priority but different frequencies.

[0074] The UE should rank all cells that meet the S criterion according to the R criterion described above. If `rangeToBestCell` is not configured, the UE performs cell reselection to the highest-ranked cell. If this cell is unsuitable, the UE does not consider any cells on that frequency for 300 seconds. If `rangeToBestCell` is configured, the UE should perform cell reselection to the cell with the most beams exceeding the threshold. If multiple such cells exist, the UE reselects to the highest-ranked cell.

[0075] In all the above scenarios, the new cell needs to meet the reselection criteria for a certain period of time (Treselection). RAT Furthermore, the UE has been camped in the current cell for more than 1 second.

[0076] 4. UE Measurement Relaxation

[0077] Case 1: If only lowMobilityEvaluation is configured, but cellEdgeEvaluation is not configured:

[0078] If the UE reselects / selects a new cell, at least T SearchDeltaP Normal same-frequency, different-frequency, and different-RAT measurements were performed within the specified time, and in T... SearchDeltaP The relaxation conditions are met within the specified time.

[0079] The UE can then choose to perform measurement relaxation for same-frequency, different-frequency, or different-RAT cells.

[0080] Low mobility measurement relaxation conditions:

[0081] (S rxlevRef –S rxlev ) SearchDeltaP ,for a period of T SearchDeltaP

[0082] ·S rxlev It is the S value of the currently serving cell. For specific calculations, please refer to the cell selection and reselection process.

[0083] ·S rxlevRef This is the reference S value for the current serving cell. Its specific setting method is as follows: at the moment the UE completes cell selection or reselection, that is, whenever the UE completes camping in a new cell, the reference S value is assigned the current S value; then, during subsequent measurements, if the S value is greater than the reference S value, the reference S value is immediately updated to the larger current S value; if the above criterion is met, but T is not maintained... SearchDeltaP If the time is long, the reference S value should also be updated to the current S value.

[0084] ·S SearchDeltaP It is the threshold value.

[0085] Measuring relaxation behavior:

[0086] (1) Cells with the same frequency:

[0087] After meeting the above criteria, the measurement enters a relaxed state (refer to 38133 4.2.2.9 relaxation methods).

[0088] (2) High-priority inter-frequency and inter-system cells:

[0089] After meeting the above criteria, if the serving cell also meets S at this time... rxlev >S nonIntraSearchP &S qual >S nonIntraSearchQ If less than one hour has passed since the last measurement of this frequency point for the purpose of cell reselection, and the parameter highPriorityMeasRelax is configured as true, then the UE can choose not to perform a measurement on this frequency point.

[0090] The parameter highPriorityMeasRelax indicates whether the UE is allowed to perform relaxed measurements on high-priority inter-frequency and inter-system cells.

[0091] (3) Any cell with different frequency or system:​

[0092] After satisfying the above criteria, if the serving cell then satisfies S... rxlev ≤S nonIntraSearchP |S qual ≤S nonIntraSearchQ If so, the UE can choose to perform relaxed measurement at different frequency and different system frequency points. For details, please refer to relaxation methods in clauses 4.2.2.10 and 4.2.2.11 in TS 38.133.

[0093] Case 2: When the UE only has CellEdgeEvaluation configured but not LowMobilityEvaluation configured, the UE determines that it is not at the cell edge based on the following criteria:

[0094] -S rxlev >S SearchThresholdP and

[0095] -S qual >S SearchThresholdQ ,if S SearchThresholdQ is configured,

[0096] in:

[0097] -S rxlev : The RSRP measurement value of the current serving cell;

[0098] -S qual : The RSRQ measurement value of the currently serving cell.

[0099] UE measurement relaxation behavior:

[0100] (1) Cells with the same frequency:

[0101] Once the above criteria are met, the UE enters the measurement relaxation state.

[0102] (2) Any inter-frequency and inter-system cell:

[0103] After satisfying the above criteria, if S is further satisfied... rxlev ≤S nonIntraSearchP or S qual ≤S nonIntraSearchQ Then the UE can choose to relax the measurement of different frequency and different system frequency points.

[0104] Case 3: Both lowMobilityEvaluation and cellEdgeEvaluation are configured:

[0105] (1) Simultaneously satisfy the Low mobility and Not celledge criteria:

[0106] For any frequency point, including those on the same frequency, different frequencies, and different systems, once the above two measurement relaxation criteria are met, the UE can choose not to perform measurements on the frequency points that meet the conditions, as long as less than one hour has passed since the last cell selection or reselection, thereby achieving the purpose of measurement relaxation.

[0107] (2) Only one of them is satisfied (it can be any one of them):

[0108] If only one criterion is met, and the parameter combineRelaxedMeasCondition is not configured, the UE can relax the measurement for intra-frequency cells, inter-frequency cells with the same or lower priority, and inter-system cells with lower priority.

[0109] If S is further satisfied at this point rxlev ≤S nonIntraSearchP or S qual ≤S nonIntraSearchQ Then the UE can relax the measurement for high-priority inter-frequency and inter-system cells.

[0110] The parameter `combineRelaxedMeasCondition` indicates whether the UE needs to meet two criteria simultaneously. If this parameter is configured in the network, the UE needs to meet both criteria simultaneously to enter measurement relaxation.

[0111] III. RRM Measurement

[0112] RRM measurement model (definitions of beam-level and cell-level measurements, and the relationship between L1 and L3 measurements)

[0113] Figure 2 shows a schematic diagram of an RRM measurement model provided in one embodiment of this application. RSRP is used as an example here, and the relevant content also applies to RSRQ / SINR:

[0114] Reference point A: This is the physical layer measurement sampling step performed by the terminal equipment, according to the beam granularity. The result is beam level L1-RSRP.

[0115] Reference point A1: The terminal equipment performs L1 filtering on the measured beam measurement results. Generally, the protocol specifies the length of the measurement period under a specific RRC configuration. The measurement period stipulates that the terminal equipment must perform at least one sampling, and the beam measurement results after L1 filtering must meet the performance requirements specified in 3GPP specification 38.133. The specific number of samplings by the terminal equipment within one measurement period at reference point A is specified. In the test example, 4 to 5 oversamplings are generally used. This yields the filtered beam-level L1-RSRP.

[0116] Reference point B: The beam measurement results obtained at reference point A1 within a certain cell are merged to synthesize the L1 cell-level measurement results, resulting in cell-level L1-RSRP.

[0117] Reference point C: The L1 cell-level measurement results of a certain cell are filtered through L3 in sequence to obtain the L3 cell-level measurement results, i.e., cell-level L3-RSRP.

[0118] Reference point E: The filtered L3 beam result yields the L3 beam-level RSRP.

[0119] Reference point F: Selected L3 beam-level RSRPs that are reported.

[0120] IV. Artificial Intelligence (AI)

[0121] Current research on AI has demonstrated its powerful predictive capabilities. Therefore, the 3GPP (3rd Generation Partnership Project) working group has been working on combining AI with communication technologies in order to better serve communication systems. According to current research and evaluation, the combination of AI and communication technologies has been shown to bring about significant performance improvements.

[0122] Figure 3 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).

[0123] Currently, when a UE performs RRM measurements, the need to continuously perform a large number of measurements increases UE power consumption. Although some conditions for relaxing UE measurement execution have been defined, these conditions are complex and their application scenarios are limited, resulting in limited energy savings for the UE. Current AI models can make relatively good predictions, but AI has not yet been incorporated into the RRM measurement process.

[0124] Please refer to Figure 4, which shows a flowchart of a wireless measurement method provided in one embodiment of this application. This method can be applied to the network architecture shown in Figure 1. The method may include the following step 420.

[0125] Step 420: The network device sends first information, which is used to determine relevant information of the AI ​​model. The AI ​​model is used to assist in RRM measurement.

[0126] Accordingly, the terminal device receives the first information.

[0127] In some embodiments, the first information includes information related to the AI ​​model. In some embodiments, the terminal device obtains the information related to the AI ​​model based on the first information. Optionally, the first information is used to indicate the storage location of the information related to the AI ​​model.

[0128] AI models have the ability to infer and predict RRM measurements through artificial intelligence or machine learning to assist in RRM measurement. 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.

[0129] RRM measurement refers to the process by which a terminal device performs quality measurements on 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.

[0130] In some embodiments, the reference signal may include, but is not limited to, at least one of the following: SSB (Synchronization Signal Block), CSI-RS (Channel State Information Reference Signal), DMRS (Demodulation Reference Signal), or Low Power-Synchronization Signal (LP-SS). The LP-SS is used by low-power terminal devices to perform wireless measurements. Measurement results include, but are not limited to, at least one of the following: RSRP, RSRQ, SINR, and RSSI.

[0131] The information related to an AI model refers to the data and attributes that maintain the normal operation of the AI ​​model. In some embodiments, the information related to the AI ​​model is related to at least one of the following: input information, output information, model type, etc., and may also be related to other aspects, which are not limited in this application embodiment.

[0132] In some embodiments, the network device sends the first information to the terminal device in at least one of the following ways.

[0133] (1) The network device sends a system broadcast message, which includes the first information.

[0134] Accordingly, the terminal device receives system broadcast messages sent by the network device.

[0135] System broadcast messages are system messages sent by network devices via broadcast. In some embodiments, system messages include, but are not limited to, at least one of the following: MIB (Master Information Block) messages and SIB messages. In some embodiments, network devices broadcast system broadcast messages in two ways: periodic broadcasting and on-demand broadcasting. Periodic broadcasting refers to network devices broadcasting system messages according to a preset period. On-demand broadcasting refers to network devices broadcasting system messages when requested by terminal devices or triggered by specific events.

[0136] In some embodiments, the terminal device obtains the first information by directly reading system broadcast messages sent by the network device.

[0137] In some embodiments, the terminal device sends a model request to the network device, the model request being used to request the network device to send relevant information about the AI ​​model. Correspondingly, the network device receives the model request sent by the terminal device; the network device then sends first information to the terminal device.

[0138] In some embodiments, when a terminal device is camped in a cell that supports AI model-assisted RRM measurement, the terminal device receives a system broadcast message sent by a network device. In some embodiments, different cells may support the same or different AI models. In some embodiments, cells belonging to the same AI measurement range support the same AI model. The AI ​​measurement range refers to the range that supports AI model-assisted RRM measurement. In some embodiments, different AI model measurement ranges correspond to different AI models.

[0139] In some embodiments, when a terminal device switches from a first cell to a second cell, and the first and second cells are not within the same AI measurement range, the terminal device reacquires the first information. That is, when the terminal device switches from the first cell to the second cell, but the first and second cells are still within the same AI measurement range, it is not necessary to reacquire the first information. It should be noted that the first cell and the second cell can be any two different cells.

[0140] The above method sends the first message by sending a system broadcast message through network devices, avoiding the signaling overhead of point-to-point communication and helping to improve the efficiency of deploying AI models.

[0141] (2) The network device sends a first dedicated signaling message, which includes the first information.

[0142] Accordingly, the terminal device receives the first dedicated signaling sent by the network device.

[0143] The first dedicated signaling is a signaling resource allocated for a specific terminal device or specific needs, used to carry first information. The network device sends the first information to the specific terminal device through the first dedicated signaling. Optionally, the specific terminal device can be any terminal device served by the network device, and this application embodiment does not limit this. Specific needs refer to the need for AI model-assisted RRM measurement. Exemplarily, the first dedicated signaling is a signaling resource allocated for implementing AI-assisted RRM measurement.

[0144] In some embodiments, the first dedicated signaling may be an RRC reconfiguration message or an RRC release message.

[0145] RRC reconfiguration messages are used to dynamically adjust the communication configuration of terminal devices. In some embodiments, RRC reconfiguration messages include, but are not limited to, at least one of the following functions: handover management, carrier aggregation, measurement configuration update, radio bearer adjustment, etc., and may also include other functions, which are not limited in this application embodiment. In this application, when the first dedicated signaling is an RRC reconfiguration message, the network device sends first information to the terminal device through the measurement configuration update function of the RRC reconfiguration message.

[0146] The RRC release message is used to actively release the RRC connection of a terminal device, causing the terminal device to switch from the RRC connected state to the RRC disconnected state. The RRC disconnected state includes the RRC idle state and the RRC inactive state. In this case, while the network device uses the RRC release message to switch the terminal device from the RRC connected state to the RRC disconnected state, it also sends the first information to the terminal device, enabling the terminal device to load and deploy the AI ​​device while in the disconnected state. When the terminal device begins to perform RRM measurements, the AI ​​model can be used to assist in the RRM measurement.

[0147] In some embodiments, when the terminal device is in a connected state, the network device actively sends a first dedicated signaling to the terminal device.

[0148] In some embodiments, when the terminal device is in a connected state, the terminal device sends a model request to the network device. In some embodiments, the network device receives the model request sent by the terminal device in the connected state; the network device sends a first dedicated signaling to the terminal device in the connected state.

[0149] The above method, which sends the first information through dedicated signaling, helps to ensure the security and privacy of information related to the AI ​​model and avoids the leakage of sensitive information.

[0150] (3) The network device sends a second dedicated signaling message, which includes the server's address information. The server's address information is used to obtain the first information from the server.

[0151] Accordingly, the terminal device receives the second dedicated signaling sent by the network device.

[0152] The second dedicated signaling is a signaling resource allocated for a specific terminal device or specific needs, used to carry the server's address information. The server's address information is used to uniquely identify the server. The server refers to a server that stores AI models or trains AI models. In some embodiments, the server's address information may include, but is not limited to, at least one of the following: IP (Internet Protocol) address, domain name, port number, MAC (Media Access Control) address, etc., and may also include other addresses, which are not limited in this application embodiment.

[0153] In some embodiments, the terminal device obtains first information from the server based on the server's address information. In some embodiments, the second dedicated signaling further includes second information, which is used to instruct the AI ​​model. In some embodiments, the terminal device obtains first information from the server based on the server's address information and the second information.

[0154] The above method sends the address information of the server storing the first information through dedicated signaling. The terminal device obtains the first information from the server based on the address information, which helps to ensure the security and privacy of the AI ​​model's related information and avoids the leakage of sensitive information.

[0155] In some embodiments, as shown in FIG5, a wireless measurement method provided by another embodiment of this application is illustrated, which further includes step 410 before step 420.

[0156] Step 410: When the terminal device is in a connected state, the terminal device sends capability information to the network device. The capability information is used to indicate whether the terminal device supports the ability to use AI model to assist in RRM measurement.

[0157] Accordingly, the network device receives capability information sent by the terminal device in the connected state.

[0158] A terminal device being in a connected state 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. In some embodiments, the connected state is an RRC connected state. Whether the terminal device supports the use of AI models to assist in RRM measurement refers to whether the terminal device has the capability to use AI models to assist in RRM measurement.

[0159] In some embodiments, capability information occupies 1 bit. In some embodiments, a capability information value of 1 indicates that the terminal device has the capability to support RRM measurement using an AI model, and a capability information value of 0 indicates that the terminal device does not have the capability to support RRM measurement using an AI model; or, a capability information value of 1 indicates that the terminal device does not have the capability to support RRM measurement using an AI model, and a capability information value of 0 indicates that the terminal device has the capability to support RRM measurement using an AI model.

[0160] In some embodiments, when a network device receives capability information from a terminal device in a connected state, it determines that the terminal device has the capability to support RRM measurement using an AI model. That is, if the network device does not receive capability information from a terminal device in a connected state, the network device determines that the terminal device does not have the capability to support RRM measurement using an AI model.

[0161] In some embodiments, the network device determines whether to send first information to the terminal device based on capability information. For example, if the capability information sent by the terminal device indicates that the terminal device has the capability to support RRM measurement using an AI model, the network device sends the first information to the terminal device. For example, if the capability information sent by the terminal device indicates that the terminal device does not have the capability to support RRM measurement using an AI model, the network device does not send the first information to the terminal device.

[0162] The technical solution provided in this application embodiment involves a network device sending first information to a terminal device to indicate relevant information about an AI model. This allows the terminal device to use the AI ​​model to assist in RRM measurement and implement some RRM measurement logic. This reduces the complexity of performing RRM measurements and also reduces the number of RRM measurements performed, thereby reducing the power consumption of the terminal device due to RRM measurement.

[0163] The following section introduces relevant information about AI models.

[0164] In some embodiments, the relevant information of the AI ​​model includes at least one of the following.

[0165] (1) Instructions from the AI ​​model.

[0166] The indication information of the AI ​​model is used to indicate the function of the AI ​​model. In some embodiments, the indication information of the AI ​​model is used to indicate that the AI ​​model is used to assist in RRM measurement.

[0167] In some embodiments, the indication information includes function identification information, which is used to distinguish the functions of different RRM measurements. In some embodiments, the functions of different RRM measurements correspond to different function identification information. In some embodiments, the functions of RRM measurements may include, but are not limited to, at least one of the following: cell selection, cell reselection, RRM relaxation measurement, cell handover, load balancing, etc., and may also include other functions, which are not limited in this application embodiment. Cell selection is the process by which a terminal device selects a suitable cell for initial access. Cell reselection is the process by which a terminal device actively selects a cell with better channel quality to camp on. RRM relaxation measurement refers to the process by which a terminal device reduces or adjusts the frequency or strictness of RRM measurements. Cell handover refers to the process by which a terminal device seamlessly switches between different cells when it is in a connected state. Load balancing refers to the process of distributing terminal devices among multiple cells to avoid cell overload.

[0168] (2) Model data of AI models.

[0169] The model data of an AI model refers to the data upon which the AI ​​model depends for its operation. In some embodiments, the model data may include, but is not limited to, at least one of the following: AI model files, model parameters, runtime code, environment dependencies, etc., and may also include other model data, which are not limited in this application embodiment. The AI ​​model file is used to store the trained AI model. Model parameters are weights or biases obtained after the AI ​​model is trained. Runtime code is used to load and run the AI ​​model. Environment dependencies include various components that enable the AI ​​model to function properly. In some embodiments, environment dependencies may include, but are not limited to, at least one of the following: programming languages, mathematical libraries, computing libraries, APIs (Application Programming Interfaces), etc., and may also include other components, which are not limited in this application embodiment.

[0170] In some embodiments, the model data of the AI ​​model is encapsulated in the form of a container. A container is a data pass-through pattern used to encapsulate the complete model data of the AI ​​model within a container, enabling transparent forwarding of the AI ​​model's model data.

[0171] (3) Indication information indicating whether the AI ​​model is activated.

[0172] Whether an AI model is activated refers to whether the AI ​​model deployed in the terminal device can assist in RRM measurement.

[0173] (4) Effective area information of AI model.

[0174] The effective area information of the AI ​​model is used to indicate the effective area where the AI ​​model can be used to assist in RRM measurement. In some embodiments, the effective area information of the AI ​​model is used to indicate the AI ​​measurement range mentioned above. In some embodiments, different effective areas correspond to different AI models. In some embodiments, the effective area information of the AI ​​model may include, but is not limited to, at least one of the following: PLMN, PLMN list, TAC (Tracking Area Code), TAC list, RNA (RAN-based Notification Area), cell list, etc., and may also include other information, which is not limited in this application embodiment.

[0175] (5) Configuration information of AI model.

[0176] The configuration information for the AI ​​model is used to indicate the relevant configurations for using the AI ​​model for RRM measurements.

[0177] In the above method, the terminal device determines various information for using the AI ​​model to assist in RRM measurement based on the first information, so as to ensure that the AI ​​model is correctly deployed in the terminal device, thereby using the AI ​​model to assist in RRM measurement to reduce the power consumption of the terminal device caused by RRM measurement.

[0178] The following describes the configuration information for the AI ​​model.

[0179] In some embodiments, the configuration information of the AI ​​model is used to determine at least one of the following.

[0180] 1) Triggering conditions for using AI models to assist in RRM measurement.

[0181] The triggering conditions for using AI model-assisted RRM measurement are used to determine when to enable AI model-assisted RRM measurement. AI model-assisted RRM measurement is only enabled when the terminal device meets the triggering conditions.

[0182] In some embodiments, the triggering conditions for using AI models to assist RRM measurements include at least one of the following.

[0183] 1. The terminal device receives an instruction to activate the AI ​​model.

[0184] 2. The terminal device is within the effective area of ​​the AI ​​model.

[0185] 3. The AI ​​model is effective.

[0186] 4. The signal quality of the serving cell of the terminal device is greater than the first threshold.

[0187] 5. The signal quality of the neighboring cell of the terminal device is greater than the second threshold.

[0188] 6. The moving speed of the terminal device is less than the third threshold.

[0189] 7. The distance between the terminal device and the reference point is less than the fourth threshold.

[0190] In some embodiments, the network device sends an instruction to the terminal device to activate the AI ​​model via broadcast. In some embodiments, the network device sends the instruction to the terminal device to activate the AI ​​model when the activation conditions are met. In some embodiments, the activation conditions are used to determine whether to enable AI model-assisted RRM measurement. For example, the activation conditions are related to at least one of the following: network device load, signal quality, spectrum congestion level, etc., and may also be related to other aspects, which are not limited in this application embodiment.

[0191] In some embodiments, the AI ​​model deployed on the terminal device is effective only if the terminal device is located within the effective area corresponding to the AI ​​model. An effective AI model means that the terminal device can use the AI ​​model to assist in RRM measurements. Due to the mobility of the terminal device, it may switch cells during movement. That is, during movement, the terminal device may leave the effective area corresponding to the deployed AI model. When the terminal device leaves the effective area corresponding to the deployed AI model, the AI ​​model deployed on the terminal device is determined to be invalid. In other words, the terminal device cannot use the currently deployed AI model to assist in RRM measurements.

[0192] An effective AI model means that the AI ​​model deployed on the terminal device is effective, meaning the terminal device can use the AI ​​model deployed on it to assist in RRM measurement. An invalid AI model means that the AI ​​model deployed on the terminal device is ineffective, meaning the terminal device cannot use the AI ​​model deployed on it to assist in RRM measurement.

[0193] For instructions on how to determine whether an AI model is effective or ineffective, please refer to the explanation below.

[0194] The serving cell is the cell currently providing service to the terminal device. The signal quality of the serving cell refers to the radio signal status of the cell to which the terminal device is currently connected, used to measure the communication quality of that cell. In some embodiments, the terminal device evaluates the signal quality of the serving cell through wireless measurement. In some embodiments, the terminal device performs wireless measurements on the serving cell to obtain measurement results for the serving cell, which are used to measure the signal quality of the serving cell. Wireless measurement can be downlink wireless measurement, i.e., the terminal device measures the reception quality of downlink signals transmitted by the network device. Optionally, wireless measurement can be RRM measurement, RLM (Radio Link Monitoring) measurement, BFD (Beam Failure Detection) measurement, etc., and other wireless measurements are also possible; this application embodiment does not limit this.

[0195] In some embodiments, the downlink signal includes, but is not limited to, at least one of the following: SSB, CSI-RS, DMRS, LP-SS. In some embodiments, signal quality can be evaluated by at least one of the following: RSRP, RSRQ, SINR, RSSI.

[0196] When the signal quality of the terminal device in the serving cell is greater than a first threshold, it indicates that the current wireless signal condition of the serving cell is good, and an AI model can be used to assist in RRM measurement for the serving cell. When the signal quality of the terminal device in the serving cell is less than the first threshold, it indicates that the current wireless signal condition of the serving cell is poor, and an AI model is not used to assist in RRM measurement for the serving cell. In some embodiments, the first threshold is configured by the network device or predefined by the protocol.

[0197] A neighboring cell refers to a cell adjacent to the serving cell. The signal quality of a neighboring cell refers to the radio signal status of the cells adjacent to the serving cell, and is used to measure the communication quality of the neighboring cell. In some embodiments, the terminal device evaluates the signal quality of the neighboring cell through wireless measurements.

[0198] When the signal quality of the terminal device in a neighboring cell is greater than a second threshold, it indicates that the current wireless signal condition of the neighboring cell is good, and an AI model can be used to assist in RRM measurement for the neighboring cell. When the signal quality of the terminal device in a neighboring cell is less than the second threshold, it indicates that the current wireless signal condition of the neighboring cell is poor, and an AI model is not used to assist in RRM measurement for the neighboring cell. In some embodiments, the second threshold is configured by the network device or predefined by the protocol.

[0199] The moving speed of a terminal device is used to measure the mobility of a mobile device. In some embodiments, the moving speed of a terminal device is measured by at least one of the following methods: Doppler frequency shift, cell dwell time, handover frequency, global navigation satellite system, etc. Other methods for measuring the moving speed of a terminal device may also be included, which are not limited in this application embodiment.

[0200] A reference point is a benchmark used for time synchronization and distance calculation. The distance between the terminal device and the reference point of the serving cell refers to the physical distance between the terminal device and the reference point. In some embodiments, the terminal device supports NTN scenarios. In some embodiments, in NTN scenarios, the reference point is a synchronization node of the satellite and terrestrial network interface. In some embodiments, the reference point may include, but is not limited to, at least one of the following: satellite, terrestrial base station, relay node, UAV base station, etc., and may also include other reference points, which are not limited in this application embodiment.

[0201] It should be noted that the triggering conditions for using AI models to assist in RRM measurement may include one or more of the above conditions.

[0202] The above method uses different trigger conditions to activate the AI ​​model to assist in RRM measurement. The AI ​​model is only used to assist in RRM measurement when the trigger conditions are met, thus avoiding the use of the AI ​​model to assist in RRM measurement at inappropriate times, which could lead to inaccurate RRM measurement results.

[0203] 2) SMTC (SSB Measurement Timing Configuration) using AI models to assist RRM measurements.

[0204] The SMTC (Measurement Window Control) is used to indicate the time window during which the terminal device performs RRM measurements for SSBs. The SMTC using AI model-assisted RRM measurement refers to an SMTC specific to the AI ​​model, used to indicate the time window during which the terminal device performs RRM measurements for SSBs when using an AI model to assist in RRM measurement. In some embodiments, the SMTC may include, but is not limited to, at least one of the following: measurement period, measurement window length, number of SSBs, number of neighboring cells, measurement window offset, reference window, etc., and may also include other configurations, which are not limited in this application embodiment. The measurement period indicates the time interval between any two measurement windows. The measurement window refers to the time window during which the terminal device performs RRM. The measurement window length indicates the duration of the measurement window. The number of SSBs refers to the number of SSBs measured by the terminal device within a single measurement window. The number of neighboring cells refers to the number of neighboring cells measured by the terminal device within a single measurement window. The measurement window offset refers to the offset of the measurement window relative to the reference window.

[0205] In some embodiments, RRM measurements assisted by AI models can be implemented using different SMTCs. In some embodiments, the relevant information of the AI ​​model includes one or more different SMTCs, for example, different SMTCs applied to the functionality of different RRM measurements.

[0206] In some embodiments, SMTCs measured using AI models to assist RRM measurements satisfy at least one of the following conditions compared to SMTCs measured without AI models to assist RRM measurements.

[0207] 1. Longer measurement cycle.

[0208] 2. The measurement window length is smaller.

[0209] 3. Fewer SSBs were measured.

[0210] 4. Fewer neighboring cells were measured.

[0211] Not using AI models to assist in RRM measurement refers to normal RRM measurement.

[0212] A longer measurement cycle refers to a measurement cycle when using an AI model to assist in RRM measurement, which is longer than that when not using an AI model to assist in RRM measurement. For example, the normal RRM measurement cycle is 40ms, while the measurement cycle when using an AI model to assist in RRM measurement is greater than 40ms, such as 320ms, 640ms, or a larger value.

[0213] A smaller measurement window length means that the measurement window length for RRM measurements using an AI model is shorter than the measurement window length for RRM measurements without an AI model. For example, the measurement window length for normal RRM measurements is 1 ms, while the measurement period length for RRM measurements using an AI model is greater than 1 ms, such as 10 ms, 20 ms, or a larger value.

[0214] Fewer SSBs measured means that the number of SSBs measured using AI model-assisted RRM is less than the number measured without AI model-assisted RRM. For example, a normal RRM measurement involves 24 SSBs, while an AI model-assisted RRM measurement involves fewer than 24 SSBs, such as 14, 8, or even fewer. For example, in normal RRM measurement, all SSBs are measured for a cell; in AI model-assisted RRM measurement, only a subset of SSBs are measured for a cell.

[0215] Fewer neighboring cells measured means that the number of neighboring cells measured using the AI ​​model-assisted RRM measurement is less than the number of neighboring cells measured without the AI ​​model-assisted RRM measurement. For example, when using normal RRM measurement, RRM measurement is performed on all neighboring cells, while when using AI model-assisted RRM measurement, RRM measurement is performed on a subset of neighboring cells.

[0216] The above method, by configuring a dedicated SMTC for the AI ​​model, enables the terminal device to reduce the frequency of RRM measurements when using the AI ​​model to assist in RRM measurements, thereby reducing the power consumption of the terminal device due to performing RRM measurements.

[0217] 3) Use AI models to assist in the measurement of relaxation factors in RRM measurement.

[0218] The measurement relaxation factor is used to determine the measurement cycle for AI model-assisted RRM measurements. The measurement relaxation factor indicates the extent to which the measurement cycle for AI model-assisted RRM measurements is increased compared to performing normal RRM measurements. Normal RRM measurements refer to RRM measurements performed at a preset measurement cycle. In some embodiments, the preset measurement cycle is specified by network device configuration or related protocols.

[0219] In some embodiments, the measurement of relaxation factors using AI model-assisted RRM measurements includes:

[0220] 1. Measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device.

[0221] 2. The measurement relaxation factor shared by the serving cell and neighboring cells of the terminal equipment.

[0222] In some embodiments, the measurement relaxation factor corresponding to the serving cell of the terminal device and the measurement relaxation factor corresponding to the neighboring cell may be the same or different. The measurement relaxation factor of the serving cell is used to determine the measurement cycle when using AI model-assisted RRM measurement on the serving cell. The measurement relaxation factor of the neighboring cell is used to determine the measurement cycle when using AI model-assisted RRM measurement on the neighboring cell.

[0223] For example, the serving cell and neighboring cells can use different values ​​such as (K1, K2), where K1 represents the measurement relaxation factor corresponding to the serving cell and K2 represents the measurement relaxation factor corresponding to the neighboring cell. K1 and K2 are not equal and are greater than 0.

[0224] For example, the serving cell and neighboring cells can use the same measurement relaxation factor K, where K is greater than 0.

[0225] In some embodiments, the measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device, respectively, or the measurement relaxation factors shared by the serving cell and neighboring cells of the terminal device, are output by the AI ​​model. In some embodiments, when using the measurement relaxation factors output by the AI ​​model, the measurement relaxation factors configured by the network device are ignored. That is, when performing RRM measurements using the measurement relaxation factors output by the AI ​​model, the measurement relaxation factors configured by the network device are not used.

[0226] The above method allows for adjustment of the RRM measurement cycle by adjusting the measurement relaxation factor when using an AI model to assist in RRM measurement. This helps to flexibly adjust the RRM measurement cycle and reduce the power consumption of the terminal device.

[0227] 4) Configure prediction results for RRM measurement using AI models.

[0228] The prediction result configuration for AI model-assisted RRM measurement is used to indicate what the AI ​​model predicts for the RRM measurement. In some embodiments, the prediction result configuration for AI model-assisted RRM measurement includes a first prediction duration for predicting the measurement result of the RRM measurement. The first prediction duration is used to indicate the duration of the measurement result of the RRM measurement predicted by the AI ​​model after a first time point. The first time point is the current time point.

[0229] For example, when using an AI model to assist in RRM measurement by predicting the measurement results over a future period, the configuration of the prediction results for AI model-assisted RRM measurement includes the future duration T2 of the prediction results, that is, the prediction of the RRM measurement results from the current moment to the future duration T2. ​​Here, T2 is greater than 0.

[0230] In some embodiments, the content predicted by the AI ​​model may include, but is not limited to, at least one of the following: cells measured by RRM, measurement period, measurement window length, number of SSBs, number of neighboring cells, etc., and may also include other configurations, which are not limited in this application example.

[0231] 5) Cells using AI models to assist in RRM measurements.

[0232] In some embodiments, the cells for which AI model-assisted measurement is used may include the serving cell and / or neighboring cells.

[0233] In some embodiments, the cell for which AI model-assisted RRM measurement is used includes: a cell identifier for the cell for which AI model-assisted RRM measurement is used. The cell identifier information is used to uniquely identify the cell.

[0234] In some embodiments, the 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. This application embodiment does not limit this.

[0235] 6) Validation configuration before using the AI ​​model.

[0236] Validation refers to verifying the effectiveness of an AI model to determine if it can function properly. Before an AI model is used, its effectiveness needs to be verified.

[0237] In some embodiments, the validity verification configuration prior to using the AI ​​model includes at least one of the following.

[0238] 1. Measurement duration for the terminal device to perform validity verification.

[0239] 2. The error threshold between the actual measurement results of the terminal device and the predicted measurement results obtained by the AI ​​model.

[0240] 3. The total number of times the terminal device performs validity verification.

[0241] 4. Threshold for the number of valid attempts to perform validity verification on the terminal device.

[0242] 5. Threshold for the percentage of valid validation attempts performed by the terminal device out of the total number of validation attempts.

[0243] 6. Configuration information for re-executing validity verification when the AI ​​model is invalid.

[0244] The measurement duration for terminal devices to perform validity verification refers to the continuous time spent validating the AI ​​model before using it. By continuously validating the AI ​​model within the measurement duration, it can be ensured that the prediction results of the AI ​​model are stable and reliable over a period of time.

[0245] The actual measurement result of the terminal device refers to the predicted result obtained without using the AI ​​model to assist in RRM measurement. The predicted measurement result obtained by the AI ​​model refers to the measurement result of the RRM measurement directly predicted by the AI ​​model. The terminal device determines whether the predicted measurement result of the AI ​​model for the RRM measurement is accurate based on the error between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model. An error threshold is used to measure whether the predicted measurement result obtained by the AI ​​model is accurate. When the error between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model is less than the error threshold, it is determined that the predicted measurement result obtained by the AI ​​model is relatively accurate, and it can also be determined that the AI ​​model has been successfully verified. When the error between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model is greater than the error threshold, it is determined that the predicted measurement result obtained by the AI ​​model is inaccurate, and it can also be determined that the AI ​​model has failed to verify. In some embodiments, the error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model is pre-configured by the network device or implemented by the terminal device. In some embodiments, the predicted measurement result obtained by the AI ​​model is predicted by the AI ​​model based on the actual prediction result.

[0246] The total number of validity verifications performed by the terminal device refers to the number of times the terminal device verifies the validity of the AI ​​model before using it. In some embodiments, the total number of validity verifications performed by the terminal device is the number of times the validity of the AI ​​model is verified within the measurement period of the validity verification performed by the terminal device. In some embodiments, the total number of validity verifications performed by the terminal device is pre-configured by the network device or implemented by the terminal device.

[0247] The number of valid validation attempts performed by the terminal device refers to the number of times the terminal device determines the AI ​​model to be valid after validating it. The terminal device determines whether the AI ​​model has been successfully validated based on the number of valid validation attempts performed. If the number of valid validation attempts performed by the terminal device exceeds a threshold value, the AI ​​model is considered successfully validated. If the number of valid validation attempts performed by the terminal device is less than the threshold value, the AI ​​model is considered to have failed. In some embodiments, the threshold value for the number of valid validation attempts performed by the terminal device is pre-configured by the network device or implemented by the terminal device.

[0248] In some embodiments, the terminal device determines the ratio of the number of valid validation attempts performed by the terminal device to the total number of validation attempts as the percentage of valid validation attempts to the total number of validation attempts. The terminal device determines whether the AI ​​model has been successfully validated based on this percentage. If the percentage of valid validation attempts to the total number of validation attempts is greater than a threshold value, the AI ​​model is considered successfully validated. If the percentage is less than the threshold value, the AI ​​model is considered to have failed to validate. In some embodiments, the threshold value for the percentage of valid validation attempts is pre-configured by the network device or implemented by the terminal device.

[0249] The configuration information for re-performing validity verification refers to the configuration information for re-performing validity verification on the AI ​​model when it is determined to be invalid. In some embodiments, the configuration information for re-performing validity verification includes at least one of the following: a set duration, a threshold for the number of consecutive invalid validity verifications performed by the terminal device, and a threshold for the number of invalid validity verifications performed by the terminal device within a preset time period. The set duration refers to the time interval between determining that the AI ​​model is invalid and re-performing validity verification. In some embodiments, the waiting time of the terminal device is pre-configured by the network device or implemented by the terminal device.

[0250] In some embodiments, if the AI ​​model is invalid, the terminal device may, based on the configuration information for re-performing the validity verification, not perform the validity verification for the AI ​​model for a set period of time, and / or, perform the validity verification for the AI ​​model again after the set period of time.

[0251] In some embodiments, if the AI ​​model is invalid, the terminal device starts a first timer; during the operation of the first timer, the terminal device does not perform validity verification for the AI ​​model; and / or, after the first timer stops running, the terminal device performs validity verification for the AI ​​model again.

[0252] The number of consecutive invalid validation attempts performed by the terminal device refers to the number of times the terminal device performs validity validation if the AI ​​model is found to be valid after multiple consecutive validation attempts. The terminal device determines whether the AI ​​model has been successfully validated based on this number of consecutive invalid validation attempts. If the number of consecutive invalid validation attempts exceeds a threshold, the AI ​​model validation is deemed to have failed. If the number of consecutive invalid validation attempts is less than the threshold, the validity validation is re-performed. In some embodiments, the number of consecutive invalid validation attempts is pre-configured by the network device or implemented by the terminal device.

[0253] The number of times the terminal device performs invalid validity verification within a preset time period refers to the number of times the terminal device performs validity verification on the AI ​​model within the preset time period and determines that the AI ​​model is invalid. The terminal device determines whether the AI ​​model verification is successful based on the number of invalid validity verifications performed within the preset time period. When the number of invalid validity verifications performed by the terminal device within the preset time period exceeds a threshold, the AI ​​model verification is determined to have failed. When the number of invalid validity verifications performed by the terminal device within the preset time period is less than the threshold, the validity verification is re-performed. In some embodiments, the threshold for the number of invalid validity verifications performed by the terminal device within the preset time period and the preset time period are pre-configured by the network device or implemented by the terminal device.

[0254] In some embodiments, the terminal device may determine whether the AI ​​model is effective based on one or more of the above validity configurations.

[0255] The above approach, by configuring multiple validation conditions for the validity verification of the AI ​​model before its use, ensures the validity of the AI ​​model when it is used, thereby reducing the risk of the AI ​​model making incorrect decisions in RRM measurement.

[0256] 7) Validation configuration during the use of AI models.

[0257] During the use of AI models, it is also necessary to verify their effectiveness.

[0258] In some embodiments, the validity verification configuration used in the AI ​​model process includes at least one of the following.

[0259] 1. Configure periodic validity verification.

[0260] Periodic validity verification refers to the process of performing validity verification on the AI ​​model according to a preset period during the use of AI model-assisted RRM measurement.

[0261] In some embodiments, the configuration for performing periodic validity verification includes at least one of the following.

[0262] (a) The cycle of periodic validity verification.

[0263] (b) Measurement duration for periodic validity verification.

[0264] (c) Measurement of relaxation factor for periodic validity verification.

[0265] (d) SMTC for periodic validity verification.

[0266] (e) Configuration of prediction results for periodic validity verification.

[0267] The periodic validity verification period is the time interval between two consecutive validity verifications performed on the AI ​​model. For example, assuming the periodic validity verification period is T4, if the terminal device performs a validity verification on the AI ​​model at time T0, then the terminal device will perform a validity verification on the AI ​​model again at time T0+T4. Here, T0 is greater than or equal to 0, and T4 is greater than 0.

[0268] The measurement duration of periodic validity verification is the continuous duration for which the terminal device performs periodic validity verification on the AI ​​model. In some embodiments, the measurement duration of periodic validity verification is the continuous duration of performing a single periodic validity verification. In some embodiments, the measurement duration of periodic validity verification refers to the continuous duration of performing multiple periodic validity verifications.

[0269] The measurement relaxation factor for periodic validity verification is used to determine the measurement cycle for RRM measurements using AI model-assisted measurement during the periodic validity verification process. In some embodiments, the measurement relaxation factor using periodic validity verification and the measurement relaxation factor without periodic validity verification may be the same or different.

[0270] The periodic validity verification SMTC is used to indicate the time window during which the terminal device performs RRM measurements against the SSB during the periodic validity verification process. In some embodiments, the periodic validity verification SMTC and the RRM measurement SMCT using an AI model can be the same or different.

[0271] The prediction result configuration for periodic validity verification is used to indicate what the AI ​​model predicts for RRM measurements during periodic validity verification. In some embodiments, the prediction result configuration for periodic validity verification includes a second prediction duration for predicting the measurement result of the RRM measurement. The second prediction duration indicates the duration for which the AI ​​model predicts the measurement result of the RRM measurement after a second time point. The second time point is the current time point. In some embodiments, the prediction result configuration for periodic validity verification and the prediction result configuration for RRM measurements assisted by the AI ​​model may be the same or different.

[0272] For example, in the case of predicting measurement results over a future period during periodic validity verification, the prediction result configuration for periodic validity verification includes the future duration T2 of the predicted result, which is the predicted measurement result of RRM measurements continuing for a future duration T2 from the current moment. Here, T2 is greater than 0.

[0273] The above approach, by setting up periodic verification during the use of the AI ​​model, helps to continuously monitor the effectiveness of the AI ​​model and avoid the AI ​​model becoming invalid when performing RRM measurements, thus affecting the measurement results of the RRM measurement.

[0274] 2. Configure the validity verification of the event-triggered event.

[0275] Event-triggered validity verification refers to the validation of the AI ​​model by triggering a specified event during the process of using an AI model to assist in RRM measurement. The specified event is a pre-defined event used to trigger the validity verification.

[0276] In some embodiments, the configuration for performing event-triggered validity verification includes at least one of the following events.

[0277] (a) The terminal device selects or reselects a new cell.

[0278] (b) The terminal device enters the state of residing in any cell.

[0279] (c) The signal quality of the serving cell of the terminal device is less than the fifth threshold.

[0280] (d) The terminal device failed to initiate random access.

[0281] For event (a), which occurs when a terminal device connects to a new cell, the validity of the AI ​​model needs to be re-verified. This is because when connecting to a new cell, the AI ​​model currently deployed on the terminal device is not the same as the AI ​​model corresponding to the new cell, or the cell currently connected to by the terminal device is not within the effective range of the currently deployed AI model. Therefore, the validity of the AI ​​model needs to be verified.

[0282] For event (b), "camping" refers to the terminal device selecting and listening to a specific cell after completing the initial access procedure. The terminal device entering the "camping on any cell" state means that, while in a connected state, after completing cell selection or cell reselection, it selects an acceptable cell to camp on. The "camping on any cell" state is also called the "camp on any cell" state. In other words, in event (b), the connection between the terminal device and the camped cell is unstable, therefore, it is necessary to perform validity verification on the AI ​​model to confirm its usability.

[0283] For event (c), when the signal quality of the serving cell to which the terminal device is connected is less than the fifth threshold, it is determined that the signal quality of the wireless signal of the cell currently connected to by the terminal device is poor. When the signal quality of the serving cell is poor, the effectiveness of the currently deployed AI model needs to be verified to avoid the problem of low accuracy in AI model-assisted RRM measurement.

[0284] Event (d) refers to a situation where a terminal device attempts to establish a connection with a network device via random access, but the access fails. Reasons for random access failure include at least one of the following: network congestion, poor signal quality, or the terminal device being too far from the base station, and may also include other reasons, which are not limited in this embodiment. Therefore, it is necessary to perform validity verification on the AI ​​model to verify its usability.

[0285] The above method, by setting up event-triggered validity verification, enables the terminal device to perform dynamic validity verification of the AI ​​model when accessing a new cell or when the signal quality is poor, thus preventing the terminal device from continuing to use inaccurate AI models to assist in RRM measurement in inappropriate scenarios.

[0286] 3. Skip the configuration for performing periodic validity checks.

[0287] In some embodiments, the configuration for skipping the execution of periodic validity verification includes: a time threshold, wherein if the time interval between the execution of an event-triggered validity verification and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

[0288] The time threshold indicates the minimum time interval between any two consecutive validity checks. When the time interval between an event-triggered validity check and the next periodic validity check is less than the time threshold, it indicates a small time interval between these two consecutive validity checks. In this case, the likelihood of a significant change in the validation result obtained from the two validity checks is low. Therefore, the next periodic validity check can be skipped. When the time interval between an event-triggered validity check and the next periodic validity check is greater than the time threshold, it indicates a large time interval between these two consecutive validity checks, and therefore the next periodic validity check can be performed.

[0289] The above method skips the execution of the next periodic validity verification by using the time interval between the event-triggered validity verification and the next periodic validity verification, thus avoiding the execution of repeated validity verification in a short period of time and reducing the resource consumption of terminal devices caused by validity verification.

[0290] The following describes a scenario where AI models are used to assist in RRM measurement.

[0291] In some embodiments, the scenarios for using AI model-assisted RRM measurement include one or more, provided that the triggering conditions for using AI model-assisted RRM measurement are met. Based on the triggering conditions for using AI model-assisted RRM measurement, it is determined whether the terminal device can use AI model-assisted RRM measurement.

[0292] (1) SMTC uses AI model to assist in RRM measurement and performs RRM measurement.

[0293] In some embodiments, the terminal device performs RRM measurement based on the SMTC assisted by the AI ​​model for RRM measurement.

[0294] In some embodiments, the SMTC using AI model-assisted RRM measurement is an SMTC configured by the network device for the AI ​​model, also known as SMTC-AI. In some embodiments, the terminal device performs RRM measurement based on the SMTC using AI model-assisted RRM measurement, obtaining a fourth measurement result set; the terminal device inputs the fourth measurement result set into the AI ​​model, and the AI ​​model outputs a fifth measurement result set, which is the fourth measurement result set filled with predicted measurement results. In some embodiments, the frequency of RRM measurement based on SMTC-AI is lower than the frequency of RRM measurement based on normal SMTC.

[0295] In other words, the terminal device only needs to perform a small number of RRM measurements according to SMTC-AI to obtain the measurement results of at least one RRM measurement. The AI ​​model then predicts the measurement results between the time points of the RRM measurement based on the measurement results of at least one RRM measurement, and fills the obtained prediction results into the measurement results of the aforementioned at least one RRM measurement.

[0296] The above method uses AI models to predict measurement results, allowing terminal devices to obtain the same number of measurement results without using AI models to assist in RRM measurements by performing only a small number of RRM measurements. This helps reduce the power consumption of terminal devices due to performing RRM measurements.

[0297] (2) Use AI model to assist in the measurement of relaxation factor of RRM measurement and perform RRM measurement.

[0298] In some embodiments, the terminal device performs RRM measurement based on a measurement relaxation factor assisted by an AI model.

[0299] In some embodiments, the terminal device performs RRM measurements on the serving cell based on the serving cell measurement relaxation factor; the terminal device performs RRM measurements on the neighboring cells based on the neighboring cell measurement relaxation factor.

[0300] In some embodiments, the terminal device performs RRM measurements on the serving cell and the neighboring cell respectively, based on a measurement relaxation factor shared by the serving cell and the neighboring cell.

[0301] In some embodiments, the measurement relaxation factor used in AI model-assisted RRM measurement may be pre-configured by the network device for the AI ​​model. In some embodiments, the measurement relaxation factor used in AI model-assisted RRM measurement is output by the AI ​​model. That is, in this case, the measurement relaxation factor used in AI model-assisted RRM measurement is predicted by the AI ​​model.

[0302] In some embodiments, the terminal device performs RRM measurement based on the measurement relaxation factor assisted by the AI ​​model to obtain a sixth measurement result set; the terminal device inputs the sixth measurement result set into the AI ​​model, and the AI ​​model outputs a seventh measurement result set, which is the sixth measurement result set filled with predicted measurement results.

[0303] It should be noted that the method of using AI model to assist RRM measurement in scenario (2) is similar to that in scenario (1), so it will not be described in detail here.

[0304] (3) Use AI models to assist in cell selection or cell reselection.

[0305] In some embodiments, the terminal device obtains a predicted measurement result based on the actual measurement result using an AI model; and performs cell selection or cell reselection based on the predicted measurement result, or based on both the predicted and actual measurement results.

[0306] Actual measurement results refer to the measurement results obtained by performing RRM measurements using a terminal device. In some embodiments, actual measurement results may be obtained by performing RRM measurements in at least one of the following ways: performing normal RRM measurements; performing RRM measurements using an AI model-assisted RRM measurement SMTC; or performing RRM measurements using an AI model-assisted RRM measurement measurement relaxation factor. Predicted measurement results refer to the measurement results predicted by an AI model for RRM measurements.

[0307] In some embodiments, the terminal device uses an AI model to fill in the actual measurement results, obtaining the filled actual measurement results. The filled actual measurement results include the actual measurement results and the predicted measurement results output by the AI ​​model. When the measurement results in the actual measurement results are sorted according to the time sequence of the RRM measurements performed, filling refers to inserting predicted measurement results between any two actual measurement results.

[0308] In some embodiments, the terminal device uses an AI model to predict the measurement results of RRM measurement in the first time period based on the actual measurement results, and obtains the predicted measurement results in the first time period; the terminal device does not perform RRM measurement in the first time period.

[0309] The above method uses the predicted results output by the AI ​​model to replace part of the actual measurement results, which allows the terminal device to reduce the number of measurements to be performed for RRM measurement, thereby reducing energy consumption.

[0310] The following describes the specific process of using an AI model to perform validity verification of RRM measurements.

[0311] Please refer to Figure 6, which shows a flowchart of validity verification provided in one embodiment of this application. The specific process of performing validity verification of RRM measurement using an AI model includes at least one of the following steps (610-640).

[0312] In some embodiments, during the use of an AI model, periodic validity verification is performed on the AI ​​model, and / or event-triggered validity verification is performed on the AI ​​model.

[0313] It should be noted that the validity verification for the periodic execution of the AI ​​model and the validity verification for the event-triggered execution of the AI ​​model have been explained above. Please refer to the corresponding sections above for relevant explanations.

[0314] Step 610: The terminal device performs RRM measurement according to the measurement duration for validity verification, and obtains a first measurement result set, which includes multiple actual measurement results.

[0315] The first measurement result set is the collection of actual measurement results obtained by performing normal RRM within the measurement period for validity verification.

[0316] In some embodiments, the terminal device performs RRM measurement based on the measurement duration for validity verification and the SMTC (Measurement Management Case) without using an AI model to assist RRM measurement, and obtains a first measurement result. SMTC without using an AI model to assist RRM refers to the SMTC performing normal RRM measurement.

[0317] Step 620: The terminal device selects a portion of the actual measurement results from the first measurement result set based on the SMTC measured using the AI ​​model-assisted RRM measurement and / or the measurement relaxation factor measured using the AI ​​model-assisted RRM measurement, to obtain the second measurement result set.

[0318] In some embodiments, when the terminal device is in scenario (1), the terminal device uses the AI ​​model-assisted RRM measurement SMTC to select a portion of the actual measurement results from the first measurement result set. In some embodiments, the terminal device determines at least one time location for performing RRM measurement based on the AI ​​model-assisted RRM measurement SMTC; the terminal device selects a portion of the actual measurement results from the first measurement result set based on the at least one time location for performing RRM measurement to obtain a second measurement result set.

[0319] For example, the terminal device can determine at least one time position of performing RRM measurement based on the SMTC using AI model-assisted RRM measurement within the measurement duration of the validity verification, according to the current time, the measurement duration of the validity verification, and the measurement cycle and measurement window corresponding to the SMTC using AI model-assisted RRM measurement.

[0320] In some embodiments, when the terminal device is in scenario (2), the terminal device uses the measurement relaxation factor of the AI ​​model-assisted RR measurement to select a portion of the actual measurement results from the first measurement result set. In some embodiments, the terminal device determines at least one time location for performing RRM measurement based on the measurement relaxation factor of the AI ​​model-assisted RRM measurement; the terminal device selects a portion of the actual measurement results from the first measurement result set based on the at least one time location for performing RRM measurement to obtain a second measurement result set.

[0321] For example, the terminal device can determine at least one time position of performing RRM measurement within the measurement duration of performing validity verification, based on the measurement measurement factor of RRM measurement using AI model assisted measurement and the normal measurement cycle, according to the current time, the measurement duration of performing validity verification, the measurement measurement factor of RRM measurement using AI model assisted measurement and the normal measurement cycle.

[0322] In some embodiments, for any one of the time locations where RRM measurements are performed, the terminal device selects the actual measurement result corresponding to that time location from the first measurement result set; the terminal device obtains a second measurement result set based on the actual measurement results corresponding to each of the at least one time location where RRM measurements are performed.

[0323] Step 630: The terminal device obtains at least one predicted measurement result based on the second measurement result set through the AI ​​model, wherein the at least one predicted measurement result is filled into the second measurement result set to obtain a third measurement result set.

[0324] In some embodiments, at least one predicted measurement result can be interpolated into the second measurement result set to obtain a third measurement result set. In some embodiments, the third measurement result set can be obtained by filling at least one measurement result into the beginning or end of the second measurement result set. In some embodiments, the step of filling at least one measurement result into the second measurement result set can be implemented by an AI model or by a terminal device, and this application embodiment does not limit this.

[0325] Step 640: The terminal device determines the validity verification result of the AI ​​model based on the difference between the first measurement result set and the third measurement result set.

[0326] In some embodiments, the differences between the first measurement result set and the third measurement result set include at least one of the following.

[0327] (1) The difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set.

[0328] In some embodiments, the terminal device performs an averaging operation on each measurement result in the first measurement result set to obtain the average value of the first measurement result set; the terminal device performs an averaging operation on each measurement result in the first measurement result set to obtain the average value of the third measurement result set.

[0329] In some embodiments, if the difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set is less than a sixth threshold, the terminal device determines that the AI ​​model is valid; if the difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set is greater than the sixth threshold, the terminal device determines that the AI ​​model is invalid.

[0330] In some embodiments, the sixth threshold is predefined by network device configuration or protocol.

[0331] (2) The variance of the differences between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set.

[0332] For any measurement result in the third measurement result set, the corresponding measurement result in the first measurement result set is determined based on the time position of the RRM measurement execution corresponding to that measurement result. In some embodiments, there is one measurement result in both the first and third measurement result sets, corresponding to the same time position of the RRM measurement execution.

[0333] In some embodiments, the terminal device calculates the difference between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set based on the time position of at least one RRM measurement performed above; the terminal device performs variance calculation on the difference between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set to obtain the variance of the difference between the first measurement result set and the third measurement result set.

[0334] In some embodiments, if the variance of the difference between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set is less than a seventh threshold, the terminal device determines that the AI ​​model is valid; if the variance of the difference between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set is greater than the seventh threshold, the terminal device determines that the AI ​​model is invalid.

[0335] In some embodiments, the seventh threshold is predefined by network device configuration or protocol.

[0336] The above method determines the effectiveness of the AI ​​model by judging the difference between the first and third measurement result sets to ascertain the accuracy of the AI ​​model's predictions for RRM measurements.

[0337] In some embodiments, the terminal device performs multiple validity verifications on the AI ​​model; the terminal device determines the AI ​​model to be valid if the number of valid times of the AI ​​model is greater than or equal to the valid number threshold, or if the proportion of the valid times of the AI ​​model to the total number of times is greater than or equal to the proportion threshold.

[0338] Performing multiple validity verifications on the AI ​​model refers to performing steps 610 to 640 multiple times. In some embodiments, the number of times the validity verification of the AI ​​model is performed is configured by the network device using relevant information about the AI ​​model.

[0339] For example, suppose the AI ​​model performs validity verification M1 times, and the threshold for the number of valid AI model verifications is M2. If the number of valid verifications performed by the AI ​​model in the M1 verifications is greater than M2, then the AI ​​model is determined to be valid. Here, M1 and M2 are integers greater than 0.

[0340] In some embodiments, the effective number threshold or proportion threshold is configured by the network device using relevant information from the AI ​​model.

[0341] For example, suppose the AI ​​model performs validity verification M1 times, and the threshold for the proportion of valid AI model performance to the total number of verifications is M3. If the proportion of valid AI model performance to the total number of verifications is greater than M3, then the AI ​​model is determined to be valid. Here, M3 is greater than 0.

[0342] It should be noted that the threshold for the number of valid verifications performed on the terminal device in the AI ​​model, as well as the threshold for the proportion of valid AI model data to the total number of data, have been explained above. Please refer to the corresponding sections for further explanation.

[0343] In some embodiments, if the AI ​​model is invalid, the terminal device indicates to the network device that the AI ​​model is invalid by initiating random access.

[0344] Accordingly, the receiving terminal device sends a random access message, which contains information indicating that the AI ​​model is invalid.

[0345] A random access message is a message sent by a terminal device to a network device during the process of initiating random access, used to request the establishment of a connection or synchronization. In some embodiments, the preamble of the random access message includes information indicating that the AI ​​model is invalid.

[0346] In some embodiments, after receiving a random access message sent by a terminal device, the network device resends the first information to the terminal device.

[0347] In this method, the terminal device sends a random access message to the network device carrying information indicating that the AI ​​model is invalid. This enables the network device to quickly detect and respond to anomalies in the AI ​​model deployed on the terminal device side, reducing signaling overhead while ensuring the normal operation of the terminal device using the AI ​​model to assist in RRM measurement.

[0348] In some embodiments, if the number of consecutive invalid AI models exceeds a first invalidation threshold, or the total number of invalid AI models exceeds a second invalidation threshold, the terminal device disables the AI ​​model. The total number of invalid AI models refers to the total number of times the AI ​​model is determined to be invalid within a second time period. In some embodiments, the second time period is configured by the network device.

[0349] It should be noted that the process of using an AI model to perform validity verification of RRM measurements described above can be applied to any of the three scenarios mentioned.

[0350] In the above method embodiments, the steps performed by the terminal device can be implemented separately as a measurement and configuration method on the terminal device side, and the steps performed by the network device can be implemented separately as a measurement and configuration method on the network device side.

[0351] Furthermore, the various embodiments of this application can be combined in any way to form new embodiments, all of which are within the protection scope of this application.

[0352] 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.

[0353] Please refer to Figure 7, which shows a block diagram of a terminal device provided in one embodiment of this application. This terminal device has the function of performing the measurement configuration method described above on the terminal device side. As shown in Figure 7, the terminal device 700 may include a receiving module 710.

[0354] The receiving module 710 is used to receive first information, which is used to determine relevant information of the AI ​​model, and the AI ​​model is used to assist in RRM measurement.

[0355] In some embodiments, the relevant information of the AI ​​model includes at least one of the following: indication information of the AI ​​model; model data of the AI ​​model; indication information of whether the AI ​​model is activated; effective area information of the AI ​​model; and configuration information of the AI ​​model.

[0356] In some embodiments, the configuration information of the AI ​​model is used to determine at least one of the following: triggering conditions for using the AI ​​model to assist RRM measurement; SSB SMTC for using the AI ​​model to assist RRM measurement; measurement relaxation factor for using the AI ​​model to assist RRM measurement; prediction result configuration for using the AI ​​model to assist RRM measurement; cell for using the AI ​​model to assist RRM measurement; validity verification configuration before using the AI ​​model; and validity verification configuration during the process of using the AI ​​model.

[0357] In some embodiments, the triggering conditions for using the AI ​​model to assist RRM measurement include at least one of the following: the terminal device receives an instruction to activate the AI ​​model; the terminal device is within the effective area of ​​the AI ​​model; the AI ​​model is valid; the signal quality of the serving cell of the terminal device is greater than a first threshold; the signal quality of the neighboring cells of the terminal device is greater than a second threshold; the moving speed of the terminal device is less than a third threshold; and the distance between the terminal device and the reference point is less than a fourth threshold. In some embodiments, the third and fourth thresholds are configured by the network device or predefined by the protocol.

[0358] In some embodiments, SMTCs using the AI ​​model to assist RRM measurement, compared to SMTCs not using the AI ​​model to assist RRM measurement, satisfy at least one of the following: longer measurement period; shorter measurement window length; fewer SSBs measured; fewer neighboring cells measured.

[0359] In some embodiments, the measurement relaxation factor used to assist RRM measurement using the AI ​​model includes: measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device, respectively; or, measurement relaxation factors shared by the serving cell and neighboring cells of the terminal device.

[0360] In some embodiments, the validity verification configuration prior to using the AI ​​model includes at least one of the following: the measurement duration for the terminal device to perform validity verification; the error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; the total number of times the terminal device performs validity verification; the threshold for the number of valid validity verifications performed by the terminal device; the threshold for the proportion of the number of valid validity verifications performed by the terminal device to the total number of verifications; and configuration information for re-performing validity verification when the AI ​​model is invalid.

[0361] In some embodiments, the validity verification configuration used in the AI ​​model process includes at least one of the following: a configuration for performing periodic validity verification; a configuration for performing event-triggered validity verification; and a configuration for skipping the performance of periodic validity verification.

[0362] In some embodiments, the configuration for performing periodic validity verification includes at least one of the following: the period of the periodic validity verification; the measurement duration of the periodic validity verification; the measurement relaxation factor of the periodic validity verification; the SMTC of the periodic validity verification; and the configuration of the prediction results of the periodic validity verification.

[0363] In some embodiments, the configuration for validating the execution event trigger includes at least one of the following events: the terminal device selects or reselects a new cell; the terminal device enters a state of camping in any cell; the signal quality of the serving cell of the terminal device is less than a fifth threshold; the terminal device fails to initiate random access. In some embodiments, the fifth threshold is configured by the network device or predefined by the protocol.

[0364] In some embodiments, the configuration for skipping the execution of periodic validity verification includes a time threshold, wherein if the time interval between the execution of an event-triggered validity verification and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

[0365] In some embodiments, the terminal device 700 further includes a processing module 720, configured to perform RRM measurement based on the SMTC and / or the measurement relaxation factor of the RRM measurement assisted by the AI ​​model, when the triggering conditions for using the AI ​​model to assist RRM measurement are met.

[0366] In some embodiments, the terminal device 700 further includes a processing module 720, configured to obtain a predicted measurement result based on the actual measurement result using the AI ​​model; and to perform cell selection or cell reselection based on the predicted measurement result, or based on the predicted measurement result and the actual measurement result.

[0367] In some embodiments, the terminal device 700 further includes a processing module 720, configured to perform RRM measurement according to the measurement duration for validity verification, to obtain a first measurement result set, the first measurement result set including multiple actual measurement results; select a portion of the actual measurement results from the first measurement result set according to the SMTC of RRM measurement assisted by the AI ​​model and / or the measurement relaxation factor of RRM measurement assisted by the AI ​​model, to obtain a second measurement result set; obtain at least one predicted measurement result through the AI ​​model based on the second measurement result set, wherein the at least one predicted measurement result is filled into the second measurement result set to obtain a third measurement result set; and determine the validity verification result of the AI ​​model based on the difference between the first measurement result set and the third measurement result set.

[0368] In some embodiments, the difference between the first measurement result set and the third measurement result set includes at least one of the following: the difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set; and the variance of the difference between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set.

[0369] In some embodiments, the terminal device 700 further includes a processing module 720, which performs multiple validity verifications on the AI ​​model; and determines that the AI ​​model is valid if the number of valid times of the AI ​​model is greater than or equal to a valid number threshold, or if the proportion of the valid times of the AI ​​model to the total number of times is greater than or equal to a proportion threshold.

[0370] In some embodiments, the terminal device 700 further includes a processing module 720, configured to perform periodic validity verification on the AI ​​model during the use of the AI ​​model, and / or perform event-triggered validity verification on the AI ​​model.

[0371] In some embodiments, the terminal device 700 further includes a processing module 720, configured to, in the event that the AI ​​model is invalid, not perform validity verification for the AI ​​model for a set period of time according to configuration information for re-performing validity verification, and / or, perform validity verification for the AI ​​model again after the set period of time.

[0372] In some embodiments, the terminal device 700 further includes a processing module 720, configured to indicate to the network device that the AI ​​model is invalid by initiating random access if the AI ​​model is invalid.

[0373] In some embodiments, the terminal device 700 further includes a sending module 730, which is used to send capability information to a network device when in a connected state. The capability information is used to indicate whether the terminal device supports the ability to use the AI ​​model to assist in RRM measurement.

[0374] In some embodiments, the receiving module 710 is configured to receive a system broadcast message, the system broadcast message including the first information; or, receive a first dedicated signaling, the first dedicated signaling including the first information; or, receive a second dedicated signaling, the second dedicated signaling including server address information, and obtain the first information from the server based on the server address information.

[0375] In summary, the technical solution provided in this application embodiment allows the network device to send first information to the terminal device to indicate relevant information of the AI ​​model, enabling the terminal device to reduce the number of RRM measurements performed by using the AI ​​model to assist in RRM measurement, thereby reducing the energy consumption of the terminal device due to performing RRM measurement.

[0376] Please refer to Figure 8, which shows a block diagram of a network device according to an embodiment of this application. This network device has the function of performing the measurement configuration method described above on the network device side. As shown in Figure 8, the network device 800 may include a transmitting module 810.

[0377] The sending module 810 is used to send first information, which is used to determine relevant information of the AI ​​model, and the AI ​​model is used to assist in RRM measurement.

[0378] In some embodiments, the relevant information of the AI ​​model includes at least one of the following: indication information of the AI ​​model; model data of the AI ​​model; indication information of whether the AI ​​model is activated; effective area information of the AI ​​model; and configuration information of the AI ​​model.

[0379] In some embodiments, the configuration information of the AI ​​model is used to determine at least one of the following: triggering conditions for using the AI ​​model to assist RRM measurement; SMTC for using the AI ​​model to assist RRM measurement; measurement relaxation factor for using the AI ​​model to assist RRM measurement; prediction result configuration for using the AI ​​model to assist RRM measurement; cell for using the AI ​​model to assist RRM measurement; validity verification configuration before using the AI ​​model; and validity verification configuration during the process of using the AI ​​model.

[0380] In some embodiments, the triggering conditions for using the AI ​​model to assist RRM measurement include at least one of the following: the terminal device receives an instruction to activate the AI ​​model; the terminal device is within the effective area of ​​the AI ​​model; the AI ​​model is effective; the signal quality of the serving cell of the terminal device is greater than a first threshold; the signal quality of the neighboring cells of the terminal device is greater than a second threshold; the moving speed of the terminal device is less than a third threshold; and the distance between the terminal device and the reference point is less than a fourth threshold.

[0381] In some embodiments, SMTCs using the AI ​​model to assist RRM measurement, compared to SMTCs not using the AI ​​model to assist RRM measurement, satisfy at least one of the following: longer measurement period; shorter measurement window length; fewer SSBs measured; fewer neighboring cells measured.

[0382] In some embodiments, the measurement relaxation factor used to assist RRM measurement with the AI ​​model includes: measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device, respectively; or, measurement relaxation factors shared by the serving cell and neighboring cells of the terminal device.

[0383] In some embodiments, the validity verification configuration prior to using the AI ​​model includes at least one of the following: the measurement duration for the terminal device to perform validity verification; the error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; the total number of times the terminal device performs validity verification; the threshold for the number of valid times the terminal device performs validity verification; the threshold for the proportion of the number of valid times the terminal device performs validity verification to the total number of times; and configuration information for re-performing validity verification when the AI ​​model is invalid.

[0384] In some embodiments, the validity verification configuration used in the AI ​​model process includes at least one of the following: a configuration for performing periodic validity verification; a configuration for performing event-triggered validity verification; and a configuration for skipping the performance of periodic validity verification.

[0385] In some embodiments, the configuration for performing periodic validity verification includes at least one of the following: the period of the periodic validity verification; the measurement duration of the periodic validity verification; the measurement relaxation factor of the periodic validity verification; the SMTC of the periodic validity verification; and the configuration of the prediction results of the periodic validity verification.

[0386] In some embodiments, the configuration for validating the execution event trigger includes at least one of the following events: the terminal device selects or reselects a new cell; the terminal device enters a state of camping in any cell; the signal quality of the serving cell of the terminal device is less than a fifth threshold; the terminal device fails to initiate random access.

[0387] In some embodiments, the configuration for skipping the execution of periodic validity verification includes a time threshold, wherein if the time interval between the execution of an event-triggered validity verification and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

[0388] In some embodiments, the network device 800 further includes a receiving module 820 for receiving a random access message sent by a terminal device, the random access message containing information indicating that the AI ​​model is invalid.

[0389] In some embodiments, the network device 800 further includes a receiving module 820, configured to receive capability information sent by a terminal device in a connected state, the capability information being used to indicate whether the terminal device supports the capability of using the AI ​​model to assist in RRM measurement.

[0390] In some embodiments, the sending module 810 is configured to send a system broadcast message, the system broadcast message including the first information; or, send a first dedicated signaling, the first dedicated signaling including the first information; or, send a second dedicated signaling, the second dedicated signaling including server address information, the server address information being used to obtain the first information from the server.

[0391] In summary, the technical solution provided in this application embodiment allows the network device to send first information to the terminal device to indicate relevant information of the AI ​​model, enabling the terminal device to reduce the number of RRM measurements performed by using the AI ​​model to assist in RRM measurement, thereby reducing the energy consumption of the terminal device due to performing RRM measurement.

[0392] 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.

[0393] 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.

[0394] Please refer to Figure 9, which shows a schematic diagram of the structure of a terminal device provided in one embodiment of this application. The terminal device 900 may include a processor 901, a transceiver 902, and a memory 903. The processor 901 is used to implement various processing functions of the terminal device 900, such as generating information to be sent, processing received information, controlling transmission and / or reception, etc., for example, to implement the functions of the processing module 720 described above. The transceiver 902 is used to implement transmission and / or reception functions, for example, to implement the functions of the receiving module 710 and / or the transmitting module 730 described above.

[0395] The processor 901 includes one or more processing cores. The processor 901 executes various functional applications and information processing by running software programs and modules.

[0396] The transceiver 902 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.

[0397] The memory 903 can be connected to the processor 901 and the transceiver 902.

[0398] The memory 903 can be used to store a computer program executed by the processor, and the processor 901 is used to execute the computer program so that the terminal device performs the various steps performed by the terminal device in the above method embodiments.

[0399] In some embodiments, transceiver 902 is used to receive first information, the first information being used to determine relevant information about an AI model, the AI ​​model being used to assist in RRM measurement.

[0400] For details not described in this embodiment, please refer to the embodiments above, which will not be repeated here.

[0401] 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.

[0402] Please refer to Figure 10, which shows a schematic diagram of the structure of a network device provided in one embodiment of this application. The network device 1000 may include a processor 1001, a transceiver 1002, and a memory 1003. The processor 1001 can be used to implement various processing functions of the network device 1000, such as generating information to be sent, processing received information, and controlling transmission and / or reception. The transceiver 1002 is used to implement transmission and / or reception functions, such as implementing the functions of the aforementioned transmission module 810 and / or reception module 820.

[0403] The processor 1001 includes one or more processing cores. The processor 1001 executes various functional applications and information processing by running software programs and modules.

[0404] The transceiver 1002 may include a receiver and a transmitter. For example, the transceiver 1002 may include a wired communication component, which may include a wired communication chip and a wired interface (such as a fiber optic interface). Optionally, the transceiver 1002 may also include a wireless communication component, which may include a wireless communication chip and a radio frequency antenna.

[0405] The memory 1003 can be connected to the processor 1001 and the transceiver 1002.

[0406] The memory 1003 can be used to store a computer program executed by the processor, and the processor 1001 is used to execute the computer program so that the network device performs the various steps performed by the network device in the above method embodiment.

[0407] In some embodiments, transceiver 1002 is configured to send first information, the first information being related to the configuration of a first measurement, and the measurement result obtained from the first measurement being used for network-side model monitoring.

[0408] For details not described in this embodiment, please refer to the embodiments above, which will not be repeated here.

[0409] Furthermore, the memory 1003 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, including but not limited to: magnetic disks or optical disks, electrically erasable programmable read-only memory, erasable programmable read-only memory, static on-demand memory, read-only memory, magnetic memory, flash memory, and programmable read-only memory.

[0410] This application embodiment also provides a computer-readable storage medium storing a computer program for execution by a processor to implement the aforementioned wireless measurement method on the terminal device side or the aforementioned wireless measurement method on the network device side. 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).

[0411] This application also provides a chip, which includes programmable logic circuits and / or program instructions. When the chip is running, it is used to implement the wireless measurement method on the terminal device side described above.

[0412] This application also provides a chip, which includes programmable logic circuitry and / or program instructions. When the chip is running in a terminal device, it is used to: receive first information, the first information being used to determine relevant information of an AI model, the AI ​​model being used to assist in RRM measurement. When the chip is running in the terminal device, it is also used to implement other steps executed by the terminal device as described in the above embodiments, which will not be repeated here.

[0413] 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 on the network device side.

[0414] This application also provides a chip, which includes programmable logic circuitry and / or program instructions. When the chip is running in a network device, it is used to: send first information, the first information being used to determine relevant information of an AI model, the AI ​​model being used to assist in RRM measurement. When the chip is running in the network device, it is also used to implement other steps performed by the network device as described in the above embodiments, which will not be repeated here.

[0415] 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 wireless measurement method on the terminal device side or the wireless measurement method on the network device side.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] In some embodiments of this application, the term "protocol" may refer to standard protocols in the field of communications, such as BLE protocol, Wi-Fi protocol, and related protocols applied in future communication systems. This application does not limit the scope of these protocols.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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: Receive first information, which is used to determine relevant information of an artificial intelligence (AI) model, which is used to assist in radio resource management (RRM) measurement.

2. The method of claim 1, wherein, The relevant information of the AI ​​model includes at least one of the following: The instruction information of the AI ​​model; The model data of the AI ​​model; Indicator information indicating whether the AI ​​model is activated; The effective region information of the AI ​​model; The configuration information of the AI ​​model.

3. The method according to claim 1 or 2, characterized in that, The configuration information of the AI ​​model is used to determine at least one of the following: Triggering conditions for using the AI ​​model to assist in RRM measurement; The AI ​​model is used to assist in the timing configuration of SSB measurement for RRM measurement; The AI ​​model was used to assist in the measurement of relaxation factors in RRM measurements. Configuration of prediction results for RRM measurement using the AI ​​model; Cells using the AI ​​model to assist in RRM measurements; Validation configuration prior to using the AI ​​model; The validity verification configuration during the use of the AI ​​model.

4. The method according to any one of claims 1 to 3, characterized in that, The triggering conditions for using the AI ​​model to assist in RRM measurement include at least one of the following: The terminal device receives an instruction to activate the AI ​​model; The terminal device is located within the effective area of ​​the AI ​​model; The AI ​​model is effective; The signal quality of the serving cell of the terminal device is greater than a first threshold. The signal quality of the neighboring cells of the terminal device is greater than the second threshold. The moving speed of the terminal device is less than the third threshold. The distance between the terminal device and the reference point is less than the fourth threshold.

5. The method according to any one of claims 1 to 4, characterized in that, SMTCs measured using the AI ​​model-assisted RRM measurement, compared to SMTCs measured without the AI ​​model-assisted RRM measurement, satisfy at least one of the following: Longer measurement cycle; The measurement window length is smaller; The number of SSBs measured was even smaller; The number of neighboring cells measured was even smaller.

6. The method according to any one of claims 1 to 5, characterized in that, The relaxation factors measured using the AI ​​model-assisted RRM measurement include: The measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device, respectively; or... The terminal device uses a measurement relaxation factor shared by its serving cell and neighboring cells.

7. The method according to any one of claims 1 to 6, characterized in that, The validity verification configuration prior to using the AI ​​model includes at least one of the following: The measurement duration for the terminal device to perform validity verification; The error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; The total number of times the terminal device performs validity verification; The threshold number of valid attempts for the terminal device to perform validity verification; The threshold for the proportion of valid validation attempts performed by the terminal device to the total number of validation attempts; When the AI ​​model is invalid, the configuration information for validity verification is retrieved again.

8. The method according to any one of claims 1 to 7, characterized in that, The validity verification configuration during the use of the AI ​​model includes at least one of the following: Configure the execution of periodic validity verification; Configure the validity verification for event-triggered events; Configure to skip performing periodic validity checks.

9. The method of claim 8, wherein, The configuration for performing periodic validity verification includes at least one of the following: The periodic validity verification cycle; The measurement duration for the periodic validity verification; The periodic effectiveness verification measures the relaxation factor; The periodic validity verification of the SMTC; The configuration of the prediction results for the periodic validity verification.

10. The method according to claim 8 or 9, characterized in that, The configuration for validity verification triggered by the execution event includes at least one of the following events: The terminal device selects or reselects a new cell; The terminal device enters a state of residing in any cell; The signal quality of the serving cell of the terminal device is less than the fifth threshold. The terminal device failed to initiate random access.

11. The method according to any one of claims 8 to 10, characterized in that, The configuration for skipping the periodic validity verification includes: A time threshold, wherein if the time interval between the validity verification triggered by the execution event and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: If the triggering conditions for using the AI ​​model to assist in RRM measurement are met, RRM measurement is performed based on the SMTC and / or the measured relaxation factor for using the AI ​​model to assist in RRM measurement.

13. The method according to any one of claims 1 to 12, characterized in that, The method further includes: The AI ​​model obtains predicted measurement results based on actual measurement results; Based on the predicted measurement results, or based on the predicted measurement results and the actual measurement results, cell selection or cell reselection is performed.

14. The method according to any one of claims 1 to 13, characterized in that, The method further includes: RRM measurement is performed based on the measurement duration for validity verification, resulting in a first measurement result set, which includes multiple actual measurement results. Based on the SMTC measured using the AI ​​model-assisted RRM and / or the measurement relaxation factor measured using the AI ​​model-assisted RRM, a portion of the actual measurement results are selected from the first measurement result set to obtain a second measurement result set; The AI ​​model obtains at least one predicted measurement result based on the second measurement result set, wherein the at least one predicted measurement result is filled into the second measurement result set to obtain a third measurement result set; The validity verification result of the AI ​​model is determined based on the difference between the first measurement result set and the third measurement result set.

15. The method of claim 14, wherein, The differences between the first measurement result set and the third measurement result set include at least one of the following: The difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set; The variance of the differences between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set.

16. The method according to any one of claims 1 to 15, characterized in that, The method further includes: Perform multiple validity checks on the AI ​​model; The AI ​​model is deemed valid if the number of valid attempts of the AI ​​model is greater than or equal to the valid attempt threshold, or if the proportion of valid attempts of the AI ​​model to the total number of attempts is greater than or equal to the proportion threshold.

17. The method according to any one of claims 1 to 16, characterized in that, The method further includes: During the use of the AI ​​model, periodic validity verification is performed on the AI ​​model, and / or event-triggered validity verification is performed on the AI ​​model.

18. The method according to any one of claims 1 to 17, characterized in that, The method further includes: If the AI ​​model is invalid, the validity verification for the AI ​​model will not be performed for a set period of time, and / or the validity verification for the AI ​​model will be performed again after the set period of time, according to the configuration information for re-performing the validity verification.

19. The method according to any one of claims 1 to 18, characterized in that, The method further includes: If the AI ​​model is invalid, the network device is notified that the AI ​​model is invalid by initiating random access.

20. The method according to any one of claims 1 to 19, characterized in that, The method further includes: When in a connected state, capability information is sent to the network device, which indicates whether the terminal device supports the ability to use the AI ​​model to assist in RRM measurement.

21. The method according to any one of claims 1 to 20, characterized in that, The receiving of the first information includes: Receive a system broadcast message, wherein the system broadcast message includes the first information; or... Receive a first dedicated signaling message, wherein the first dedicated signaling message includes the first information; or... Receive a second dedicated signaling message, which includes the server's address information, and obtain the first information from the server based on the server's address information.

22. A wireless measurement method, comprising: The method is performed by a network device, and the method includes: Send first information, which is used to determine relevant information of an artificial intelligence (AI) model, which is used to assist in wireless resource management (RRM) measurement.

23. The method of claim 22, wherein, The relevant information of the AI ​​model includes at least one of the following: The instruction information of the AI ​​model; The model data of the AI ​​model; Indicator information indicating whether the AI ​​model is activated; The effective region information of the AI ​​model; The configuration information of the AI ​​model.

24. The method of claim 22 or 23, wherein, The configuration information of the AI ​​model is used to determine at least one of the following: Triggering conditions for using the AI ​​model to assist in RRM measurement; The AI ​​model is used to assist in the timing configuration of SSB measurement for RRM measurement; The AI ​​model was used to assist in the measurement of relaxation factors in RRM measurements. Configuration of prediction results for RRM measurement using the AI ​​model; Cells using the AI ​​model to assist in RRM measurements; Validation configuration prior to using the AI ​​model; The validity verification configuration during the use of the AI ​​model.

25. The method according to any one of claims 22 to 24, characterized in that, The triggering conditions for using the AI ​​model to assist in RRM measurement include at least one of the following: The terminal device receives an instruction to activate the AI ​​model; The terminal device is located within the effective area of ​​the AI ​​model; The AI ​​model is effective; The signal quality of the serving cell of the terminal device is greater than the first threshold. The signal quality of the neighboring cell of the terminal device is greater than the second threshold. The terminal device's moving speed is less than the third threshold; The distance between the terminal device and the reference point is less than the fourth threshold.

26. The method of any one of claims 22 to 25, wherein, SMTCs measured using the AI ​​model-assisted RRM measurement, compared to SMTCs measured without the AI ​​model-assisted RRM measurement, satisfy at least one of the following: Longer measurement cycle; The measurement window length is smaller; The number of SSBs measured was even smaller; The number of neighboring cells measured was even smaller.

27. The method of any one of claims 22 to 26, wherein, The relaxation factors measured using the AI ​​model-assisted RRM measurement include: The measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device; or, The measurement relaxation factor shared by the serving cell and neighboring cells of the terminal device.

28. The method of any one of claims 22 to 27, wherein, The validity verification configuration prior to using the AI ​​model includes at least one of the following: The measurement time for the terminal device to perform validity verification; The error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; The total number of times the terminal device performs validity verification; The threshold for the number of valid validation attempts performed by the terminal device; The threshold for the percentage of valid validation attempts performed by the terminal device out of the total number of validation attempts; The configuration information for re-performing validity verification when the AI ​​model is invalid.

29. The method according to any one of claims 22 to 28, characterized in that, The validity verification configuration during the use of the AI ​​model includes at least one of the following: Configure the execution of periodic validity verification; Configure the validity verification for event-triggered events; Configure to skip performing periodic validity checks.

30. The method of claim 29, wherein, The configuration for performing periodic validity verification includes at least one of the following: The periodic validity verification cycle; The measurement duration for the periodic validity verification; The periodic effectiveness verification measures the relaxation factor; The periodic validity verification of the SMTC; The configuration of the prediction results for the periodic validity verification.

31. The method of claim 29 or 30, wherein, The configuration for validity verification triggered by the execution event includes at least one of the following events: The terminal device selects or reselects a new cell; The terminal device enters a state of residing in any cell; The signal quality of the serving cell of the terminal device is less than the fifth threshold. The terminal device failed to initiate random access.

32. The method of any one of claims 29 to 31, wherein, The configuration for skipping the periodic validity verification includes: A time threshold, wherein if the time interval between the validity verification triggered by the execution event and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

33. The method of any one of claims 22 to 32, wherein, The method further includes: The system receives a random access message sent by a terminal device, the random access message containing information indicating that the AI ​​model is invalid.

34. The method of any one of claims 22 to 33, wherein, The method further includes: The terminal device receives capability information sent in a connected state, the capability information being used to indicate whether the terminal device supports the ability to use the AI ​​model to assist in RRM measurement.

35. The method of any one of claims 22 to 34, wherein, The sending of the first information includes: Send a system broadcast message, wherein the system broadcast message includes the first information; or... Send a first dedicated signaling message, which includes the first information; or... Send a second dedicated signaling message, which includes the server's address information, and the server's address information is used to obtain the first information from the server.

36. A terminal device, comprising: The terminal device includes: A receiving module is used to receive first information, which is used to determine relevant information of an artificial intelligence (AI) model, which is used to assist in radio resource management (RRM) measurement.

37. The terminal device of claim 36, wherein, The relevant information of the AI ​​model includes at least one of the following: The instruction information of the AI ​​model; The model data of the AI ​​model; Indicator information indicating whether the AI ​​model is activated; The effective region information of the AI ​​model; The configuration information of the AI ​​model.

38. The terminal device of claim 36 or 37, wherein, The configuration information of the AI ​​model is used to determine at least one of the following: Triggering conditions for using the AI ​​model to assist in RRM measurement; The AI ​​model is used to assist in the timing configuration of SSB measurement for RRM measurement; The AI ​​model was used to assist in the measurement of relaxation factors in RRM measurements. Configuration of prediction results for RRM measurement using the AI ​​model; Cells using the AI ​​model to assist in RRM measurements; Validation configuration prior to using the AI ​​model; The validity verification configuration during the use of the AI ​​model.

39. The terminal device of any one of claims 36 to 38, wherein, The triggering conditions for using the AI ​​model to assist in RRM measurement include at least one of the following: The terminal device receives an instruction to activate the AI ​​model; The terminal device is located within the effective area of ​​the AI ​​model; The AI ​​model is effective; The signal quality of the serving cell of the terminal device is greater than a first threshold. The signal quality of the neighboring cells of the terminal device is greater than the second threshold. The moving speed of the terminal device is less than the third threshold. The distance between the terminal device and the reference point is less than the fourth threshold.

40. The terminal device of any one of claims 36 to 39, wherein, SMTCs measured using the AI ​​model-assisted RRM measurement, compared to SMTCs measured without the AI ​​model-assisted RRM measurement, satisfy at least one of the following: Longer measurement cycle; The measurement window length is smaller; The number of SSBs measured was even smaller; The number of neighboring cells measured was even smaller.

41. The terminal device of any one of claims 36 to 40, wherein, The relaxation factors measured using the AI ​​model-assisted RRM measurement include: The measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device, respectively; or... The terminal device uses a measurement relaxation factor shared by its serving cell and neighboring cells.

42. The terminal device of any one of claims 36 to 41, wherein, The validity verification configuration prior to using the AI ​​model includes at least one of the following: The measurement duration for the terminal device to perform validity verification; The error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; The total number of times the terminal device performs validity verification; The threshold number of valid attempts for the terminal device to perform validity verification; The threshold for the proportion of valid validation attempts performed by the terminal device to the total number of validation attempts; The configuration information for re-performing validity verification when the AI ​​model is invalid.

43. The terminal device of any one of claims 36 to 42, wherein, The validity verification configuration during the use of the AI ​​model includes at least one of the following: Configure the execution of periodic validity verification; Configure the validity verification for event-triggered events; Configure to skip performing periodic validity checks.

44. The terminal device of claim 43, wherein, The configuration for performing periodic validity verification includes at least one of the following: The periodic validity verification cycle; The measurement duration for the periodic validity verification; The periodic effectiveness verification measures the relaxation factor; The periodic validity verification of the SMTC; The configuration of the prediction results for the periodic validity verification.

45. The terminal device of claim 43 or 44, wherein, The configuration for validity verification triggered by the execution event includes at least one of the following events: The terminal device selects or reselects a new cell; The terminal device enters a state of residing in any cell; The signal quality of the serving cell of the terminal device is less than the fifth threshold. The terminal device failed to initiate random access.

46. The terminal device of any one of claims 43 to 45, wherein, The configuration for skipping the periodic validity verification includes: A time threshold, wherein if the time interval between the validity verification triggered by the execution event and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

47. The terminal device of any one of claims 36 to 46, wherein, The terminal device also includes: The processing module is configured to perform RRM measurement based on the SMTC and / or the measured relaxation factor when the triggering conditions for using the AI ​​model to assist RRM measurement are met.

48. The terminal device of any one of claims 36 to 47, wherein, The terminal device also includes: The processing module is used to obtain predicted measurement results based on the actual measurement results using the AI ​​model; The processing module is further configured to perform cell selection or cell reselection based on the predicted measurement results, or based on the predicted measurement results and the actual measurement results.

49. The terminal device of any one of claims 36 to 48, wherein, The terminal device also includes: The processing module is used to perform RRM measurement according to the measurement duration for validity verification, and obtain a first measurement result set, which includes multiple actual measurement results; The processing module is further configured to select a portion of the actual measurement results from the first measurement result set based on the SMTC measured using the AI ​​model-assisted RRM and / or the measurement relaxation factor measured using the AI ​​model-assisted RRM, to obtain a second measurement result set; The processing module is further configured to obtain at least one predicted measurement result based on the second measurement result set using the AI ​​model, wherein the at least one predicted measurement result is filled into the second measurement result set to obtain a third measurement result set; The processing module is further configured to determine the validity verification result of the AI ​​model based on the difference between the first measurement result set and the third measurement result set.

50. The terminal device of claim 49, wherein, The differences between the first measurement result set and the third measurement result set include at least one of the following: The difference between the average value of each measurement result in the first measurement result set and the average value of each measurement result in the third measurement result set; The variance of the differences between each measurement result in the first measurement result set and the corresponding measurement result in the third measurement result set.

51. The terminal device according to any one of claims 36 to 50, characterized in that, The terminal device also includes: The processing module is used to perform multiple validity verifications on the AI ​​model; The processing module is further configured to determine that the AI ​​model is valid when the number of valid occurrences of the AI ​​model is greater than or equal to the effective occurrences threshold, or when the proportion of the effective occurrences of the AI ​​model to the total number of occurrences is greater than or equal to the proportion threshold.

52. The terminal device according to any one of claims 36 to 51, characterized in that, The terminal device also includes: The processing module is used to perform periodic validity verification on the AI ​​model during the use of the AI ​​model, and / or to perform event-triggered validity verification on the AI ​​model.

53. The terminal device according to any one of claims 36 to 52, characterized in that, The terminal device also includes: The processing module is configured to, in the event that the AI ​​model is invalid, not perform validity verification for the AI ​​model for a set period of time according to the configuration information for re-performing validity verification, and / or, perform validity verification for the AI ​​model again after the set period of time.

54. The terminal device according to any one of claims 36 to 53, characterized in that, The terminal device also includes: The processing module is used to indicate to the network device that the AI ​​model is invalid by initiating random access if the AI ​​model is invalid.

55. The terminal device according to any one of claims 36 to 54, characterized in that, The terminal device also includes: The sending module is used to send capability information to the network device when in a connected state. The capability information is used to indicate whether the terminal device supports the ability to use the AI ​​model to assist in RRM measurement.

56. The terminal device according to any one of claims 36 to 55, characterized in that, The receiving module is configured to receive a system broadcast message, wherein the system broadcast message includes the first information; or... The receiving module is configured to receive a first dedicated signaling, wherein the first dedicated signaling includes the first information; or... The receiving module is used to receive a second dedicated signaling, which includes the address information of the server, and to obtain the first information from the server based on the address information of the server.

57. A network device, characterized in that, The network device includes: The transmitting module is used to transmit first information, which is used to determine relevant information of an artificial intelligence (AI) model, and the AI ​​model is used to assist in radio resource management (RRM) measurement.

58. The network device according to claim 57, characterized in that, The relevant information of the AI ​​model includes at least one of the following: The instruction information of the AI ​​model; The model data of the AI ​​model; Indicator information indicating whether the AI ​​model is activated; The effective region information of the AI ​​model; The configuration information of the AI ​​model.

59. The network device according to claim 57 or 58, characterized in that, The configuration information of the AI ​​model is used to determine at least one of the following: Triggering conditions for using the AI ​​model to assist in RRM measurement; The AI ​​model is used to assist in the timing configuration of SSB measurement for RRM measurement; The AI ​​model was used to assist in the measurement of relaxation factors in RRM measurements. Configuration of prediction results for RRM measurement using the AI ​​model; Cells using the AI ​​model to assist in RRM measurements; Validation configuration prior to using the AI ​​model; The validity verification configuration during the use of the AI ​​model.

60. The network device according to any one of claims 57 to 59, characterized in that, The triggering conditions for using the AI ​​model to assist in RRM measurement include at least one of the following: The terminal device receives an instruction to activate the AI ​​model; The terminal device is located within the effective area of ​​the AI ​​model; The AI ​​model is effective; The signal quality of the serving cell of the terminal device is greater than the first threshold. The signal quality of the neighboring cell of the terminal device is greater than the second threshold. The terminal device's moving speed is less than the third threshold; The distance between the terminal device and the reference point is less than the fourth threshold.

61. The network device according to any one of claims 57 to 60, characterized in that, SMTCs measured using the AI ​​model-assisted RRM measurement, compared to SMTCs measured without the AI ​​model-assisted RRM measurement, satisfy at least one of the following: Longer measurement cycle; The measurement window length is smaller; The number of SSBs measured was even smaller; The number of neighboring cells measured was even smaller.

62. The network device according to any one of claims 57 to 61, characterized in that, The relaxation factors measured using the AI ​​model-assisted RRM measurement include: The measurement relaxation factors corresponding to the serving cell and neighboring cells of the terminal device; or, The measurement relaxation factor shared by the serving cell and neighboring cells of the terminal device.

63. The network device according to any one of claims 57 to 62, characterized in that, The validity verification configuration prior to using the AI ​​model includes at least one of the following: The measurement time for the terminal device to perform validity verification; The error threshold between the actual measurement result of the terminal device and the predicted measurement result obtained by the AI ​​model; The total number of times the terminal device performs validity verification; The threshold for the number of valid validation attempts performed by the terminal device; The threshold for the percentage of valid validation attempts performed by the terminal device out of the total number of validation attempts; The configuration information for re-performing validity verification when the AI ​​model is invalid.

64. The network device according to any one of claims 57 to 63, characterized in that, The validity verification configuration during the use of the AI ​​model includes at least one of the following: Configure the execution of periodic validity verification; Configure the validity verification for event-triggered events; Configure to skip performing periodic validity checks.

65. The network device according to claim 64, characterized in that, The configuration for performing periodic validity verification includes at least one of the following: The periodic validity verification cycle; The measurement duration for the periodic validity verification; The periodic effectiveness verification measures the relaxation factor; The periodic validity verification of the SMTC; The configuration of the prediction results for the periodic validity verification.

66. The network device according to claim 64 or 65, characterized in that, The configuration for validity verification triggered by the execution event includes at least one of the following events: The terminal device selects or reselects a new cell; The terminal device enters a state of residing in any cell; The signal quality of the serving cell of the terminal device is less than the fifth threshold. The terminal device failed to initiate random access.

67. The network device according to any one of claims 64 to 66, characterized in that, The configuration for skipping the periodic validity verification includes: A time threshold, wherein if the time interval between the validity verification triggered by the execution event and the next periodic validity verification is less than the time threshold, the execution of the next periodic validity verification is skipped.

68. The network device according to any one of claims 57 to 67, characterized in that, The network device also includes: The receiving module is used to receive random access messages sent by the terminal device, wherein the random access messages contain information indicating that the AI ​​model is invalid.

69. The network device according to any one of claims 57 to 68, characterized in that, The network device also includes: The receiving module is used to receive capability information sent by the terminal device in the connected state. The capability information is used to indicate whether the terminal device supports the ability to use the AI ​​model to assist in RRM measurement.

70. The network device according to any one of claims 57 to 69, characterized in that, The sending module is used to send a system broadcast message, the system broadcast message including the first information; or... The sending module is configured to send a first dedicated signaling message, wherein the first dedicated signaling message includes the first information; or... The sending module is used to send a second dedicated signaling, which includes the address information of the server. The address information of the server is used to obtain the first information from the server.

71. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to cause the terminal device to perform the method as described in any one of claims 1 to 21.

72. A network device, characterized in that, The network device includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to cause the network device to perform the method as described in any one of claims 22 to 35.

73. 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 21, or to implement the method as claimed in any one of claims 22 to 35.

74. 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 21, or to implement the method as described in any one of claims 22 to 35.

75. 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 21, or the method as claimed in any one of claims 22 to 35.

Images