Communication method, terminal device, and network device

Abstract

Provided are a communication method, a terminal device, and a network device. The method comprises: a terminal device receives configuration information sent by a network device, the configuration information being used for configuring the terminal device to report performance‑related data of a measurement event prediction function, wherein the performance‑related data is related to one or more of the following performance indicators: a measurement prediction performance indicator, an intermediate result performance indicator, and a system‑level performance indicator.

Description

Communication methods, terminal equipment and network equipment Technical Field

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

[0002] Some terminal devices have models or functions for predicting measurement events. To improve prediction accuracy, performance monitoring of these models or functions is necessary. However, how to perform performance monitoring and report relevant data on the terminal devices are technical problems that need to be solved. Summary of the Invention

[0003] This application provides a communication method, a terminal device, and a network device. The various aspects covered by this application are described below.

[0004] In a first aspect, a communication method is provided, comprising: a terminal device receiving configuration information sent by a network device, the configuration information being used to configure performance-related data of the terminal device's reported measurement event prediction function; wherein the performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0005] Secondly, a communication method is provided, comprising: a network device sending configuration information to a terminal device, the configuration information being used to configure performance-related data of the terminal device's measurement event prediction function; wherein the performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0006] Thirdly, a terminal device is provided, the terminal device comprising: a receiving unit, configured to receive configuration information sent by a network device, the configuration information being configured to configure performance-related data of the terminal device's reported measurement event prediction function; wherein the performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0007] Fourthly, a network device is provided, the network device comprising: a sending unit, configured to send configuration information to a terminal device, the configuration information being configured to configure performance-related data of the terminal device's measurement event prediction function; wherein the performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0008] Fifthly, a terminal device is provided, including a transceiver, a memory, and a processor, wherein the memory is used to store a program, and the processor is used to invoke the program in the memory and control the transceiver to receive or send signals so that the terminal device performs the method as described in the first aspect.

[0009] A sixth aspect provides a network device including a transceiver, a memory, and a processor, wherein the memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals to cause the network device to perform the method as described in the second aspect.

[0010] A seventh aspect provides a chip including a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in the first or second aspect.

[0011] Eighthly, a computer-readable storage medium is provided having a program stored thereon that causes a computer to perform the method as described in the first or second aspect.

[0012] Ninth aspect, a computer program product is provided, including a program that causes a computer to perform the method as described in the first or second aspect.

[0013] In a tenth aspect, a computer program is provided that causes a computer to perform the method as described in the first or second aspect.

[0014] In this embodiment, the terminal device can report performance-related data of the measurement event prediction function based on the configuration information of the network device. This performance-related data is related to at least one of the measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators. Therefore, the terminal device can monitor and report multiple performance indicators, enabling the network device to evaluate the performance of the measurement event prediction function from multiple dimensions, thereby optimizing the prediction model and improving prediction accuracy. Attached Figure Description

[0015] Figure 1 is a system architecture example diagram of a communication system applicable to embodiments of this application.

[0016] Figure 2 is a schematic diagram of the measurement process of the terminal device.

[0017] Figure 3 is an example diagram of a time-domain prediction that can be applied to an embodiment of this application.

[0018] Figure 4 is an example diagram of another time-domain prediction that can be applied to embodiments of this application.

[0019] Figure 5 is an example diagram of spatial domain prediction that can be applied to embodiments of this application.

[0020] Figure 6 is an example diagram of frequency domain prediction that can be applied to embodiments of this application.

[0021] Figure 7 is a schematic flowchart of a communication method provided in one embodiment of this application.

[0022] Figure 8 is a schematic diagram of the structure of a terminal device provided in one embodiment of this application.

[0023] Figure 9 is a schematic diagram of the structure of a network device provided in one embodiment of this application.

[0024] Figure 10 is a schematic diagram of the structure of a device applicable to the embodiments of this application. Detailed Implementation

[0025] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0026] Communication system

[0027] The embodiments of this application can be applied to various communication systems. For example, the embodiments of this application can be applied to Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), General Packet Radio Service (GPRS), Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), New Radio (NR), evolution systems of NR, LTE-based access to unlicensed spectrum (LTE-U), NR-based access to unlicensed spectrum (NR-U), Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), and 5th-generation (5G) systems. The embodiments of this application can also be applied to other communication systems, such as future communication systems. This future communication system could be, for example, a sixth-generation mobile communication system or a satellite communication system.

[0028] Traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, communication systems can now support not only traditional cellular communication but also one or more other types of communication. For example, a communication system can support one or more of the following communication methods: device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, and vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to communication systems that support the above-mentioned communication methods.

[0029] 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.

[0030] The communication system in this application embodiment can be applied to unlicensed spectrum. This unlicensed spectrum can also be considered a shared spectrum. Alternatively, the communication system in this application embodiment can also be applied to licensed spectrum. This licensed spectrum can also be considered a dedicated spectrum.

[0031] The embodiments of this application can be applied to terrestrial networks (TN) systems as well as non-terrestrial networks (NTN) systems. As an example, the NTN system can include an NR-based NTN system and an Internet of Things (IoT)-based NTN system.

[0032] A communication system may include one or more terminal devices. The terminal devices mentioned in the embodiments of this application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device, etc.

[0033] In some embodiments, the terminal device may be a station (ST) in a WLAN. In some embodiments, the terminal device may also be a cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA) device, handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in a next-generation communication system (e.g., NR system), or terminal device in a future evolved public land mobile network (PLMN) network, etc.

[0034] In some embodiments, the terminal device may be a device that provides voice and / or data connectivity to the user. For example, the terminal device may be a handheld device, an in-vehicle device, etc., with wireless connectivity. As some specific examples, the terminal device may be a mobile phone, tablet, laptop, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc.

[0035] In some embodiments, the terminal device may be deployed on land. For example, the terminal device may be deployed indoors or outdoors. In some embodiments, the terminal device may be deployed on water, such as on a ship. In some embodiments, the terminal device may be deployed in the air, such as on an airplane, balloon, or satellite.

[0036] In addition to terminal devices, the communication system may also include one or more network devices. In this embodiment, the network device may be a device for communicating with the terminal device; this network device may also be referred to as an access network device or a radio access network (RAN) device. For example, the network device may be a base station. In this embodiment, the network device may refer to an access network node (or device) that connects the terminal device to the wireless network. Access network equipment can broadly encompass various names listed below, or be interchangeable with them, such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point (AP), transmitting and receiving point (TRP), transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-mode radio (MSR) node, home base station, network controller, access node, radio node, transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. Base stations can be macro base stations, micro base stations, relay nodes, donor nodes, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0037] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0038] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0039] By way of example and not limitation, in the embodiments of this application, the network device may have mobility characteristics; for example, the network device may be a mobile device. In some embodiments of this application, the network device may be satellite-based or space-based, that is, the network device is installed on a satellite or flying equipment. In some embodiments of this application, the network device may also be a base station installed in locations such as land or water.

[0040] 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) 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.

[0041] For example, Figure 1 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. As shown in Figure 1, the communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal, terminal). The network device 110 can provide communication coverage for a specific geographical area and can communicate with terminal devices located within that coverage area.

[0042] Figure 1 illustrates an exemplary network device and two terminal devices. In some embodiments of this application, the communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area. This application does not limit this aspect.

[0043] In some embodiments of this application, the wireless communication system shown in FIG1 may also include other network entities such as a mobility management entity (MME) and an access and mobility management function (AMF), but this application does not limit this.

[0044] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the communication system 100 shown in FIG1 as an example, the communication devices may include network devices 110 and terminal devices 120 with communication functions. Network devices 110 and terminal devices 120 can be the specific devices described above, which will not be repeated here. The communication devices may also include other devices in the communication system 100, such as network controllers, mobility management entities, and other network entities, which are not limited in this application embodiment.

[0045] To facilitate understanding, some related technical knowledge involved in the embodiments of this application is first introduced. The following related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0046] Radio resource management (RRM) measurement

[0047] In 3GPP cellular communication systems, terminal devices need to use Radio Resource Management (RRM) measurements to determine the strength or quality of radio signals in the serving cell and neighboring cells. The terminal device can then report the measurement results to the network device via a Radio Resource Control (RRC) message in the form of a measurement report, enabling the network device to make handover decisions based on the report. For example, relevant protocols specify how the terminal device performs measurements and how it determines measurement events based on parameters configured in the network device.

[0048] As an example, in NR technology, the terminal device actually measures reference signals configured within the cell, such as synchronization signal blocks (SSBs) or channel state information reference signals (CSI-RS). There are often more than one SSB and CSI-RS. In this application, the reference signal can be replaced by a beam.

[0049] In some embodiments, the results of the terminal device's measurement of the reference signal or beam may include beam-level measurement results and / or cell-level measurement results, as well as layer 1 (L1) measurement results and / or layer 3 (L3) measurement results. RRM measurements can be described with reference to the model diagram in section 9.2.4 of the specification protocol TS 38.300 (see Figure 2).

[0050] The following description uses reference signal received power (RSRP) as an example, combined with multiple reference points in the RRM measurement model shown in Figure 2. It should be understood that the measurement results applied in the embodiments of this application are not limited to RSRP; related measurement results can also be reference signal received quality (RSRQ) or signal to interference plus noise ratio (SINR), which are not limited here.

[0051] Figure 2 includes multiple reference points. Reference point A represents the physical layer measurement sampling stage performed by the terminal device. At reference point A, the terminal device can sample according to beam granularity to obtain measurement results without layer 1 filtering. As shown in Figure 2, the terminal device receives K beams from the network device (e.g., gNB), namely beam 1 to beam K. The terminal device performs physical layer measurement sampling on the K beams to obtain the beam-level L1-RSRP.

[0052] At reference point A1, the terminal equipment performs Layer 1 filtering on the obtained beam measurement results. The relevant protocol specifies the length of the measurement period under a specific RRC configuration. Within one measurement period, the terminal equipment must perform at least one measurement sampling. The number of samplings is an internal implementation requirement of the terminal equipment. The beam measurement results after Layer 1 filtering must meet the relevant performance requirements specified in 3GPP specification 38.133. Generally, the number of samplings by the terminal equipment at reference point A is also specified. For example, in a test case within one measurement period, 4 to 5 oversamplings can be used. That is, the measurement results from 4 to 5 time slots are used for sampling. At reference point A1, after Layer 1 filtering, the filtered beam level L1-RSRP can be obtained.

[0053] At reference point B, the terminal device merges the beam measurement results obtained at reference point A1 within a specific cell to synthesize a Layer 1 cell-level measurement result. As shown in Figure 2, the terminal device can perform beam merging / selection based on RRC configuration parameters to obtain the cell-level L1-RSRP. For example, the terminal device can select several beams whose measurement results are higher than a pre-configured threshold. The threshold and the maximum number of selected beams can be configured by the network device. When no beam meets the criteria, the terminal device selects the measurement result of the beam with the best measurement result as the Layer 1 cell-level measurement result.

[0054] At reference point C, the Layer 1 cell-level measurement results of a certain cell can be filtered by Layer 3 to obtain the Layer 3 cell-level measurement results. Layer 3 filtering can be used for cell quality (L3 filtering for cell quality). Multiple Layer 1 cell-level measurement results can be filtered by Layer 3 in sequence to obtain the cell-level L3-RSRP.

[0055] At reference point D, the measurement results of the serving cell and / or neighboring cells are used to determine whether a specific measurement event is valid according to certain decision conditions (which can be configured by the network equipment). For example, whether the measurement result of the neighboring cell is higher than the measurement result of the primary cell (PCell) by an offset value.

[0056] At reference point E, the layer 3 beam result after layer 3 beam filtering can be obtained, namely the layer 3 beam level RSRP.

[0057] At reference point F, a portion of the Layer 3 beam-level RSRP is reported after filtering. As shown in Figure 2, the K beams at reference point E are reduced to X beams after beam selection for reporting.

[0058] Artificial intelligence (AI) / machine learning (ML) in 3GPP

[0059] The 3GPP protocols include research on AI mobility projects. For example, Release 18 investigated whether AI / ML models could be applied to key physical layer technologies. Release 19, for instance, applied techniques used for beam measurement prediction to RRM measurements.

[0060] In R19, three sub-use cases were defined for the AI ​​Mobility Project: RRM measurement prediction, radio link failure (RLF) / handover failure (HOF) prediction, and measurement event prediction.

[0061] For RRM measurement prediction, the model's input and output can be the information from points A / A1 / B / C / E / F in the RRM measurement model shown in Figure 2. The input and output measurement results can come from the same cell, different cells at different frequency layers, or a group of cells. RRM measurement prediction can be performed in the time domain, frequency domain, or between different frequencies (i.e., frequency domain).

[0062] In some implementations, the terminal device can perform predictions in the time domain, spatial domain, or frequency domain. Prediction in the time domain can be understood as using historical measurement results to predict future measurement results. The timing of the terminal device performing measurements in the time domain is referred to as the measurement timing in this application. The measurement timing can be understood as the sampling timing within a measurement cycle, or as the timing of obtaining the measurement results after Layer 1 filtering. Prediction in the spatial domain can be understood as predicting the measurement results of other reference signals by measuring a portion of the reference signals within a cell. Prediction in the frequency domain can be understood as using the measurement results at one frequency point to predict the measurement results at another frequency point.

[0063] For RRM measurement prediction, relevant conferences (such as RAN2#126) have defined four high-priority study scenarios. These four scenarios are time-domain scenario A, time-domain scenario B, spatial prediction, and frequency-domain prediction. The following sections, with reference to Figures 3 to 6, will introduce each of these four high-priority scenarios.

[0064] Figure 3 is a schematic diagram of the prediction in the time domain scenario A. The shaded boxes in Figure 3 represent the measured results, and the white boxes represent the predicted results. As shown in Figure 3, the first four time points on the time axis represent the measured results. These measured results are used for prediction to obtain the predicted results for the last two time points.

[0065] As shown in Figure 3, the prediction of time-domain scenario A refers to predicting the measurement results for a future period of time using historical measurement results. For example, using the four measured results from time slots 1 to 4, the measurement results for time slots 5 and 6 are predicted.

[0066] Figure 4 shows a prediction diagram for time-domain scenario B. Similar to Figure 3, the shaded box represents the measured results, and the white box represents the predicted results. As shown in Figure 4, the time instances of the measured or predicted results are not continuous, but rather skipped time instances.

[0067] As shown in Figure 4, the prediction of time-domain scenario B refers to interpolation prediction using partial measurement results; therefore, it can also be called time-domain interpolation-based measurement prediction. In some implementations, even-numbered time slots can be predicted based on the measured results of odd-numbered time slots, or vice versa. For example, the measured results of time slots 1, 3, 5, and 7 can be used to predict the values ​​of time slots 2, 4, 6, and 8. Similarly, the measured results of time slots 1, 3, 5, and 7 can be used to predict the value of time slot 8, and the measured results of time slots 3, 5, 7, and 9 can be used to predict the value of time slot 10, and so on. Likewise, the measured results of time slots 1, 5, and 9 can be used to predict the values ​​of time slots 10 and 11, and the measured results of time slots 5, 9, and 13 can be used to predict the values ​​of time slots 14 and 15, and so on.

[0068] Figure 5 is a schematic diagram of spatial domain prediction. The shaded area in Figure 5 represents the measurement beam, and the gray area represents the prediction beam. The mean reciprocal rank (MRR) of the model is 50%. As shown in Figure 5, measurement instances in spatial domain prediction can be indicated based on the azimuth angle and zenith angle. The prediction beam and measurement beam are set sequentially along the azimuth and zenith angles.

[0069] As shown in Figure 5, spatial prediction refers to using the measurement results of a portion of the beams to predict the measurement values ​​of the remaining unmeasured beams.

[0070] Figure 6 is a schematic diagram of frequency domain prediction. In Figure 6, the gray area represents cell B, and the shaded area represents cell A. In the scenario shown in Figure 6, the measured results of the frequency point represented by the shaded area (cell A) can be used to predict the signal coverage of the frequency in the gray area (cell B).

[0071] As shown in Figure 6, higher-priority frequency domain prediction refers to using the measurement value of a certain frequency point to predict the measurement values ​​of other frequencies. This frequency domain prediction method can also be called inter-frequency measurement prediction.

[0072] For HOF / RLF events, as one of the three use cases in the AI / ML mobility project, direct or indirect prediction methods can be employed. It is important to note that the measurement results input to the relevant models must include at least the serving cell and / or neighboring cells directly related to the event.

[0073] For measurement event prediction, relevant protocols define two methods: direct prediction and indirect prediction. In the indirect prediction method, the results of RRM measurement predictions are combined with configuration parameters related to a specific measurement event in the network configuration to infer whether a measurement event will occur at a future point in time. In the direct prediction method, the input measurement results (including at least the serving cell and / or neighboring cells directly related to the event) are used to infer whether a measurement event has occurred using a model.

[0074] In some implementations, the serving cell is the cell currently corresponding to the terminal device, and the neighboring cells are the cells adjacent to the serving cell.

[0075] In some implementations, direct prediction is based on historical measurement data (e.g., RSRP) to directly predict whether a measurement event will occur. Measurement events include, for example, the A3 event in Layer 3 measurement events, or LTM events related to lower-layer triggered mobility (LTM) cell replacement.

[0076] As an example, layer 3 measurement events may include the following events:

[0077] A1 event: The serving cell becomes better than the threshold;

[0078] A2 event: The serving cell becomes worse than the threshold;

[0079] A3 incident: The neighboring cell has better offset than the main cell;

[0080] A4 event: Neighboring cells become better than the threshold;

[0081] Event A5: The primary cell becomes worse than threshold 1 and the neighboring cell becomes better than threshold 2;

[0082] Event A6: The neighboring cell had better offset than the auxiliary cell.

[0083] As an example, LTM events can include the following events:

[0084] LTM2 event: The serving cell's beam becomes worse than the absolute threshold;

[0085] LTM3 event: The candidate cell’s beam is better than the serving cell’s beam by a specific offset;

[0086] LTM4 event: The beam of the candidate cell becomes better than the absolute threshold;

[0087] LTM5 event: The serving cell’s beam becomes worse than absolute threshold 1 and the candidate cell’s beam becomes better than absolute threshold 2.

[0088] In some implementations, indirect prediction is based on historical measurement data to first predict unmeasured or future measurement values, and then uses the predicted measurement values ​​and traditional switching mechanisms to determine whether a measurement event will occur. As one implementation, after obtaining the prediction result based on the aforementioned RRM measurement prediction, it is possible to further determine whether a measurement event has occurred. For example, based on the RSRP value of the past 2 seconds, the RSRP for the next 3 seconds is predicted, and then the predicted RSRP is used to determine whether an A3 event will occur in the next 3 seconds based on traditional measurement event decision methods.

[0089] The preceding text, with reference to Figures 1 to 6, introduced the relevant technologies for RRM measurement prediction and measurement event prediction using AI / ML on terminal devices. Both RRM measurement prediction and measurement event prediction can be implemented based on corresponding functions or models. Simultaneously, performance monitoring of these functions or models is necessary to ensure prediction accuracy.

[0090] However, in related technologies, there are no clear regulations on the performance monitoring and reporting methods for measurement event prediction of terminal devices. In other words, the current performance monitoring methods for measurement event prediction functions or models are too general. For example, they only require reporting the error between the measured value and the predicted value of the terminal device, but lack specific configuration information on the network side, as well as the reporting conditions and / or reporting information of the terminal device.

[0091] Furthermore, when predicting measurement events using indirect prediction methods, the switching of the performance monitoring phase is determined based on the predicted values. However, for the time-domain scenario B (based on interpolation) and frequency-domain predictions mentioned earlier, the predicted values ​​are not the most accurate basis for judgment. This is because, in both prediction methods, performance monitoring at the current moment may be based on measured values. Compared to predicted values, switching based on measured values ​​is more accurate. If switching is based on measured values, the configuration of the predicted values ​​also needs to be considered.

[0092] In summary, how terminal devices can monitor the performance of measurement event prediction functions or models and report related issues is a technical problem that needs to be solved.

[0093] To address the aforementioned issues, this application provides a communication method. In this method, a terminal device receives configuration information from a network device and determines, based on this information, the performance-related data for the measurement event prediction function that the terminal device needs to report. The terminal device needs to monitor one or more performance metrics associated with this performance-related data: measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. By introducing multiple performance metrics, the network can evaluate the performance of measurement event prediction from multiple dimensions, thereby optimizing the prediction model and significantly improving prediction accuracy.

[0094] The embodiments of this application will now be described in detail with reference to Figure 7. In the embodiments of this application, "prediction" and "inference" can be used interchangeably.

[0095] Figure 7 is a schematic flowchart of the communication method provided in an embodiment of this application. The method shown in Figure 7 is described from the perspective of the interaction between the terminal device and the network device. The terminal device can be any communication terminal with a measurement event prediction model or measurement event prediction function, such as a UE. The network device can be any network-side device that communicates with the terminal device, such as a base station.

[0096] In some implementations, having a measurement event prediction model on the terminal device can be understood as having a measurement event prediction model deployed on the terminal device side. The measurement event prediction model can predict measurement events based on direct or indirect prediction methods. The measurement event prediction model on the terminal device side can utilize artificial intelligence algorithms for prediction. This measurement event prediction model can be an AI model or a ML model.

[0097] In some implementations, the terminal device's measurement event prediction function can be understood as possessing the capability to predict measurement events. This function can be used for direct or indirect prediction of measurement events. Furthermore, the measurement event prediction function is based on AI / ML models; that is, the terminal device can utilize artificial intelligence algorithms to implement this function.

[0098] In some implementations, the terminal device can send capability information to the network device. This capability information can indicate that the terminal device has deployed a measurement event prediction model or possesses measurement event prediction capabilities.

[0099] As an implementation method, a model with the function of predicting measurement events can also be called a measurement event prediction model.

[0100] Referring to Figure 7, in step S710, the terminal device receives configuration information sent by the network device.

[0101] The configuration information is used to configure the performance-related data of the measurement event prediction function reported by the terminal device. The performance-related data of the measurement event prediction function can be understood as the result of performance monitoring of the measurement event prediction function or measurement event prediction model, or as data related to the performance of the measurement event prediction function or measurement event prediction model. In this embodiment, the performance-related data can also be replaced with performance data or predicted performance data. For simplicity, the following description uses the measurement event prediction function as an example.

[0102] The measurement event prediction function can be used by terminal devices to predict whether measurement events will occur in the future, so that network devices can prepare for measurement and / or handover. The measurement event prediction function can predict the occurrence time and event type of measurement events. The event type can be the A1 to A6 events or LTM events mentioned above, or other or future-defined measurement events, which are not limited here.

[0103] In some implementations, the measurement events triggered by the terminal device can be related to the terminal device's cell handover. Cell handover by the terminal device can include traditional Layer 3 handover, conditional Layer 3 handover, and LTM cell replacement, etc.

[0104] In some implementations, the measurement event prediction function is used to perform direct and / or indirect prediction of measurement events. Therefore, the measurement event prediction function on the terminal device side can support multiple prediction methods for diverse performance monitoring. As one implementation, the measurement event prediction function can be used to perform direct prediction of measurement events. For example, it can directly predict whether a measurement event will occur at a future point in time or during a specific time period based on current and / or historical measurement data. As another implementation, the measurement event prediction function can be used to perform indirect prediction of measurement events. For example, it can predict measurement results based on the measurement prediction function, and then determine whether a measurement event will occur at a future point in time or during a specific time period based on the prediction results and related switching mechanisms. As yet another implementation, the measurement event prediction function can be used to perform both direct and indirect prediction of measurement events.

[0105] In some implementations, the measurement event prediction function can be used to predict at least one predicted measurement event. A predicted measurement event can be understood as a measurement event that the AI / ML model predicts will occur. The terminal device can evaluate the performance of the measurement event prediction function using actual measurement events related to at least one predicted measurement event. An actual measurement event can be understood as a measurement event that actually occurs. The correlation between a predicted measurement event and an actual measurement event can refer to measurement events that occur at the same or similar times and / or are of the same type.

[0106] The measurement prediction function can predict measurement results in the time, spatial, or frequency domains. For example, it can be used to predict measurement results in the four higher-priority scenarios described above. Furthermore, it can perform one or more of the following functions: prediction of measurement results within a frequency range; prediction of measurement results between frequencies (as shown in Figure 6). Also, it can perform one or more of the following functions: prediction of measurement results based on historical data in the time domain (as shown in Figure 3); prediction of measurement results based on interpolation in the time domain (as shown in Figure 4).

[0107] The measurement results between frequencies can be determined based on actual measurement results, and the measurement results between frequencies and the actual measurement results are for different frequencies. The frequency corresponding to the measurement results may or may not belong to the service frequency of the terminal equipment.

[0108] Interpolation-based measurement results in the time domain can be determined based on actual measurement results, with the interval between the measurement timing corresponding to the actual measurement results and the measurement timing of the predicted measurement results set. This setting method can be determined based on the configuration information of network devices or higher layers.

[0109] In some implementations, the inference results of the measurement prediction function may include one or more predicted measurement results. Predicted measurement results can be understood as measurement results determined by the prediction function or prediction model, i.e., predicted values ​​or prediction results. In contrast to predicted measurement results, measurement results determined through actual measurement can be called measured measurement results, or simply measured values, measured results, or actual measurement results.

[0110] As one implementation method, the measured or predicted measurement results can be RSRP, RSRQ, or SINR, and no specific limitation is made here.

[0111] In some implementations, the inference result of the measurement prediction function includes at least one predicted measurement result within a prediction window. This prediction window may include one or more measurement opportunities or measurement instances. For example, in time-domain prediction, the prediction window may be a time period including multiple measurement opportunities. This time period may be continuous or discontinuous. Similarly, in frequency-domain measurement, the prediction window may include signal coverage at multiple measurement frequencies. And, in spatial-domain prediction, the prediction window may include multiple different measurement beams.

[0112] In the above implementation, the prediction window can be configured by the network device or determined by the terminal device based on the actual communication situation.

[0113] In the above implementation, the measurement prediction function is used to make predictions at one or more measurement points within a prediction window to determine the predicted measurement results at these measurement points. The one or more predicted measurement results can be arranged based on time sequence.

[0114] In the above implementation, the measurement prediction function is used to make predictions on one or more measurement instances within a prediction window to determine the predicted measurement results for these measurement instances. The one or more predicted measurement results can be arranged based on frequency magnitude or positional relationship.

[0115] In the above implementation, the prediction window can serve as a performance monitoring window for the measurement prediction function. The terminal device can perform actual measurements within the prediction window and monitor the performance of the measurement prediction function based on the actual measurement results and the predicted measurement results.

[0116] In some implementations, the measurement prediction model of the terminal device can be an RRM measurement prediction model. The measurement prediction function of the terminal device can also be an RRM measurement prediction function. As one implementation, the measured or predicted measurement results can be any measurement result obtained from the RRM measurement model. For example, the measurement values ​​corresponding to the various reference points shown in Figure 2. These measurement values ​​can be one or more of the following: Layer 1 measurement results and / or Layer 3 measurement results, cell-level measurement results and / or beam-level measurement results, filtered measurement results and / or unfiltered measurement results.

[0117] In some implementations, the measurement object associated with the measurement prediction function can be a reference signal within the serving cell of the terminal device, a reference signal within a neighboring cell of the serving cell of the terminal device, or a reference signal within a candidate cell corresponding to the terminal device. The reference signal can be an SSB or a CSI-RS.

[0118] Performance-related data is used to indicate the performance of the measurement event prediction function. This performance-related data includes key performance indicators (KPIs) for the measurement event prediction function. Terminal devices can report performance-related data to network devices to indicate the current performance status of the measurement event prediction function, enabling the network devices to optimize the function in a timely manner. Performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0119] In some implementations, performance-related data is used to train or update a model with measurement event prediction capabilities. For example, a terminal device or network device can train a model with measurement event prediction capabilities based on this performance-related data. Alternatively, a terminal device or network device can update a model with measurement event prediction capabilities based on this performance-related data to optimize the measurement event prediction function.

[0120] In some implementations, measurement prediction performance metrics are used to indicate the performance of the measurement prediction function of the terminal device to evaluate the prediction accuracy of the measurement results. In indirect prediction methods for measurement events, the terminal device can predict measurement events based on the inference results of the measurement prediction function. If the prediction performance of the measurement prediction function is good, the accuracy of the measurement event prediction function is high. If the prediction performance of the measurement prediction function is poor, it may reduce the accuracy of the measurement event prediction function.

[0121] As one implementation, measurement prediction performance metrics can include measurement prediction KPIs to monitor the performance of the measurement prediction function. When the measurement prediction function is an RRM measurement prediction function, the measurement prediction performance metrics include RRM measurement prediction KPIs.

[0122] As an implementation approach, measurement prediction performance metrics can include various types of parameters. For example, measurement prediction performance metrics may include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; beam-level measurement results; cell-level measurement results; filtered measurement results; unfiltered measurement results; and the error of at least one predicted measurement result within the prediction window. These will be described in detail below with reference to Example 1.

[0123] As one implementation approach, the measurement prediction function of a terminal device can be implemented through a measurement prediction model deployed on the terminal device side. It should be understood that the measurement prediction function and the event prediction function of the terminal device can be implemented using the same model or different models; this is not limited here. For example, a measurement prediction model and a measurement event prediction model can be deployed separately on the terminal device side. Alternatively, an AI / ML model deployed on the terminal device side can simultaneously predict both measurement results and measurement events.

[0124] In some implementations, performance monitoring of the measurement prediction function can be used to monitor the performance of the measurement event prediction function based on indirect prediction. Performance monitoring of the measurement prediction function can be achieved through one or more measured results. In other words, the performance of the measurement prediction function is determined based on at least one measured result within the prediction window. When the terminal device receives this at least one measured result, it is also used by the terminal device or network device to make a handover decision. The handover decision can be understood as whether to perform a handover.

[0125] As one implementation, at least one measured result within the prediction window is used to determine the accuracy of the predicted measurement result, thereby assessing the performance of the measurement prediction function. When this at least one measured result is used for switching decisions, the corresponding at least one predicted measurement result is no longer used for switching decisions. At least one predicted measurement result can be used solely for performance monitoring of the measurement prediction function.

[0126] As one implementation, network devices can be configured to use at least one measured result within a prediction window for handover decision-making. Within this prediction window (performance monitoring window), the terminal device performs actual measurements at the predicted measurement time to compare the measured results with the predicted measurement results. For example, the network device's configuration information can configure at least one measured result within the prediction window for handover decision-making.

[0127] In the above implementation, when the terminal device needs to report the measurement results within the prediction window, the reported value can be the actual measurement result. For example, the network device's configuration information can configure at least one actual measurement result within the prediction window to also be used for data reporting.

[0128] As one implementation, network devices can be configured so that predicted measurement results within the prediction window used for performance monitoring are not used for handover decisions. For example, the network device's configuration information can also be used to configure at least one predicted measurement result within the prediction window not to be used for handover decisions. Alternatively, the network device can be configured so that at least one predicted measurement result within the prediction window is used only for performance monitoring. Furthermore, the network device can also be configured so that at least one predicted measurement result within the performance monitoring window of the measurement prediction function is not used for data reporting.

[0129] For example, in time-domain interpolation-based measurement prediction, the terminal device, based on the measured results of time slots 1, 3, 5, and 7, can use an AI model to predict the measurement results for time slots 2, 4, 6, and 8. To monitor the performance of the measurement prediction function, the terminal device also performs actual measurements on time slots 2, 4, 6, and 8. Therefore, the terminal device can obtain the measured results for time slots 1-8. Since the measured results are more accurate than the predicted results, the terminal device can use the measured results for time slots 1-8 to make switching decisions, instead of using the predicted results. Furthermore, the predicted measurement results for time slots 2, 4, 6, and 8 can be used only to determine the prediction error for even-numbered time slots.

[0130] In the aforementioned implementation methods, under certain prediction scenarios of the measurement prediction function, at least one actual measurement result within the prediction window is used for switching decisions. These prediction scenarios may include time-domain interpolation-based measurement result prediction and / or frequency-based measurement result prediction. Under these prediction scenarios, the terminal device can perform actual measurements at the current time, thereby acquiring real data. For example, for performance monitoring based on indirect prediction, if the indirect prediction of the measurement event is based on time-domain scenario B or frequency-based prediction, the terminal device can use the actual acquired data for switching decisions, and the predicted data can be used solely for performance monitoring.

[0131] As an example, for performance monitoring of the measurement prediction function, the terminal device can report the predicted measurement results and the corresponding actual measurement results, or it can report the difference between the predicted measurement results and the corresponding actual measurement results, so that the network device can determine the performance results.

[0132] As another example, network devices can also configure error thresholds for terminal devices. The terminal device can first determine the prediction error, which is the difference between the predicted measurement result and the corresponding measured result; then, it reports the error based on the relationship between the prediction error and the error threshold. For example, the terminal device can report whether the prediction error is less than the error threshold configured by the network device using 1 bit. When the value of this 1 bit is 0, it indicates that the prediction error is less than the error threshold; when the value of this 1 bit is 1, it indicates that the prediction error is not less than the error threshold, and vice versa.

[0133] In some implementations, intermediate result performance metrics can be used to indicate the performance of the measurement event prediction function itself. These metrics can be used to evaluate the quality of the measurement event prediction algorithm, i.e., algorithm performance. When the algorithm for the measurement event prediction function is reasonable or applicable, the prediction accuracy of the measurement events is high; when the algorithm is not applicable, the prediction accuracy of the measurement events will decrease.

[0134] As an implementation approach, intermediate result performance metrics can be termed intermediate result KPIs. Intermediate result performance metrics can include intermediate parameters and / or metrics used to evaluate the algorithm. For example, intermediate result performance metrics can include one or more of the following: F-axis metrics that measure the event prediction function. β Score; measures the precision of the event prediction function; measures the recall of the event prediction function; first intermediate parameter. These will be described in detail later with reference to Example 2.

[0135] In the above implementation, the first intermediate parameter can be determined based on at least one predicted measurement event and / or at least one measured measurement event of the terminal device. The at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event related to the first predicted measurement event. The first intermediate parameter can be used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event. That is, the first intermediate parameter can represent the interval between the occurrence time of the predicted measurement event and the occurrence time of the measured measurement event. When this interval is less than the maximum tolerance error window configured by the network device, the prediction can be considered accurate. For direct or indirect prediction, by configuring the maximum tolerance error window value, the accuracy of the measurement event prediction result can be evaluated more accurately.

[0136] In some implementations, system-level performance metrics can be used to indicate handovers related to measurement event prediction. This handover can be any type of handover based on measurement results or triggered by measurement events, such as cell handovers. System-level performance metrics are related to overall network performance and user experience. When the accuracy of measurement event predictions is high, system-level performance metrics can reflect good network performance. Monitoring system-level performance metrics helps to optimize measurement event prediction strategies from a holistic perspective, improving overall network performance and user experience.

[0137] As an implementation approach, system-level performance metrics can be referred to as system-level KPIs. System-level performance metrics can include one or more parameters related to handover. For example, system-level performance metrics can include one or more of the following: handover failure rate of the terminal device; number of handovers per unit time of the terminal device; ping-pong handover rate of the terminal device; short dwell time of the terminal device; number of handover failures per unit time of the terminal device. These will be described in detail later with reference to Example 3.

[0138] In some implementations, the performance-related data reported by the terminal device can be determined based on at least one of the measurement prediction performance metric, intermediate result performance metric, and system-level performance metric, or used to indicate the calculation result of at least one of the measurement prediction performance metric, intermediate result performance metric, and system-level performance metric. This performance-related data can indirectly indicate the current performance of the measurement event prediction function by referring to any performance metric. For example, when an intermediate result performance metric is greater than a first threshold, the performance of the measurement event prediction function meets the requirements, and the performance-related data can be indicated using 1 bit. Similarly, when a system-level performance metric is greater than a second threshold, the prediction performance of the measurement event prediction function can be considered poor, and this can also be indicated using 1 bit.

[0139] As one implementation, the performance-related data used to indicate the measurement event prediction function can be one or more data points. For example, the terminal device determines a performance-related data point based on any one of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators, and then reports it. Alternatively, the performance-related data can include data indicating multiple performance indicators. These multiple performance indicators can be at least two of multiple measurement prediction performance indicators, multiple intermediate result performance indicators, and multiple system-level performance indicators.

[0140] In some implementations, the performance-related data reported by the terminal device can be at least one of measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. That is, the terminal device can directly report at least one of these three metrics. For example, measurement prediction performance metrics can include the error of the predicted measurement result within the prediction window (i.e., prediction error), and the terminal device can directly report the prediction error within the prediction window.

[0141] As one implementation approach, the performance-related data (performance metrics) reported by the terminal device can be a single data point. For example, a performance metric can be any one of multiple measured predictive performance metrics. Similarly, a performance metric can be any one of multiple intermediate result performance metrics. Or, a performance metric can be any one of multiple system-level performance metrics.

[0142] As one implementation, the performance-related data reported by the terminal device can be multiple data sets. For example, performance-related data may include at least two of multiple measured predictive performance metrics, multiple intermediate result performance metrics, and multiple system-level performance metrics. Alternatively, performance-related data may include any performance metric, and may also include related data used to indicate any performance metric.

[0143] The performance-related data reported by the terminal device regarding the measurement event prediction function may also include the terminal device's monitoring of the measurement event prediction function's performance. Configuration information sent by the network device is also used to configure the terminal device's monitoring of the measurement event prediction function's performance. For example, this configuration information may be used to configure the duration of performance monitoring for the measurement event prediction function. Furthermore, the network device may configure KPIs for the terminal device's monitoring of the measurement event prediction function. These KPIs may include RRM prediction KPIs and / or intermediate result KPIs and / or system-level KPIs. The terminal device can monitor the measurement event prediction function's performance based on the KPIs configured by the network device.

[0144] As one implementation, the configuration information used to configure the terminal device to report performance-related data and the configuration information used to configure the terminal device's monitoring and measurement event prediction function can be sent through the same signaling or be the same configuration information.

[0145] As one implementation, the configuration information used to configure the terminal device to report performance-related data and the configuration information used to configure the terminal device's monitoring and measurement event prediction function can be sent using different signaling, or they can be different configuration information. For example, the configuration information used to configure the terminal device to report performance-related data is the first configuration information, and the configuration information used to configure the terminal device's monitoring and measurement event prediction function is the second configuration information. The first configuration information and the second configuration information can be sent using the same or different signaling.

[0146] In some implementations, terminal devices can monitor the performance of the measurement event prediction function based on at least one of the following: measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. Performance monitoring of the measurement event prediction function can be applied to both direct and / or indirect prediction of measurement events. When applicable to both direct and indirect prediction, it provides network devices with diverse monitoring methods.

[0147] As one implementation approach, for direct prediction of measurement events, the performance-related data of the measurement event prediction function is correlated with intermediate result performance metrics and / or system-level performance metrics. In other words, when the measurement event prediction function performs direct prediction of measurement events, its prediction performance can be indicated by intermediate result performance metrics and / or system-level performance metrics. For example, for direct prediction, the KPIs of the measurement event prediction function may include intermediate result KPIs and / or system-level KPIs.

[0148] As one implementation approach, for indirect prediction of measurement events, the performance-related data of the measurement event prediction function is associated with at least one of the following: measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. In other words, when the measurement event prediction function performs indirect prediction of measurement events, the prediction performance can be indicated by at least one of the following: measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. For example, for indirect prediction, the KPIs of the measurement event prediction function may include at least one of the following: RRM prediction KPIs, intermediate result KPIs, and system-level KPIs.

[0149] In some implementations, the network device can also be configured to allow the terminal device to collect statistical information related to performance data and / or the aforementioned performance metrics. That is, the network device's configuration information is also used to configure the terminal device to collect statistical information. This statistical information can be used to determine one or more performance metrics and / or performance-related data associated with the performance-related data. For example, the terminal device can collect statistical information based on the network device's configuration and calculate RRM prediction KPIs and / or intermediate result KPIs and / or system-level KPIs.

[0150] As one implementation, the configuration information used to configure the terminal device to report performance-related data and the configuration information used to configure the terminal device to collect statistical information can be sent using the same signaling, or they can be the same configuration information. For example, the configuration information used to configure the terminal device to report performance-related data can also be used to configure the terminal device to collect statistical information.

[0151] As one implementation, the configuration information used to configure the terminal device to report performance-related data and the configuration information used to configure the terminal device to collect statistical information can be sent using different signaling, or they can be different configuration information. For example, the configuration information used to configure the terminal device to collect statistical information can be a third configuration information. The first configuration information and the third configuration information can be sent using the same or different signaling.

[0152] In some implementations, terminal devices can send performance-related data for measurement event prediction functions based on conditional or event-triggered methods. Network device configuration information is also used to configure the trigger conditions for terminal devices to report performance-related data. These trigger conditions can be called reporting trigger conditions. For example, based on the reporting trigger conditions configured by the network device, the terminal device can report the calculated KPI or whether the KPI meets a given threshold to the network device to optimize measurement event prediction. Based on this, network devices can configure different reporting trigger conditions according to actual needs (such as the number of switching events during AI / ML function operation, timer expiration, KPI values ​​not meeting preset thresholds, etc.), making the monitoring mechanism more flexible and adaptable to different application scenarios and network conditions. Furthermore, by reasonably setting reporting trigger conditions, unnecessary signaling interactions can be reduced, thereby reducing signaling overhead.

[0153] As one implementation, the configuration information used to configure the performance-related data reported by the terminal device and the configuration information used to configure the reporting trigger conditions can be sent using the same signaling, or they can be the same configuration information. For example, the configuration information used to configure the performance-related data reported by the terminal device can also be used to configure the trigger conditions for the terminal device to report performance-related data.

[0154] As one implementation, the configuration information used to configure the performance-related data reported by the terminal device and the configuration information used to configure the reporting trigger conditions can be sent using different signaling, or they can be different configuration information. For example, the configuration information used to configure the reporting trigger conditions for performance-related data is the fourth configuration information. The first configuration information and the fourth configuration information can be sent using the same or different signaling.

[0155] In some implementations, the triggering conditions for a terminal device to report performance-related data may include one or more of the following: reaching the maximum number of handovers within the runtime of the measurement event prediction function; the expiration of the first timer configured by the network device; the performance indicator not meeting the corresponding preset threshold; the network device instructing the terminal device to report performance-related data; and the terminal device reaching the reporting interval period configured by the network device.

[0156] As one implementation, when the maximum number of handovers is reached during the runtime of the event prediction function, the terminal device reports performance-related data for the event prediction function. The maximum number of handovers can be a predefined parameter or determined based on the network device's configuration information. For example, when a given maximum number of handovers is reached during the operation of the AI / ML function, the terminal device reports performance-related data.

[0157] As one implementation, when the first timer configured on the network device expires, the terminal device reports performance-related data related to the measurement event prediction function. The first timer can be used to indicate the monitoring duration of the measurement event prediction function, i.e., the performance monitoring duration. The settings and related parameters of the first timer can be predefined or determined according to the network device configuration. For example, in response to the expiration of the first timer, the terminal device can send measurement prediction performance metrics to the network device.

[0158] As one implementation, when a performance metric fails to meet a corresponding preset threshold, the terminal device reports performance-related data for the measurement event prediction function. The performance metric is at least one of measurement prediction performance metrics, intermediate result performance metrics, and system-level performance metrics. The preset threshold may include at least one of multiple thresholds corresponding to the measurement prediction performance metric, intermediate result performance metric, or system-level performance metric, respectively. For example, when a KPI value related to measurement event prediction fails to meet a preset threshold, the terminal device reports performance-related data.

[0159] In the above implementation, the preset threshold is determined by predefined parameters and / or based on the network device's configuration information. For example, the measured predictive performance indicators, intermediate result performance indicators, and system-level performance indicators can each correspond to a predefined threshold. The preset threshold may include a first threshold corresponding to the intermediate result performance indicator, or a second threshold corresponding to the system-level performance indicator. Furthermore, the network device can configure one or more preset thresholds based on one or more performance indicators related to performance-related data.

[0160] As one implementation, when the network device instructs the terminal device to report performance-related data, the terminal device reports the performance-related data for the measurement event prediction function. In other words, the network device can directly instruct the terminal device to report performance-related data. For example, the network device can explicitly issue a command to instruct the terminal device to report performance-related data. Therefore, the network device can also make judgments based on certain triggering conditions. When the network device confirms that the terminal device needs to report performance-related data, it directly instructs the terminal device to report it.

[0161] As one implementation, when the terminal device reaches the reporting interval configured by the network device, the terminal device reports performance-related data for the measurement event prediction function. Therefore, the terminal device can periodically report performance-related data based on the reporting interval.

[0162] In the above-mentioned implementation methods, network devices can configure parameters such as maximum number of handovers, preset threshold, and first timer, or they can be configured through the first configuration information mentioned above, or through the fourth configuration information related to the reporting trigger conditions.

[0163] In some implementations, terminal devices can send performance-related data for the measurement event prediction function on a periodic reporting basis. When performance-related data is reported periodically, the terminal device can send the measurement report within each reporting interval. Network devices can also configure the reporting interval for performance-related data. By reasonably setting the reporting interval, terminal devices can report key performance data only when necessary, reducing unnecessary signaling interactions and improving the overall efficiency of the system.

[0164] As one implementation, the configuration information used to configure the performance-related data reported by the terminal device and the configuration information used to configure the reporting interval of the performance-related data can be sent using the same signaling, or they can be the same configuration information. For example, the configuration information used to configure the performance-related data reported by the terminal device can also be used to configure the reporting interval of the performance-related data.

[0165] As one implementation, the configuration information used to configure the performance-related data reported by the terminal device and the configuration information used to configure the reporting interval period for performance-related data can be sent via different signaling, or they can be different configuration information. For example, the configuration information used to configure the reporting interval period is the fifth configuration information. The first configuration information and the fifth configuration information can be sent via the same or different signaling.

[0166] In some implementations, the terminal device can send performance-related data for the measurement event prediction function in a combination of periodic reporting and condition-based triggering. For example, the terminal device can trigger the event based on whether a trigger condition is met, and then send performance-related data in a periodic reporting manner.

[0167] In some implementations, performance-related data for the measurement event prediction function can be carried in multiple information formats. These formats may include RRC messages, media access control control elements (MAC CEs), or uplink control information (UCIs). As one implementation, performance-related data can be carried in RRC, MAC CE, or UCI. In other implementations, RRC, MAC CE, and UCI can be combined to send performance-related data.

[0168] The above description, in conjunction with Figure 7, introduces a method for monitoring the performance of measurement event prediction. As described above regarding step S710, in this embodiment, the terminal device can report performance monitoring-related data based on the network device's configuration information. The performance-related data is related to at least one of the measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators, enabling the network device to comprehensively evaluate the predictive performance of the measurement event prediction function. The following sections describe different performance indicators using various embodiments.

[0169] Example 1: RRM for KPI Prediction

[0170] RRM prediction KPIs are measurement prediction performance metrics used to monitor the indirect prediction performance of measured events. Measurement prediction performance metrics can include individual measurements in the RRM model, or the error of at least one predicted measurement within a prediction window.

[0171] In some implementations, RRM prediction KPIs may include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; beam-level measurement results; cell-level measurement results; filtered measurement results; and unfiltered measurement results. Taking the reference points in Figure 2 as examples, the RRM prediction KPIs may include at least one of the following: Layer 1 unfiltered beam-level measurement results corresponding to reference point A (i.e., unfiltered beam-level measurement results), Layer 1 filtered beam-level measurement results corresponding to reference point A1 (i.e., filtered beam-level measurement results), Layer 1 filtered cell-level measurement results corresponding to reference point B, Layer 3 filtered cell-level measurement results corresponding to reference point C, and Layer 3 filtered beam-level measurement results corresponding to reference points E / F. Among these, compared to reference point E, the Layer 3 filtered beam-level measurement results corresponding to reference point F are still beam-selected measurement results.

[0172] As one implementation, RRM can predict KPIs using the RSRP values ​​corresponding to reference points A / A1 / B / C / E / F as shown in Figure 2.

[0173] In some implementations, RRM-predicted KPIs may also include the prediction errors of one or more predicted measurements within the prediction window. For example, RRM-predicted KPIs may also include one or more of the following: the prediction error of all predicted measurements within the prediction window, the average error of all predicted measurements within the prediction window, the prediction error of the last predicted measurement within the prediction window, and the maximum prediction error among the predicted measurements within the prediction window.

[0174] In some implementations, the terminal device can directly report RRM predicted KPIs, or it can report performance-related data based on an error threshold. For example, the terminal device can report the relationship between the error of at least one predicted measurement result within the prediction window and the error threshold.

[0175] In some implementations, the network device can configure a first timer to indicate the monitoring duration. Before the first timer expires, the terminal device can continuously monitor the measurement prediction function and / or measurement event prediction function. As one embodiment, when the first timer expires, the terminal device can report to the network device the average prediction error of all predicted measurement results within the prediction window.

[0176] As an example, the network device is configured to allow the terminal device to indirectly predict measurement events based on time-domain scenario B. The terminal device can monitor the layer 3 cell-level RSRP error and monitor the performance of the measurement event prediction function based on the RSRP error. Specifically, the terminal device can make handover decisions based on the measured RSRP value, while the predicted RSRP value of the measurement function is only used for model performance monitoring.

[0177] Example 2: Intermediate Result KPI

[0178] Intermediate outcome KPIs are performance metrics used to monitor the direct and / or indirect predictive performance of measured events. Intermediate outcome performance metrics may include evaluation metrics for the measured event prediction model, or intermediate parameters used to evaluate the model.

[0179] In some implementations, intermediate result KPIs can include evaluation metrics for the model or algorithm, such as F-values ​​that measure the event prediction capability. β Score and / or precision and / or recall. Recall reflects the model's ability to identify positive samples. The higher the recall, the stronger the model's ability to identify positive samples. Precision reflects the model's ability to distinguish negative samples. The higher the precision, the stronger the model's ability to distinguish negative samples. F β The score is a combination of precision and recall. F β The fraction is greater than 0 and less than 1. F β The higher the score, the more robust the model.

[0180] As an implementation method, F β The β in the score reflects the model's preference for classification ability. When β = 1, F β The score is the F1 score, with precision and recall having equal weight. When β > 1, precision has a greater weight, and a higher recall is better, indicating that the model prioritizes the ability to identify positive samples. When β < 1, recall has a greater weight, and a higher precision is better, indicating that the model prioritizes the ability to distinguish negative samples.

[0181] In some implementations, intermediate result KPIs may include a first intermediate parameter. As mentioned earlier, the first intermediate parameter may indicate or be the interval between the predicted and actual occurrence times of a measurement event. To statistically analyze intermediate results, network devices may configure a maximum tolerance window value for terminal devices. When the interval between the predicted and actual occurrence times of a measurement event is less than the maximum tolerance window, the measurement event prediction is considered accurate. For example, if the first intermediate parameter is the time interval between the occurrence of a first predicted measurement event and a first actual measurement event, and if the first intermediate parameter is less than the maximum tolerance window, the prediction of the first predicted measurement event is considered accurate; if the first intermediate parameter is greater than or equal to the maximum tolerance window, the prediction of the first predicted measurement event is considered inaccurate.

[0182] In some implementations, network devices can configure a first threshold for intermediate result performance metrics. The first threshold may include parameters related to F... βThe first threshold can be at least one of several thresholds corresponding to the F1 score, precision, recall, and a first intermediate parameter. For example, the first threshold could be a threshold value corresponding to the F1 score. Alternatively, the first threshold could be a maximum tolerance error window corresponding to the first intermediate parameter.

[0183] As an example, the network device is configured to monitor the F1 score of terminal devices and report the monitoring results after 10 terminal device handovers. To calculate the F1 score, the network device can also be configured with a maximum tolerance window of 80ms. When the interval between the predicted and actual occurrence times of a measured event is less than 80ms, the prediction is accurate and considered a positive sample. Assuming the first threshold corresponding to the F1 score is 0.8, if the F1 score is less than 0.8, the reported performance-related data indicates that the performance does not meet requirements; if the F1 score is greater than or equal to 0.8, the reported performance-related data indicates that the performance meets requirements.

[0184] In the example above, performance-related data can be indicated using a single bit. For instance, a value of 1 indicates that the performance meets the requirements, while a value of 0 indicates that the performance does not meet the requirements, and vice versa.

[0185] Example 3: System-level KPIs

[0186] System-level KPIs are system-level performance metrics used to monitor the performance of direct and / or indirect prediction of measurement events. System-level performance metrics can be used by network devices to optimize measurement event prediction strategies from a holistic perspective, reduce handover failures and ping-pong handover phenomena, and improve overall network performance and user experience.

[0187] In some implementations, system-level KPIs may include one or more of the following: terminal device handover failure rate, number of handovers per unit time, ping-pong handover rate, short time-of-stay, and number of handover failures per unit time.

[0188] As one implementation approach, network devices can be configured to monitor one or more of the aforementioned system-level KPIs to assess the performance of the measurement event prediction function. For example, terminal devices or network devices can assess the accuracy of the measurement event prediction function by monitoring system-level KPIs (such as handover failure rate, ping-pong handover rate, short dwell time, etc.).

[0189] In some implementations, network devices can configure a second threshold for system-level performance metrics. The second threshold may include at least one of several thresholds that correspond one-to-one with the handover failure rate, number of handovers per unit time, ping-pong handover rate, short dwell time, and number of handover failures per unit time for each terminal device. For example, the first threshold may be a threshold value corresponding to the handover failure rate.

[0190] As an example, the network device is configured to allow terminal devices to directly predict measurement events and to assess the performance of the measurement event prediction function based on the number of handover failures per unit time. If the number of handover failures monitored by the terminal device per unit time exceeds a preset threshold (second threshold) configured by the network device, the prediction performance of the measurement event prediction function is considered poor, and the terminal device reports this.

[0191] Based on the three embodiments described above, this application proposes a performance monitoring method for measurement event prediction in a wireless communication system. This method allows network devices to configure terminal devices to monitor multi-dimensional KPIs (including RRM prediction KPIs, intermediate result KPIs, and system-level KPIs), thereby comprehensively evaluating the prediction performance of measurement events. Terminal devices can also report performance data as needed based on reporting trigger conditions configured by the network device (such as the number of switching operations during AI / ML function runtime, timer expiration, KPI values ​​not meeting thresholds, etc.), thereby reducing signaling overhead. Therefore, this method is a flexible and efficient performance monitoring method for measurement event prediction. By reasonably configuring the relevant KPIs and reporting trigger conditions for the measurement event prediction function, the network device achieves comprehensive monitoring and optimization of the relevant performance of the measurement event prediction function.

[0192] Furthermore, this method can support both direct and indirect prediction of measurement events. During the performance monitoring period of the measurement prediction function, the terminal device can also use measured data for switching decisions, while the predicted data is used only for performance monitoring.

[0193] The method embodiments of this application have been described in detail above with reference to Figures 1 to 7. The apparatus embodiments of this application will be described in detail below with reference to Figures 8 to 10. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments. Therefore, any parts not described in detail can be referred to the foregoing method embodiments.

[0194] Figure 8 is a schematic diagram of a terminal device provided in an embodiment of this application. The terminal device 800 shown in Figure 8 is any of the terminal devices described above. As shown in Figure 8, the terminal device 800 includes a receiving unit 810.

[0195] The receiving unit 810 can be used to receive configuration information sent by the network device. The configuration information is used to configure the performance-related data of the measurement event prediction function reported by the terminal device. The performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0196] In some implementations, the measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

[0197] In some implementations, the inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is further used to configure that the at least one predicted measurement result is not used for the switching decision.

[0198] In some implementations, the measurement prediction function performs one or more of the following functions: prediction of interpolation-based measurement results in the time domain; prediction of measurement results between frequencies.

[0199] In some implementations, the terminal device 800 further includes a sending unit for sending the measurement prediction performance index in response to the expiration of a first timer; wherein the first timer is used to indicate the monitoring duration of the measurement event prediction function.

[0200] In some implementations, the measurement prediction performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; beam-level measurement results; cell-level measurement results; filtered measurement results; unfiltered measurement results; and the error of at least one predicted measurement result within the prediction window.

[0201] In some implementations, the intermediate result performance metrics include one or more of the following: the F-axis of the measurement event prediction function. β Score; precision of the measured event prediction function; recall of the measured event prediction function; first intermediate parameter.

[0202] In some implementations, the first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

[0203] In some implementations, the at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event associated with the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

[0204] In some implementations, the performance-related data is used to indicate the relationship between the intermediate result performance metric and a first threshold, which is determined based on the network device's configuration information.

[0205] In some implementations, the system-level performance metrics include one or more of the following: the handover failure rate of the terminal device; the number of handovers per unit time of the terminal device; the ping-pong handover rate of the terminal device; the short dwell time of the terminal device; and the number of handover failures per unit time of the terminal device.

[0206] In some implementations, the performance-related data is used to indicate the relationship between the system-level performance metric and a second threshold, which is determined based on the network device's configuration information.

[0207] In some implementations, the performance-related data is indicated using one bit.

[0208] In some implementations, the configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

[0209] In some implementations, the triggering conditions include one or more of the following: the maximum number of switching operations is reached within the runtime of the measurement event prediction function; the first timer configured by the network device expires; the performance indicator does not meet the corresponding preset threshold; the network device instructs the terminal device to report the performance-related data; the terminal device reaches the reporting interval period configured by the network device.

[0210] In some implementations, the preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

[0211] In some implementations, the configuration information is further used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

[0212] In some implementations, the measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

[0213] In some implementations, the performance-related data is used to train or update a model with the measurement event prediction function.

[0214] Figure 9 is a schematic diagram of a network device provided in an embodiment of this application. The network device 900 shown in Figure 9 is any of the network devices described above. As shown in Figure 9, the network device 900 includes a transmitting unit 910.

[0215] The sending unit 910 can be used to send configuration information to the terminal device. The configuration information is used to configure the performance-related data of the measurement event prediction function reported by the terminal device. The performance-related data is related to one or more of the following performance indicators: measurement prediction performance indicators, intermediate result performance indicators, and system-level performance indicators.

[0216] In some implementations, the measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

[0217] In some implementations, the inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is further used to configure that the at least one predicted measurement result is not used for the switching decision.

[0218] In some implementations, the measurement prediction function performs one or more of the following functions: prediction of interpolation-based measurement results in the time domain; prediction of measurement results between frequencies.

[0219] In some implementations, the network device 900 further includes a receiving unit, which can be used to receive the measurement prediction performance index sent by the terminal device; wherein the sending time of the measurement prediction performance index is determined based on a first timer, the first timer being used to indicate the monitoring duration of the measurement event prediction function.

[0220] In some implementations, the measurement prediction performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; beam-level measurement results; cell-level measurement results; filtered measurement results; unfiltered measurement results; and the error of at least one predicted measurement result within the prediction window.

[0221] In some implementations, the intermediate result performance metrics include one or more of the following: the F-axis of the measurement event prediction function. β Score; precision of the measured event prediction function; recall of the measured event prediction function; first intermediate parameter.

[0222] In some implementations, the first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

[0223] In some implementations, the at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event associated with the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

[0224] In some implementations, the performance-related data is used to indicate the relationship between the intermediate result performance metric and a first threshold, which is determined based on the network device's configuration information.

[0225] In some implementations, the system-level performance metrics include one or more of the following: the handover failure rate of the terminal device; the number of handovers per unit time of the terminal device; the ping-pong handover rate of the terminal device; the short dwell time of the terminal device; and the number of handover failures per unit time of the terminal device.

[0226] In some implementations, the performance-related data is used to indicate the relationship between the system-level performance metric and a second threshold, which is determined based on the network device's configuration information.

[0227] In some implementations, the performance-related data is indicated using one bit.

[0228] In some implementations, the configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

[0229] In some implementations, the triggering conditions include one or more of the following: the maximum number of switching operations is reached within the runtime of the measurement event prediction function; the first timer configured by the network device expires; the performance indicator does not meet the corresponding preset threshold; the network device instructs the terminal device to report the performance-related data; the terminal device reaches the reporting interval period configured by the network device.

[0230] In some implementations, the preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

[0231] In some implementations, the configuration information is further used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

[0232] In some implementations, the measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

[0233] In some implementations, the performance-related data is used to train or update a model with the measurement event prediction function.

[0234] Figure 10 is a schematic structural diagram of a communication device according to an embodiment of this application. The dashed lines in Figure 10 indicate that the unit or module is optional. This device 1000 can be used to implement the methods described in the above method embodiments. The device 1000 can be a chip, a terminal device, or a network device.

[0235] Apparatus 1000 may include one or more processors 1010. The processor 1010 may support apparatus 1000 in implementing the methods described in the preceding method embodiments. The processor 1010 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0236] The apparatus 1000 may further include one or more memories 1020. The memories 1020 store a program that can be executed by the processor 1010, causing the processor 1010 to perform the methods described in the preceding method embodiments. The memories 1020 may be independent of the processor 1010 or integrated within the processor 1010.

[0237] The device 1000 may also include a transceiver 1030. The processor 1010 can communicate with other devices or chips via the transceiver 1030. For example, the processor 1010 can send and receive data with other devices or chips via the transceiver 1030.

[0238] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0239] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0240] This application also provides a computer program. This computer program can be applied to a terminal device or network device provided in this application, and the computer program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0241] It should be understood that the terminology used in this application is only for explaining specific embodiments of this application and is not intended to limit this application. The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0242] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0243] In the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0244] In the embodiments of this application, the term "correspondence" can indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0245] In this application embodiment, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0246] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0247] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0248] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0249] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0250] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0251] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0252] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs) or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0253] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: include: The terminal device receives configuration information sent by the network device, the configuration information being used to configure performance-related data for the terminal device's reported measurement event prediction function; The performance-related data are related to one or more of the following performance metrics: measured and predicted performance metrics, intermediate result performance metrics, and system-level performance metrics.

2. The method of claim 1, wherein, The measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

3. The method of claim 2, wherein, The inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is also used to configure that the at least one predicted measurement result is not used for the switching judgment.

4. The method according to claim 2 or 3, characterized in that, The measurement prediction function performs one or more of the following functions: Prediction function of interpolation-based measurement results in the time domain; Predictive function for measurement results between frequencies.

5. The method according to any one of claims 2 to 4, characterized in that, The method further includes: In response to the expiration of the first timer, the terminal device sends the measured predictive performance index; The first timer is used to indicate the monitoring duration of the measurement event prediction function.

6. The method according to any one of claims 2 to 5, characterized in that, The measured predictive performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; Beam-level measurement results; Community-level measurement results; Filtered measurement results; Unfiltered measurement results; Error of at least one predicted measurement result within the prediction window.

7. The method according to any one of claims 1 to 6, characterized in that, The intermediate result performance metrics include one or more of the following: The measurement event prediction function F β Fraction; The accuracy of the measured event prediction function; The recall rate of the measured event prediction function; First intermediate parameter.

8. The method of claim 7, wherein, The first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

9. The method of claim 8, wherein, The at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event related to the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

10. The method according to any one of claims 7 to 9, characterized in that, The performance-related data is used to indicate the relationship between the intermediate result performance index and the first threshold, which is determined based on the configuration information of the network device.

11. The method according to any one of claims 1 to 10, characterized in that, The system-level performance metrics include one or more of the following: The handover failure rate of the terminal device; The number of times the terminal device switches per unit time; The ping-pong switching rate of the terminal device; The short dwell time of the terminal device; The number of switching failures per unit time for the terminal device.

12. The method of claim 11, wherein, The performance-related data is used to indicate the relationship between the system-level performance metric and the second threshold, which is determined based on the configuration information of the network device.

13. The method according to claim 10 or 12, characterized in that, The performance-related data is indicated by 1 bit.

14. The method according to any one of claims 1 to 13, characterized in that, The configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

15. The method of claim 14, wherein, The triggering conditions include one or more of the following: The maximum number of switching operations is reached within the runtime of the measurement event prediction function; The first timer configured on the network device expires; The performance indicator does not meet the corresponding preset threshold; The network device instructs the terminal device to report the performance-related data; The terminal device reaches the reporting interval period configured by the network device.

16. The method of claim 15, wherein, The preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

17. The method of any one of claims 1 to 16, wherein, The configuration information is also used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

18. The method of any one of claims 1 to 17, wherein, The measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

19. The method of any one of claims 1 to 18, wherein, The performance-related data is used to train or update the model with the measurement event prediction function.

20. A method of communication, comprising: include: The network device sends configuration information to the terminal device, the configuration information being used to configure the performance-related data of the terminal device's measurement event prediction function; The performance-related data are related to one or more of the following performance metrics: measured and predicted performance metrics, intermediate result performance metrics, and system-level performance metrics.

21. The method of claim 20, wherein, The measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

22. The method of claim 21, wherein, The inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is also used to configure that the at least one predicted measurement result is not used for the switching judgment.

23. The method of claim 21 or 22, wherein, The measurement prediction function performs one or more of the following functions: Prediction function of interpolation-based measurement results in the time domain; Predictive function for measurement results between frequencies.

24. The method of any one of claims 21-23, wherein, The method further includes: The network device receives the measurement and prediction performance indicators sent by the terminal device; The transmission time of the measurement prediction performance index is determined based on a first timer, which is used to indicate the monitoring duration of the measurement event prediction function.

25. The method of any one of claims 21-24, wherein, The measured predictive performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; Beam-level measurement results; Community-level measurement results; Filtered measurement results; Unfiltered measurement results; Error of at least one predicted measurement result within the prediction window.

26. The method of any one of claims 20-25, wherein, The intermediate result performance metrics include one or more of the following: The F of the measurement event prediction function β Fraction; The accuracy of the measured event prediction function; The recall rate of the measured event prediction function; First intermediate parameter.

27. The method of claim 26, wherein, The first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

28. The method of claim 27, wherein, The at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event related to the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

29. The method of any one of claims 26-28, wherein, The performance-related data is used to indicate the relationship between the intermediate result performance index and the first threshold, which is determined based on the configuration information of the network device.

30. The method of any one of claims 20-29, wherein, The system-level performance metrics include one or more of the following: The handover failure rate of the terminal device; The number of times the terminal device switches per unit time; The ping-pong switching rate of the terminal device; The short dwell time of the terminal device; The number of switching failures per unit time for the terminal device.

31. The method of claim 30, wherein, The performance-related data is used to indicate the relationship between the system-level performance metric and the second threshold, which is determined based on the configuration information of the network device.

32. The method of claim 29 or 31, wherein, The performance-related data is indicated by 1 bit.

33. The method of any one of claims 20-32, wherein, The configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

34. The method of claim 33, wherein, The triggering conditions include one or more of the following: The maximum number of switching operations is reached within the runtime of the measurement event prediction function; The first timer configured on the network device expires; The performance indicator does not meet the corresponding preset threshold; The network device instructs the terminal device to report the performance-related data; The terminal device reaches the reporting interval period configured by the network device.

35. The method of claim 34, wherein, The preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

36. The method of any one of claims 20-35, wherein, The configuration information is also used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

37. The method of any one of claims 20-36, wherein, The measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

38. The method of any one of claims 20-37, wherein, The performance-related data is used to train or update the model with the measurement event prediction function.

39. A terminal device, comprising: The terminal device includes: A receiving unit is configured to receive configuration information sent by a network device, wherein the configuration information is used to configure performance-related data of the terminal device's reported measurement event prediction function; The performance-related data are related to one or more of the following performance metrics: measured and predicted performance metrics, intermediate result performance metrics, and system-level performance metrics.

40. The terminal device of claim 39, wherein, The measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

41. The terminal device of claim 40, wherein, The inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is also used to configure that the at least one predicted measurement result is not used for the switching judgment.

42. The terminal device of claim 40 or 41, wherein, The measurement prediction function performs one or more of the following functions: Prediction function of interpolation-based measurement results in the time domain; Predictive function for measurement results between frequencies.

43. The terminal device of any one of claims 40 to 42, wherein, The terminal device also includes: A sending unit is configured to send the measured and predicted performance metrics in response to the expiration of a first timer. The first timer is used to indicate the monitoring duration of the measurement event prediction function.

44. The terminal device of any one of claims 40 to 43, wherein, The measured predictive performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; Beam-level measurement results; Community-level measurement results; Filtered measurement results; Unfiltered measurement results; Error of at least one predicted measurement result within the prediction window.

45. The terminal device of any one of claims 39 to 44, wherein, The intermediate result performance metrics include one or more of the following: The F of the measurement event prediction function β Fraction; The accuracy of the measured event prediction function; The recall rate of the measured event prediction function; First intermediate parameter.

46. The terminal device of claim 45, wherein, The first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

47. The terminal device of claim 46, wherein, The at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event related to the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

48. The terminal device of any one of claims 45 to 47, wherein, The performance-related data is used to indicate the relationship between the intermediate result performance index and the first threshold, which is determined based on the configuration information of the network device.

49. The terminal device of any one of claims 39 to 48, wherein, The system-level performance metrics include one or more of the following: The handover failure rate of the terminal device; The number of times the terminal device switches per unit time; The ping-pong switching rate of the terminal device; The short dwell time of the terminal device; The number of switching failures per unit time for the terminal device.

50. The terminal device of claim 49, wherein, The performance-related data is used to indicate the relationship between the system-level performance metric and the second threshold, which is determined based on the configuration information of the network device.

51. The terminal device of claim 48 or 50, wherein, The performance-related data is indicated by 1 bit.

52. The terminal device of any one of claims 39 to 51, wherein, The configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

53. The terminal device of claim 52, wherein, The triggering conditions include one or more of the following: The maximum number of switching operations is reached within the runtime of the measurement event prediction function; The first timer configured on the network device expires; The performance indicator does not meet the corresponding preset threshold; The network device instructs the terminal device to report the performance-related data; The terminal device reaches the reporting interval period configured by the network device.

54. The terminal device of claim 53, wherein, The preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

55. The terminal device of any one of claims 39 to 54, wherein, The configuration information is also used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

56. The terminal device of any one of claims 39 to 55, wherein, The measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

57. The terminal device of any one of claims 39 to 56, wherein, The performance-related data is used to train or update the model with the measurement event prediction function.

58. A network device, comprising: The network device includes: A sending unit is used to send configuration information to a terminal device, wherein the configuration information is used to configure performance-related data of the terminal device's measurement event prediction function; The performance-related data are related to one or more of the following performance metrics: measured and predicted performance metrics, intermediate result performance metrics, and system-level performance metrics.

59. The network device of claim 58, wherein, The measurement prediction performance index is used to indicate the performance of the measurement prediction function of the terminal device. The performance of the measurement prediction function is determined based on at least one measured result within the prediction window. The at least one measured result is also used for switching judgment.

60. The network device of claim 59, wherein, The inference result of the measurement prediction function includes at least one predicted measurement result within the prediction window, and the configuration information is also used to configure that the at least one predicted measurement result is not used for the switching judgment.

61. The network device of claim 59 or 60, wherein, The measurement prediction function performs one or more of the following functions: Prediction function of interpolation-based measurement results in the time domain; Predictive function for measurement results between frequencies.

62. The network device according to any one of claims 59 to 61, characterized in that, The network device also includes: A receiving unit is configured to receive the measurement prediction performance index sent by the terminal device; The transmission time of the measurement prediction performance index is determined based on a first timer, which is used to indicate the monitoring duration of the measurement event prediction function.

63. The network device according to any one of claims 59 to 62, characterized in that, The measured predictive performance metrics include one or more of the following: Layer 1 measurement results; Layer 3 measurement results; Beam-level measurement results; Community-level measurement results; Filtered measurement results; Unfiltered measurement results; Error of at least one predicted measurement result within the prediction window.

64. The network device according to any one of claims 58 to 63, characterized in that, The intermediate result performance metrics include one or more of the following: The F of the measurement event prediction function β Fraction; The accuracy of the measured event prediction function; The recall rate of the measured event prediction function; First intermediate parameter.

65. The network device according to claim 64, characterized in that, The first intermediate parameter is determined based on at least one predicted measurement event and / or at least one actual measurement event of the terminal device.

66. The network device according to claim 65, characterized in that, The at least one predicted measurement event includes a first predicted measurement event, and the at least one measured measurement event includes a first measured measurement event related to the first predicted measurement event. The first intermediate parameter is used to indicate the interval between the occurrence time of the first predicted measurement event and the occurrence time of the first measured measurement event.

67. The network device according to any one of claims 64 to 66, characterized in that, The performance-related data is used to indicate the relationship between the intermediate result performance index and the first threshold, which is determined based on the configuration information of the network device.

68. The network device according to any one of claims 58 to 67, characterized in that, The system-level performance metrics include one or more of the following: The handover failure rate of the terminal device; The number of times the terminal device switches per unit time; The ping-pong switching rate of the terminal device; The short dwell time of the terminal device; The number of switching failures per unit time for the terminal device.

69. The network device according to claim 68, characterized in that, The performance-related data is used to indicate the relationship between the system-level performance metric and the second threshold, which is determined based on the configuration information of the network device.

70. The network device according to claim 67 or 69, characterized in that, The performance-related data is indicated by 1 bit.

71. The network device according to any one of claims 58 to 70, characterized in that, The configuration information is also used to configure the triggering conditions for the terminal device to report the performance-related data.

72. The network device according to claim 71, characterized in that, The triggering conditions include one or more of the following: The maximum number of switching operations is reached within the runtime of the measurement event prediction function; The first timer configured on the network device expires; The performance indicator does not meet the corresponding preset threshold; The network device instructs the terminal device to report the performance-related data; The terminal device reaches the reporting interval period configured by the network device.

73. The network device according to claim 72, characterized in that, The preset threshold is determined by predefined parameters and / or based on the configuration information of the network device.

74. The network device according to any one of claims 58 to 73, characterized in that, The configuration information is also used to configure the terminal device to collect statistical information, which is used to determine one or more performance indicators and / or performance-related data.

75. The network device according to any one of claims 58 to 74, characterized in that, The measurement event prediction function is used to perform direct and / or indirect prediction of measurement events.

76. The network device according to any one of claims 58 to 75, characterized in that, The performance-related data is used to train or update the model with the measurement event prediction function.

77. A terminal device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or send signals so that the terminal device performs the method as described in any one of claims 1 to 19.

78. A network device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals so that the network device performs the method as described in any one of claims 20 to 38.

79. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1 to 38.

80. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1 to 38.

81. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1 to 38.

82. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1 to 38.

Images