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 receiving first information sent by a network device, wherein the first information is used for determining one or more sets of inference configurations, the inference configurations are used for model inference of a model of the terminal device, and the model is used for predicting a measurement event. In the present application, a network device sends first information to a terminal device for the terminal device to determine one or more sets of inference configurations, so that the terminal device can use, on the basis of the one or more sets of inference configurations, a prediction model of a measurement event to execute model inference, thereby implementing effective prediction of the measurement event.

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] After performing radio resource management (RRM) measurements, terminal devices can report the measurement results to network devices in the form of a measurement report. This allows network devices to make relevant decisions based on the measurement report, such as cell handover decisions and beam switching decisions. Measurement events are crucial for triggering measurement reports and subsequent operations. Therefore, predicting the occurrence of measurement events becomes a problem that needs 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 first information sent by a network device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of a model of the terminal device, and the model being used for prediction of measurement events.

[0005] In a second aspect, a communication method is provided, comprising: a network device sending first information to a terminal device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of a model of the terminal device, and the model being used for prediction of measurement events.

[0006] Thirdly, a terminal device is provided, including a transceiver unit, configured to: receive first information sent by a network device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

[0007] Fourthly, a network device is provided, including a transceiver unit, configured to: send first information to a terminal device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of a model of the terminal device, and the model being used for prediction of measurement events.

[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] In a sixth aspect, a network 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 transmit signals so that the network device performs the method as described in the second aspect.

[0010] A seventh aspect provides an apparatus including a processor for calling a program from a memory to cause the apparatus to perform the method as described in any one of the first or second aspects.

[0011] Eighthly, a chip is provided, including a processor for calling a program from memory, causing a device having the chip mounted to perform the method as described in the first or second aspect.

[0012] A ninth aspect provides a computer-readable storage medium having a program stored thereon that causes a computer to perform the method as described in the first or second aspect.

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

[0014] Eleventhly, a computer program is provided that causes a computer to perform the method as described in the first or second aspect.

[0015] In this embodiment of the application, the network device sends first information to the terminal device to determine one or more inference configurations, so that the terminal device can perform model inference based on the one or more inference configurations and the prediction model of the measurement event, thereby achieving effective prediction of the measurement event. Attached Figure Description

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

[0017] Figure 2 is a schematic diagram of the inference process of the AI / ML model that can be applied to the embodiments of this application.

[0018] Figure 3 is a schematic diagram of a time-domain Case A prediction scenario that can be applied to the embodiments of this application.

[0019] Figure 4 is a schematic diagram of a time-domain Case B prediction scenario that can be applied to the embodiments of this application.

[0020] Figure 5 is a schematic diagram of the spatial prediction scenarios that can be applied to the embodiments of this application.

[0021] Figure 6 is a schematic diagram of a frequency domain prediction scenario that can be applied to the embodiments of this application.

[0022] Figure 7 is a flowchart illustrating the communication method according to an embodiment of this application.

[0023] Figure 8 is a schematic diagram of the structure of the terminal device according to an embodiment of this application.

[0024] Figure 9 is a schematic diagram of the structure of a network device according to an embodiment of this application.

[0025] Figure 10 is a schematic diagram of a communication apparatus according to an embodiment of this application. Detailed Implementation

[0026] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0027] Communication system

[0028] Figure 1 is an example diagram of the system architecture of a communication system 100 to which embodiments of this application can be applied. The communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 can provide network coverage for a specific geographical area and can communicate with the terminal device 120 located within that coverage area. The terminal device 120 can access a network, such as a wireless network, through the network device 110. Optionally, the communication system 100 may also include other network entities such as a network controller and a mobility management entity; this embodiment of the application does not limit this.

[0029] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: fifth generation (5G) systems, new radio (NR), long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as sixth generation mobile communication systems, satellite communication systems, etc.

[0030] In this application embodiment, the terminal device 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 device, user agent, or user apparatus. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, vehicle-mounted device, etc. Terminal devices can also be mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes. Optionally, terminal devices can act as base stations. For example, a terminal device can act as a dispatching entity, providing sidelink signals between terminal devices in vehicle-to-everything (V2X) or device-to-device (D2D) systems. For instance, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices communicate without relaying communication signals through base stations.

[0031] In this embodiment, the network device can be a device used to communicate with a terminal device. The network device can be an access network device or a wireless access network device. For example, the network device can be a base station. The term "base station" can broadly encompass various names as follows, or can be replaced by names such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, 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, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entity, or a combination 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, or an entity that performs base station functions in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network-side device in a 6G network, or an entity 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. In some deployments, the network equipment may include a CU or a DU; or, the network equipment may include both a CU and a DU. Optionally, the base station may include an AAU.

[0032] Furthermore, 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.

[0033] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0034] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform such as a cloud platform.

[0035] RRM measurement

[0036] In 3GPP cellular communication systems, terminal equipment typically needs to determine the strength or quality of the radio signals in the current serving cell and neighboring cells through measurements. For example, the terminal equipment can measure the cell's signal strength, i.e., reference signal receiving power (RSRP); it can also measure the cell's signal quality, i.e., reference signal receiving quality (RSRQ); and it can measure the cell's signal-to-interference noise ratio (SINR). These types of measurements are called RRM measurements. After performing RRM measurements, the terminal equipment can report the relevant information to the network equipment in the form of a measurement report, so that the network equipment can make relevant decisions based on the reported information, such as cell handover decisions and beam switching decisions.

[0037] The measurement report can be carried, for example, within a radio resource control (RRC) message. This report may include specific measurement events and / or measurement results. The cells reported by the terminal device in the measurement report may include the current serving cell and / or neighboring cells. For example, the terminal device may report the signal strength and signal quality of the current serving cell; or, the terminal device may report the signal strength and signal quality of both the current serving cell and neighboring cells. The measurement objects included in the measurement report can be various, such as frequencies from the same frequency, different frequencies, or different communication systems.

[0038] RRM measurement model

[0039] The RRM measurement model describes how a terminal device performs measurement sampling according to beams at layer 1 (L1), and how it makes judgments on measurement events based on network configuration parameters. This involves beam-level or cell-level definitions, and the relationship between layer 1 and layer 3 (L3) measurement values. The following description uses RSRP measurement as an example, with reference to Figure 2, to illustrate the reference points involved in this process.

[0040] Reference point A: This is the physical layer measurement sampling step performed by the terminal device. The terminal device can perform physical layer measurement sampling according to beam granularity, obtaining beam-level layer 1 measurement results (e.g., beam level L1-RSRP). As an example, Figure 2 shows sampling for beams 1 to K. Here, the sampling can also be referred to as sampling or measurement.

[0041] Reference point A1: The terminal equipment performs Layer 1 filtering on the beam measurement results of the K beams. Typically, the protocol specifies the length of the measurement cycle under a specific RRC configuration. Within each measurement cycle, the terminal equipment must perform at least one sampling, and the beam measurement results after Layer 1 filtering must meet the performance requirements specified in specification 38.133. The number of samplings by the terminal equipment within each measurement cycle is predetermined; for example, the terminal equipment can perform 4 to 5 oversamplings within a test cycle.

[0042] Reference point B: The beam measurement results of K beams within a cell obtained at reference point A1 are merged to form a layer 1 cell-level measurement result (e.g., cell-level L1-RSRP). The cell-level layer 1 measurement result can typically represent the signal quality of the cell.

[0043] Reference point C: The cell-level layer 1 measurement results are sequentially filtered by layer 3 to obtain the cell-level layer 3 measurement results (e.g., cell-level L3-RSRP).

[0044] Reference point D: The measurement results of the serving cell and / or neighboring cells are used to determine whether a specific measurement event has occurred, based on predetermined decision conditions. For example, it may determine whether the measurement result of a neighboring cell is higher than the measurement result of the current serving cell by an offset value (i.e., an A3 event has occurred). These decision conditions can be configured by network devices, for example.

[0045] Reference point E: The beam-level layer 3 measurement result obtained by filtering the layer 3 beam measurement result (e.g., L3 beam-level RSRP).

[0046] Reference point F: Selected beam-level layer 3 quantity results for reporting (e.g., L3 beam-level RSRP).

[0047] Artificial intelligence (AI) mobility projects

[0048] The AI ​​mobility project defines three sub-use cases: RRM measurement, radio link failure (RLF) / handover failure (HOF), and measurement event prediction.

[0049] RRM Measurement Prediction: The model's input and output can be the A / A1 / B / C / E / F point information from the aforementioned measurement model. The input and output measurement results can come from the same cell, different cells at different frequency layers, or a group of cells. Prediction can be performed in the time domain, frequency domain, or between different frequencies (i.e., frequency domain).

[0050] Measurement event prediction: One approach is to infer whether a specific measurement event will occur at a future point in time based on the results of RRM measurement predictions and the configuration parameters related to that measurement event in the network configuration. This approach is called indirect prediction. Another approach is direct prediction, which is based on the input measurement results (at least including the measurement results of the serving cell and / or neighboring cells directly related to the event), and then uses a model to infer whether a measurement event will occur.

[0051] HOF / RLF events: Similar to measurement event prediction, direct or indirect prediction methods can be used, but the input measurement results must include at least the measurement results of the serving cell and / or neighboring cells directly related to the event.

[0052] High-priority scenarios for mobile AI / ML

[0053] At the RAN2#126 meeting, the following four high-priority research scenarios were proposed for RRM measurement prediction.

[0054] Scenario 1: Time-domain prediction

[0055] Time-domain prediction includes two cases: time-domain Case A and time-domain Case B.

[0056] Time-domain Case A predicts future measurement results based on historical measurement results, allowing for advance knowledge of what will happen and preparation. As an example, as shown in Figure 3, black represents the actual measurement values, and white represents the predicted values ​​obtained by using the model to predict the measurement results. Using the measurement values ​​at sampling times T1, T2, T3, and T4, the measurement results at sampling times T5 and T6 are predicted.

[0057] Time-domain Case B utilizes partial measurement results for interpolation prediction. This interpolation prediction fills in the missing values ​​between adjacent measurements, thus reducing the number of measurements required. As an example, as shown in Figure 4, black represents the actual measured values, and white represents the predicted values ​​obtained after using the model to predict the measurement results. Previously, measurements needed to be taken at sampling times T1, T2, T3, T4, T5, and T6. Now, measurements can be taken only at sampling times T1, T3, and T5, and the model can predict the measurement results at sampling times T2, T4, and T6. This effectively reduces the measurement overhead and energy consumption of the terminal equipment without compromising mobility performance.

[0058] Scenario 2: Airspace Prediction

[0059] Spatial prediction, for example, refers to using measurements of a subset of beams to predict the measurement results of the remaining unmeasured beams. For instance, as shown in Figure 4, black represents the measured beams, white represents the unmeasured beams, the horizontal axis represents the azimuth angle, and the vertical axis represents the zenith angle. Where 32 beams originally required measurement, now only 16 beams need to be measured, and the model can be used to predict the measurement results of the remaining 16 beams. Figure 4 uses a measurement reduction ratio (MRR) of 50% as an example, where MRR = 1 - 16 / 32 = 50%.

[0060] Scenario 3: Frequency Domain Prediction

[0061] Frequency domain prediction refers to using the measurement value of a certain frequency point to predict the measurement results of other frequencies and obtain the corresponding predicted values. For example, as shown in Figure 6, the black part represents the frequency point where cell A is located, and the white part represents the frequency point where cell B is located. The measurement value of the frequency point where cell A is located is used to predict the measurement result of the frequency point where cell B is located.

[0062] Switching events and switching-related parameters, filtering-related parameters

[0063] A handover event refers to the conditions that trigger a handover by a network device based on signal strength, quality, or other factors. Common handover events may include the following:

[0064] Event A1: The signal quality of the serving cell is higher than a certain threshold, which is used to shut down ongoing inter-frequency measurements;

[0065] A2 event: The signal quality of the serving cell falls below a certain threshold, which is used to initiate inter-frequency measurement or switch to another frequency band;

[0066] A3 event: The signal quality of a neighboring cell is higher than that of the serving cell plus an offset value (hysteresis), used for handover between the same frequency or different frequencies;

[0067] A4 event: The signal quality of a neighboring cell exceeds a certain threshold, used for inter-frequency handover;

[0068] A5 event: The signal quality of the serving cell is lower than threshold 1, while the signal quality of the neighboring cells is higher than threshold 2, which is used for load balancing handover.

[0069] B1 event: The signal quality of a neighboring cell in a different system is higher than a certain threshold, which is used to switch from the current system to another system (e.g., from a 4G system to a 5G system).

[0070] B2 event: The signal quality of the serving cell is lower than threshold 1, while the signal quality of a neighboring cell in the other system is higher than threshold 2, which is used for inter-system handover.

[0071] Handover-related parameters include, for example, the threshold value mentioned in the above event, handover hysteresis, handover offset, cell individual bias (CIO), time-triggered timer (TTT), handover preparation time, etc.

[0072] Filtering-related parameters include, for example, the filter coefficient, the number of SSBs used to calculate the average value (nrofSS-BlocksToAverage), and the absolute threshold for SSB merging (absThreshSS-BlocksConsolidation).

[0073] Among the related technologies, the primary consideration is the lifecycle management (LCM) process in AI / ML for air projects, which discloses some relatively general inference configuration processes and content. The AI / ML for mobility related content mainly focuses on beam management, but there are overall differences from the specific needs of AI mobility projects, especially regarding measurement event prediction, for which there are currently no detailed solutions.

[0074] Therefore, in this embodiment of the application, the network device sends first information to the terminal device to determine one or more inference configurations, so that the terminal device can perform model inference based on the one or more inference configurations and the prediction model of the measurement event, thereby achieving effective prediction of the measurement event.

[0075] The embodiments of this application will be described in detail below with reference to Figure 7.

[0076] Figure 7 is a flowchart illustrating the communication method provided in an embodiment of this application. The method 700 shown in Figure 7 can be executed by a terminal device and a network device. The terminal device can be, for example, the terminal device 120 shown in Figure 1, and the network device can be, for example, the network device 110 shown in Figure 1.

[0077] Referring to Figure 7, in step 710, the network device sends the first information to the terminal device.

[0078] In step 720, the terminal device receives the first information sent by the network device.

[0079] The first piece of information is used to determine (e.g., indicate) one or more inference configurations for model inference of the terminal device's model. The terminal device's model is, for example, a model for predicting measurement events.

[0080] Optionally, the first information may include the content of one or more inference configurations; or, the first information may include indexes of one or more inference configurations. The index of each inference configuration is used to identify or indicate the content of that inference configuration. The content of the inference configurations is described below.

[0081] In some implementations, the inference configuration includes one or more of the following: model-related configuration; model input-related configuration; and model output-related configuration. That is, the network device instructs the terminal device on specific configurations for model inference using first information, such as model-related configuration, model input-related configuration, and model output-related configuration. This assists the terminal device in making inference decisions, thereby effectively completing the model inference process. The embodiments of this application are applicable to AI / ML-based event prediction, including direct prediction and / or indirect prediction. By introducing AI / ML technology, the overhead for event prediction can be reduced or switching performance can be improved.

[0082] Model-related configuration

[0083] Model-related configurations may include, for example, information on the model's applicability conditions and / or the model's activation conditions. The applicability conditions information may include, for example, one or more of the following: applicable prediction scenarios, applicable prediction types, and applicable movement speed information.

[0084] Optionally, the prediction scenarios applicable to the model may include one or more of the aforementioned time-domain prediction, frequency-domain prediction, and spatial-domain prediction. Time-domain prediction includes time-domain Case A (i.e., predicting RRM measurement results at future times) and time-domain Case B (i.e., predicting RRM measurement results at unmeasured time locations). The predicted RRM measurement results are used for the prediction of measurement events; for example, the measurement event is determined based on the RRM measurement results obtained from the time-domain prediction and / or the actual RRM measurement results, as well as parameters related to the measurement event.

[0085] The prediction scenarios to which this model is applicable may include a single measurement scenario, such as time-domain prediction, frequency-domain prediction, or spatial-domain prediction; or, the prediction scenarios to which this model is applicable may also include a combination of multiple measurement scenarios, such as a combination of time-domain Case A and frequency-domain prediction, a combination of time-domain Case A and spatial-domain prediction, a combination of time-domain Case B and frequency-domain prediction, a combination of time-domain Case B and spatial-domain prediction, a combination of frequency-domain prediction and spatial-domain prediction, a combination of time-domain Case A, frequency-domain prediction, and spatial-domain prediction, or a combination of time-domain Case B, frequency-domain prediction, and spatial-domain prediction.

[0086] If the prediction scenario in the applicable conditions information included in the model-related configuration includes time-domain prediction, and this time-domain prediction is Time-domain Case B, i.e., predicting RRM measurement results at unmeasured time locations, then optionally, the model-related configuration may also include the measurement reduction rate in the temporal domain (MRRT) of the time-domain prediction. The MRRT of the time-domain prediction indicates the amount of measurement reduction achieved by using time-domain prediction. For example, for time-domain prediction, if measurements were originally required at 20 time locations, and the model using time-domain prediction predicts the measurement results at 10 of these time locations, then only 10 time locations need to be actually measured. Thus, time-domain prediction can save 50% of the measurement, i.e., the measurement reduction rate MRRT = 50%.

[0087] If the prediction scenario in the applicable conditions included in the model-related configuration includes frequency domain prediction, then optionally, the model-related configuration may also include one or more of the following: input frequency information; output frequency information; and frequency prediction direction. Input frequency information may include, for example, frequency points, frequency bands, or combinations of multiple frequency bands; output frequency information may include, for example, frequency points, frequency bands, or combinations of multiple frequency bands. The frequency prediction direction refers, for example, whether the prediction is performed from high frequency to low frequency, from low frequency to high frequency, or based on other frequency sequences.

[0088] If the prediction scenario in the applicable conditions included in the model-related configuration includes spatial domain prediction, then optionally, the model-related configuration may also include the measurement reduction rate in the spatial domain (MRRS). The MRRS for spatial domain prediction indicates the amount of measurement reduction achieved by using spatial domain prediction. For example, if spatial domain prediction originally required measurements of 32 beams, and if the model uses spatial domain prediction to predict the measurements of 8 of these beams, then only 24 beams need to be actually measured. Thus, spatial domain prediction can save 25% of the measurement amount, i.e., the measurement reduction rate MRRS = 25%.

[0089] The prediction types applicable to the model include, for example, direct prediction and / or indirect prediction. For direct prediction, the model-related configuration may further include, for example, one or more of the following: the type of measurement event, parameters associated with the measurement event, and filter coefficients associated with the measurement event. The parameters associated with the measurement event may include, for example, information about the TTT timer associated with the measurement event and / or threshold information associated with the measurement event.

[0090] The types of events to be measured include, for example, the aforementioned A1 event, A2 event, A3 event, A4 event, A5 event, B1 event, B2 event, etc.

[0091] The TTT timer is associated with the triggering of measurement events. Specifically, the terminal device measures a reference signal within the cell and starts the TTT timer associated with that reference signal when the measurement result meets the entry condition of the measurement event. If the strength of the reference signal in the cell no longer meets the entry condition during the TTT timer's operation, the TTT timer stops; if the TTT timer eventually times out, the measurement event is triggered.

[0092] The threshold information associated with a measurement event refers to the threshold used to determine the measurement event. For example, taking event A3 as an example, this threshold can refer to the offset value (A3-offset) of event A3, or the threshold offset. If the signal quality of the neighboring cell is greater than or equal to the signal quality of the serving cell plus A3-offset, it indicates that event A3 is triggered.

[0093] The applicable speed information for the model includes, for example, the applicable speed or speed range, where the speed refers to, for example, the speed of the terminal device. The speed of the terminal device may affect the performance of the model. As an example, if the applicable speed range for the model is between 30 and 60 km / h, then the model can be used to predict measurement events when the terminal device's speed is between 30 and 60 km / h. If the terminal device's speed is outside this range, for example, exceeding 60 km / h, then the model is no longer applicable.

[0094] Optionally, the model activation condition information is used to indicate the conditions that must be met to activate the model, i.e., to indicate when the model should be activated for predicting measurement events. After receiving the first information, if the first information includes the model activation condition information, the terminal device will activate the model if the activation conditions are met; otherwise, the terminal device may activate the model immediately or at a pre-agreed or pre-configured time.

[0095] The model's activation conditions may include, for example, S-measure conditions, handover event entry conditions, or timer information. S-measure conditions typically initiate neighbor cell measurements; for instance, measurements of neighbor cells are initiated when the serving cell's signal quality falls below a threshold. The measurement event entry conditions are usually handover event trigger conditions, used to determine whether to handover to the target cell. The timer can be used to determine when to activate the model; for example, the terminal device starts the timer indicated in the first information upon receiving it, and activates the model when the timer expires. This timer can also be pre-defined or pre-configured.

[0096] Enter relevant configuration

[0097] Input-related configurations may include one or more of the following: the length of the observation window (OW) for the model's input data; the time interval between adjacent measurements within the OW; the number of input data for the model; RRM measurement configuration information; and the type of input data for the model.

[0098] Here, the OW (Workout) of the model's input data refers, for example, to the time window in which the measurement data that can be used as model input data is located. The time interval between adjacent measurement results within the OW refers, for example, to the interval between the time positions corresponding to two consecutive measurement results within the OW. For instance, if the time interval between adjacent measurement results within the OW is 40ms, then the measurement data at each 40ms time position within the OW is used as the model's input data.

[0099] The amount of input data for a model refers to, for example, the maximum amount of measurement data that the model can input at any given time.

[0100] RRM measurement configuration information, also known simply as measurement configuration, includes parameters related to RRM measurement, such as one or more of the following: measurement object, reporting configuration, measurement interval, and thresholds related to measurement events. For details on the specific content of the RRM measurement configuration, please refer to the RRM measurement configuration documentation in related technologies.

[0101] The types of input data for the model can include one or more of the following: Layer 1 measurements; Layer 3 measurements; beam-level measurements; cell-level measurements; filtered data; and unfiltered data. For example, the type of input data for the model can be data or a combination of data at reference points such as reference point A, reference point A1, reference point B, or reference point C, as shown in Figure 2. As an example, as shown in Figure 2, the type of input data for the model can be Layer 1 cell-level filtered data, Layer 1 cell-level unfiltered data, Layer 1 beam-level filtered data, Layer 1 beam-level unfiltered data, Layer 3 cell-level filtered data, Layer 3 cell-level unfiltered data, Layer 3 beam-level filtered data, or Layer 3 beam-level unfiltered data, or a combination of one or more of the above data types.

[0102] If the prediction scenario applicable to the model is time-domain prediction, and this time-domain prediction is time-domain Case B, i.e., predicting RRM measurement results at unmeasured time locations, then optionally, the model's input-related configuration may also include a measurement reduction pattern. The terminal device can selectively skip certain time locations without performing RRM measurements or predictions at these time locations based on the skipping pattern, instead performing measurements and / or predictions only at a subset of these time locations, and using the resulting measurement results as the model's input.

[0103] If the model is applicable to a spatial prediction scenario, then optionally, the model's input-related configuration may also include a measurement reduction pattern. The terminal device may selectively skip certain beams without measuring or predicting them, based on the skipping pattern, and only measure and / or predict a subset of the beams, using the resulting measurements as the model's input.

[0104] If the model is applicable to frequency domain prediction, then optionally, the model's input-related configuration may also include input frequency information and / or frequency prediction direction. Input frequency information may include, for example, frequency points, frequency bands, or combinations of multiple frequency bands; output frequency information may include, for example, frequency points, frequency bands, or combinations of multiple frequency bands. Frequency prediction direction refers, for example, whether prediction is performed from high frequency to low frequency, from low frequency to high frequency, or based on other frequency sequences.

[0105] Output related configurations

[0106] Output-related configurations may include one or more of the following: the length of the prediction window (PW) of the model's output data; the time interval between adjacent predictions within the PW; the amount of model output data; and cell information associated with measurement events.

[0107] Here, the PW (Predicted Time Window) of the model's input data refers, for example, the time window in which the predicted data that can be used as the model's output data is located. The time interval between adjacent measurement results within the PW refers, for example, the interval between the time positions corresponding to two consecutive predicted data within the PW. For instance, the time interval between adjacent predicted data within the PW is 80ms, meaning that the model's output data includes the predicted data at each time position within the PW every 80ms.

[0108] The amount of output data of a model refers to, for example, the maximum amount of predicted data that the model can output each time.

[0109] Cell information associated with the measurement event includes, for example, cell identification information, which indicates whether the model's output is for the serving cell or one or more neighboring cells.

[0110] In this embodiment, the first information is carried in an RRC message or a MAC CE. The conditions for sending the first information include, for example, that the network device has not previously sent the first information to the terminal device.

[0111] Network devices can send inference configurations for model inference to terminal devices multiple times. If a network device has already sent a portion of the inference configuration information to a terminal device via a first message, the subsequent first messages may not include the content of the already sent inference configurations, but may include the content of the inference configurations that have not been transmitted before.

[0112] Optionally, before step 710, method 700 may further include the terminal device reporting capability information to the network device; and / or the terminal device reporting model-supported functional information to the network device.

[0113] The capability information may include, for example, the ability to predict measurement events, meaning that the terminal device has a model for predicting measurement events. The network device will only send the inference configuration related to the model used for predicting measurement events to the terminal device after it knows that the terminal device has this capability.

[0114] The functional information supported by the model can be used to determine the inference configuration for model inference. For example, if the terminal device supports time-domain prediction, frequency-domain prediction, or spatial-domain prediction, the network device, knowing that the terminal device supports such a function, provides the terminal device with an inference configuration that matches the time-domain, frequency-domain, or spatial-domain prediction. As another example, if the terminal device supports direct or indirect prediction, the network device, knowing that the terminal device supports such a function, provides the terminal device with an inference configuration that matches the direct or indirect prediction. As yet another example, if the terminal device supports prediction of same-frequency measurement time, different-frequency measurement events, or inter-RAT measurement events, the network device, knowing that the terminal device supports such a function, provides the terminal device with an inference configuration that matches the prediction of same-frequency measurement time, different-frequency measurement events, or inter-RAT measurement events. In other words, the inference configuration in the first information sent by the network device may include, for example, the inference configuration of the prediction capabilities and / or supported functions explicitly indicated by the terminal device.

[0115] When the capability information and / or supported function information of the terminal device changes or is updated, the network device can resend the first information to the terminal device to provide a new inference configuration that matches the updated capabilities and / or functions.

[0116] When a network device sends multiple inference configurations to a terminal device, it can send multiple inference configurations to the terminal device through a single first message; or, the network device can send multiple first messages to the terminal device to carry multiple inference configurations respectively, that is, each inference configuration is sent to the terminal device through a separate first message.

[0117] The embodiments of this application are described in more detail below with specific examples. It should be noted that the following examples are merely to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of this application to the specific numerical values ​​or scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or variations based on the given examples, and such modifications or variations also fall within the scope of the embodiments of this application.

[0118] Example 1: Time Domain Case A

[0119] The terminal device supports time-domain prediction, and the prediction type is time-domain Case A. The network device sends first information to the terminal device, which includes the inference configuration for time-domain Case A configured for the terminal device. This inference configuration includes model-related configuration, model input-related configuration, and model output-related configuration.

[0120] The model-related configuration includes applicable condition information and / or model activation condition information. Applicable condition information includes: applicable only to time-domain Case A, i.e., predicting RRM measurement results at future times and determining measurement events; applicable to directly predicting A3 events; applicable speed range of 0-30 km / h. Model activation condition information includes: the entering condition is met.

[0121] The input-related configurations include: the OW of the model's input data is 200ms; the time interval between adjacent measurement results within the OW is 50ms; the number of model input data is 4; the measurement configuration is to use a specific measurement configuration P, based on the RRM prediction configuration setting; the type of model input data is the reference point A1, i.e., the filtered data of layer 1 beam level (L1, beam-level, filtered).

[0122] The output-related configurations include: the prediction window PW for the model's output data is 200ms; the time interval between adjacent prediction results within PW is 50ms; the number of model output data is 4; and the cell information associated with the measurement event includes the serving cell and neighboring cells X.

[0123] By directly predicting RRM measurement results over a future period and identifying predicted events, we can more accurately anticipate network resource usage and trends, enabling more timely decision-making, such as adjusting resource allocation and optimizing network configuration in advance. Activating the model only when conditions are met reduces unnecessary inference work, thus saving energy.

[0124] Example 2: Time Domain Case B

[0125] The terminal device supports time-domain prediction and the prediction type is time-domain Case B. The network device sends first information to the terminal device, which includes the inference configuration for time-domain Case B configured for the terminal device. This inference configuration includes model-related configuration, model input-related configuration, and model output-related configuration.

[0126] The model-related configuration includes applicable condition information and / or model startup condition information. Applicable condition information includes: applicable only to time-domain Case B, i.e., predicting RRM measurement results at unmeasured time locations and determining measurement events; applicable to indirect prediction; applicable speed range is 0-60 km / h. The model startup condition information is default, indicating that the terminal device continues to run the model after receiving the first information; time-domain measurement reduction MRRT = 50%.

[0127] The input configuration includes: the OW of the model input data is 600ms; the time interval between adjacent measurement results within the OW is 200ms; the number of model input data is 2; the type of model input data is reference point C, i.e., layer 3 cell-level filtered data; and the measurement reduction mode is to use a specific skipping pattern R.

[0128] Output-related configurations include: the prediction window (PW) for the model's output data is 200ms; the time interval between adjacent prediction results within the PW is 200ms; the number of model output data is 1; cell information associated with the measurement event is not configured, indicating that it applies to the serving cell and all neighboring cells.

[0129] By predicting RRM measurement results at unmeasured time locations and identifying predicted events, the measurement overhead of terminal devices can be significantly reduced without affecting the handover performance of terminal devices.

[0130] Example 3: Frequency Domain

[0131] The terminal device supports frequency domain prediction. The network device sends first information to the terminal device, which includes inference configuration for frequency domain prediction configured for the terminal device. This inference configuration includes model-related configuration, model input-related configuration, and model output-related configuration.

[0132] The model-related configuration includes applicable condition information and / or model activation condition information. Applicable condition information includes: applicable only to the frequency domain; applicable to direct prediction; applicable speed range is 0-90 km / h. Model activation condition information includes: the entering condition is met; the applicable input frequency is in the frequency range [f9, f10], the applicable output frequency is in the frequency range [f11, f12], and the prediction direction is from low frequency to high frequency.

[0133] The input configuration includes: the open time (OW) of the model input data is 120ms; the time interval between adjacent measurement results within the OW is 40ms; the number of model input data is 3; and the type of model input data is reference point C, i.e., layer 3 cell-level filtered data (L3, cell-level, filtered).

[0134] The output-related configurations include: the prediction window PW of the model's output data is 40ms; the time interval between adjacent prediction results within PW is 40ms; the number of model output data is 1; and the cell information associated with the measurement event includes the serving cell and neighboring cells Z.

[0135] By configuring the appropriate input frequency, output frequency, and prediction direction for the frequency domain prediction of terminal devices, more accurate management and optimization of spectrum measurements can be achieved, avoiding the measurement gap caused by frequent switching between different frequencies. At the same time, it will not significantly affect the switching performance of the terminal devices.

[0136] Example 4: Airspace

[0137] The terminal device supports spatial domain prediction. The network device sends first information to the terminal device, which includes the inference configuration for spatial domain prediction configured for the terminal device. This inference configuration includes model-related configuration, model input-related configuration, and model output-related configuration.

[0138] The model-related configuration includes applicable condition information and / or model activation condition information. Applicable condition information includes: applicable only to airspace; applicable to indirect prediction; applicable speed range greater than 60 km / h. Model activation condition information includes: configured timer information; airspace measurement reduction (MRRS) = 50%.

[0139] The input configuration includes: the OW of the model's input data is 80ms; the time interval between adjacent measurement results within the OW is 40ms; the number of model input data is 2*16, where 16 represents the number of beams in each time slot; the type of model input data is reference point A, i.e., unfiltered data at the layer 1 beam level (L1, beam-level, non-filtered); and the measurement reduction mode is to use a specific skipping pattern U.

[0140] The output-related configurations include: the prediction window (PW) of the model's output data is 80ms; the time interval between adjacent prediction results within the PW is 40ms; the number of model output data is 2*16, where 16 represents the number of beams in each time slot; and the cell information associated with the measurement event includes the serving cell and all neighboring cells.

[0141] Model-based spatial prediction can reduce the overhead of spatial measurement without significantly sacrificing the mobile handover performance of terminal devices. It can dynamically select beams and allocate resources based on beam prediction results, thereby enhancing the adaptability and flexibility of the network.

[0142] The method embodiments of this application have been described in detail above with reference to Figures 1 to 5. The apparatus embodiments of this application will be described in detail below with reference to Figures 6 to 8. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be referred to the preceding method embodiments.

[0143] Figure 8 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. The terminal device 800 shown in Figure 8 may include a transceiver unit 810. The transceiver unit 810 is used to receive first information sent by a network device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

[0144] In some implementations, the first information includes the content of the set or more inference configurations; or, the first information includes the index of the set or more inference configurations.

[0145] In some implementations, the inference configuration includes one or more of the following: model-related configuration of the model; input-related configuration of the model; and output-related configuration of the model.

[0146] In some implementations, the model-related configuration includes: applicable condition information of the model; and / or, startup condition information of the model.

[0147] In some implementations, the applicable condition information includes one or more of the following: applicable prediction scenario; applicable prediction type; applicable movement speed information.

[0148] In some implementations, the prediction scenario includes one or more of the following: time-domain prediction; spatial-domain prediction; frequency-domain prediction.

[0149] In some implementations, the time-domain prediction includes: predicting RRM measurement results at future times; or, predicting RRM measurement results at unmeasured time locations; wherein the RRM measurement results are used for the prediction of measurement events.

[0150] In some implementations, the time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes MRRT.

[0151] In some implementations, the prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: input frequency information; output frequency information; frequency prediction direction.

[0152] In some implementations, the input frequency information and / or the output frequency information includes: a frequency point; or a frequency band; or a combination of multiple frequency bands.

[0153] In some implementations, the prediction scenario includes spatial prediction, and the model-related configuration also includes MRRS.

[0154] In some implementations, the prediction type includes: direct prediction; and / or, indirect prediction.

[0155] In some implementations, the prediction type includes direct prediction, and the model-related configuration further includes one or more of the following: the type of the measurement event; information about the TTT timer associated with the measurement event; threshold information associated with the measurement event; and filter coefficients associated with the measurement event.

[0156] In some implementations, the input-related configuration includes one or more of the following: the length of the OW of the model's input data; the time interval between adjacent measurement results within the OW; the number of input data of the model; RRM measurement configuration information; and the type of input data of the model.

[0157] In some implementations, the input data of the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; beam-level measurement; cell-level measurement; filtered data; unfiltered data.

[0158] In some implementations, the prediction scenario for which the model is applicable is time-domain prediction, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations, and the input-related configuration further includes a measurement reduction mode; and / or, the prediction scenario for which the model is applicable is spatial-domain prediction, and the input-related configuration further includes a measurement reduction mode; and / or, the prediction scenario for which the model is applicable is frequency-domain prediction, and the input-related configuration further includes input frequency information and / or frequency prediction direction.

[0159] In some implementations, the output-related configuration includes one or more of the following: the length of the PW of the model's output data; the time interval between adjacent prediction results within the PW; the number of output data of the model; and cell information associated with the measurement event.

[0160] In some implementations, the first information is carried in an RRC message; or, the first information is carried in a MAC CE.

[0161] In some implementations, the transceiver order 810 yuan is also used to: report capability information to the network device, the capability information including measurement event prediction capability.

[0162] In some implementations, the transceiver unit 810 is further configured to: report the functional information supported by the model to the network device, the functional information being used to determine the inference configuration.

[0163] It is understood that the transceiver unit 810 may be, for example, a transceiver 1030. Additionally, the terminal device 800 may optionally include a processor 1010 and a memory 1020, as shown in Figure 10.

[0164] Figure 9 is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device 900 shown in Figure 9 may include a transceiver unit 910. The transceiver unit 910 is used to send first information to a terminal device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

[0165] In some implementations, the first information includes the content of the set or more inference configurations; or, the first information includes the index of the set or more inference configurations.

[0166] In some implementations, the inference configuration includes one or more of the following: model-related configuration of the model; input-related configuration of the model; and output-related configuration of the model.

[0167] In some implementations, the model-related configuration includes: applicable condition information of the model; and / or, startup condition information of the model.

[0168] In some implementations, the applicable condition information includes one or more of the following: applicable prediction scenario; applicable prediction type; applicable movement speed information.

[0169] In some implementations, the prediction scenario includes one or more of the following: time-domain prediction; spatial-domain prediction; frequency-domain prediction.

[0170] In some implementations, the time-domain prediction includes: predicting RRM measurement results at future times; or, predicting RRM measurement results at unmeasured time locations; wherein the RRM measurement results are used for the prediction of measurement events.

[0171] In some implementations, the time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes MRRS.

[0172] In some implementations, the prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: input frequency information; output frequency information; frequency prediction direction.

[0173] In some implementations, the input frequency information and / or the output frequency information includes: a frequency point; or a frequency band; or a combination of multiple frequency bands.

[0174] In some implementations, the prediction scenario includes spatial prediction, and the model-related configuration also includes MRRS.

[0175] In some implementations, the prediction type includes: direct prediction; and / or, indirect prediction.

[0176] In some implementations, the prediction type includes direct prediction, and the model-related configuration further includes one or more of the following: the type of the measurement event; information about the TTT timer associated with the measurement event; threshold information associated with the measurement event; and filter coefficients associated with the measurement event.

[0177] In some implementations, the input-related configuration includes one or more of the following: the length of the OW of the model's input data; the time interval between adjacent measurement results within the OW; the number of input data of the model; RRM measurement configuration information; and the type of input data of the model.

[0178] In some implementations, the input data of the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; beam-level measurement; cell-level measurement; filtered data; unfiltered data.

[0179] In some implementations, the prediction scenario for which the model is applicable is time-domain prediction, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations, and the input-related configuration further includes a measurement reduction mode; and / or, the prediction scenario for which the model is applicable is spatial-domain prediction, and the input-related configuration further includes a measurement reduction mode; and / or, the prediction scenario for which the model is applicable is frequency-domain prediction, and the input-related configuration further includes input frequency information and / or frequency prediction direction.

[0180] In some implementations, the output-related configuration includes one or more of the following: the length of the PW of the model's output data; the time interval between adjacent prediction results within the PW; the number of output data of the model; and cell information associated with the measurement event.

[0181] In some implementations, the first information is carried in an RRC message; or, the first information is carried in a MAC CE.

[0182] In some implementations, the transceiver unit 710 is further configured to: receive capability information reported by the terminal device, the capability information including measurement event prediction capability.

[0183] In some implementations, the transceiver unit 710 is further configured to: receive the function information supported by the model reported by the terminal device, the function information being used to determine the inference configuration.

[0184] It is understood that the transceiver unit 910 may be, for example, a transceiver 1030. Additionally, the network device 900 may optionally include a processor 1010 and a memory 1020, as detailed in Figure 10.

[0185] Figure 10 is a schematic structural diagram of a communication apparatus according to an embodiment of this application. The dashed lines in Figure 10 indicate that the unit or module is optional. The apparatus 1000 can be used to implement the methods described in the above method embodiments. The apparatus 1000 may be, for example, a chip, a terminal device, or a network device.

[0186] Apparatus 1000 may include one or more processors 1010. Processor 1010 may support apparatus 1000 in implementing the methods described in the foregoing method embodiments. Processor 1010 may be a general-purpose processor or a special-purpose processor. For example, processor 1010 may be a central processing unit (CPU). Alternatively, processor 1010 may also 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. General-purpose processors may be microprocessors or any conventional processor, etc.

[0187] The apparatus 1000 may further include one or more memories 1020. The memories 1020 store programs that can be executed by the processor 1010, causing the processor 1010 to perform the methods described in the above method embodiments. The memories 1020 may be independent of the processor 1010, or they may be integrated into the processor 1010.

[0188] The device 1000 may also include a transceiver 1030. The processor 1010 can communicate with other devices or chips through the transceiver 1030. For example, the processor 1010 can send and receive data with other devices or chips through the transceiver 1030.

[0189] This application also provides a communication system. The communication system includes the terminal device and network device described above. In some implementations, the system further includes other devices that interact with the terminal device and network device.

[0190] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal device or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal device or network device in various embodiments of this application.

[0191] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal device or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0192] This application also provides a computer program. This computer program can be applied to the terminal device or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal device or network device in the various embodiments of this application.

[0193] It should be understood that the terms "system" and "network" in the embodiments of this application can be used interchangeably. Furthermore, 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," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] In the 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 displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0202] 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.

[0203] 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.

[0204] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as 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 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)).

[0205] 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 in that, include: The terminal device receives first information sent by the network device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

2. The method according to claim 1, characterized in that, The first information includes the content of the one or more inference configurations; or, The first information includes the index of the one or more inference configurations.

3. The method according to claim 1 or 2, characterized in that, The inference configuration includes one or more of the following: The model-related configuration of the model; The input-related configuration of the model; The output-related configuration of the model.

4. The method according to claim 3, characterized in that, The model-related configurations include: Information on the applicable conditions of the model; and / or, The startup conditions information of the model.

5. The method according to claim 4, characterized in that, The applicable conditions information includes one or more of the following: Applicable prediction scenarios; Applicable forecast types; Applicable movement speed information.

6. The method according to claim 5, characterized in that, The predicted scenarios include one or more of the following: Time-domain prediction; Airspace prediction; Frequency domain prediction.

7. The method according to claim 6, characterized in that, The time-domain prediction includes: Predicting future Radio Resource Management (RRM) measurements; or, Predict RRM measurements at unmeasured time locations; The RRM measurement results are used to predict measurement events.

8. The method according to claim 7, characterized in that, The time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes the measurement reduction amount MRRT predicted by the time-domain prediction.

9. The method according to any one of claims 6 to 8, characterized in that, The prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: Input frequency information; Output frequency information; Frequency prediction direction.

10. The method according to claim 9, characterized in that, The input frequency information and / or the output frequency information include: Frequency point; or, Frequency band; or, A combination of multiple frequency bands.

11. The method according to any one of claims 6 to 10, characterized in that, The prediction scenario includes spatial prediction, and the model-related configuration also includes the Measurement Reduction (MRRS) for the spatial prediction.

12. The method according to any one of claims 5 to 11, characterized in that, The prediction types include: Direct prediction; and / or, Indirect prediction.

13. The method according to claim 12, characterized in that, The prediction type includes direct prediction, and the model-related configurations also include one or more of the following: The type of the measurement event; Information about the trigger time (TTT) timer associated with the measurement event; The threshold information associated with the measurement event; The filter coefficients associated with the measured events.

14. The method according to any one of claims 1 to 13, characterized in that, The input-related configuration includes one or more of the following: The length of the observation window OW for the input data of the model; The time interval between adjacent measurement results within the OW; The number of input data for the model; RRM measurement configuration information; The type of input data for the model.

15. The method according to claim 14, characterized in that, The input data for the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; Beam-level measurement; Community-level measurement; Filtered data; Unfiltered data.

16. The method according to claim 14 or 15, characterized in that, The model is applicable to time-domain prediction scenarios, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations. The input-related configuration also includes a measurement reduction mode; and / or, The model is applicable to spatial domain prediction scenarios, and the input-related configurations also include a measurement reduction mode; and / or, The model is applicable to frequency domain prediction scenarios, and the input-related configurations also include input frequency information and / or frequency prediction direction.

17. The method according to any one of claims 1 to 16, characterized in that, The output-related configuration includes one or more of the following: The length of the prediction window PW for the output data of the model; The time interval between adjacent prediction results within the PW; The number of output data of the model; Cell information associated with measurement events.

18. The method according to any one of claims 1 to 17, characterized in that, The first information is carried in a Radio Resource Control (RRC) message; or, The first information is carried in the Media Access Control (MAC) control element CE.

19. The method according to any one of claims 1 to 18, characterized in that, The method further includes: The terminal device reports capability information to the network device, including measurement event prediction capability.

20. The method according to any one of claims 1 to 19, characterized in that, The method further includes: The terminal device reports the functional information supported by the model to the network device, and the functional information is used to determine the inference configuration.

21. A communication method, characterized in that, include: The network device sends first information to the terminal device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

22. The method according to claim 21, characterized in that, The first information includes the content of the one or more inference configurations; or, The first information includes the index of the one or more inference configurations.

23. The method according to claim 21 or 22, characterized in that, The inference configuration includes one or more of the following: The model-related configuration of the model; The input-related configuration of the model; The output-related configuration of the model.

24. The method according to claim 23, characterized in that, The model-related configurations include: Information on the applicable conditions of the model; and / or, The startup conditions information of the model.

25. The method according to claim 24, characterized in that, The applicable conditions information includes one or more of the following: Applicable prediction scenarios; Applicable forecast types; Applicable movement speed information.

26. The method according to claim 25, characterized in that, The predicted scenarios include one or more of the following: Time-domain prediction; Airspace prediction; Frequency domain prediction.

27. The method according to claim 26, characterized in that, The time-domain prediction includes: Predicting future Radio Resource Management (RRM) measurements; or, Predict RRM measurements at unmeasured time locations; The RRM measurement results are used to predict measurement events.

28. The method according to claim 27, characterized in that, The time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes the measurement reduction amount MRRT predicted by the time-domain prediction.

29. The method according to any one of claims 26 to 28, characterized in that, The prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: Input frequency information; Output frequency information; Frequency prediction direction.

30. The method according to claim 29, characterized in that, The input frequency information and / or the output frequency information include: Frequency point; or, Frequency band; or, A combination of multiple frequency bands.

31. The method according to any one of claims 26 to 30, characterized in that, The prediction scenario includes spatial prediction, and the model-related configuration also includes the Measurement Reduction (MRRS) for the spatial prediction.

32. The method according to any one of claims 25 to 31, characterized in that, The prediction types include: Direct prediction; and / or, Indirect prediction.

33. The method according to claim 32, characterized in that, The prediction type includes direct prediction, and the model-related configurations also include one or more of the following: The type of the measurement event; Information about the trigger time (TTT) timer associated with the measurement event; The threshold information associated with the measurement event; The filter coefficients associated with the measured events.

34. The method according to any one of claims 21 to 33, characterized in that, The input-related configuration includes one or more of the following: The length of the observation window OW for the input data of the model; The time interval between adjacent measurement results within the OW; The number of input data for the model; RRM measurement configuration information; The type of input data for the model.

35. The method according to claim 34, characterized in that, The input data for the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; Beam-level measurement; Community-level measurement; Filtered data; Unfiltered data.

36. The method according to claim 34 or 35, characterized in that, The model is applicable to time-domain prediction scenarios, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations. The input-related configuration also includes a measurement reduction mode; and / or, The model is applicable to spatial domain prediction scenarios, and the input-related configurations also include a measurement reduction mode; and / or, The model is applicable to frequency domain prediction scenarios, and the input-related configurations also include input frequency information and / or frequency prediction direction.

37. The method according to any one of claims 21 to 36, characterized in that, The output-related configuration includes one or more of the following: The length of the prediction window PW for the output data of the model; The time interval between adjacent prediction results within the PW; The number of output data of the model; Cell information associated with measurement events.

38. The method according to any one of claims 21 to 37, characterized in that, The first information is carried in a Radio Resource Control (RRC) message; or, The first information is carried in the Media Access Control (MAC) control element CE.

39. The method according to any one of claims 21 to 38, characterized in that, The method further includes: The network device receives capability information reported by the terminal device, the capability information including measurement event prediction capability.

40. The method according to any one of claims 21 to 39, characterized in that, The method further includes: The network device receives the functional information supported by the model reported by the terminal device, and the functional information is used to determine the inference configuration.

41. A terminal device, characterized in that, include: A transceiver unit is used to receive first information sent by a network device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

42. The terminal device according to claim 41, characterized in that, The first information includes the content of the one or more inference configurations; or, The first information includes the index of the one or more inference configurations.

43. The terminal device according to claim 41 or 42, characterized in that, The inference configuration includes one or more of the following: The model-related configuration of the model; The input-related configuration of the model; The output-related configuration of the model.

44. The terminal device according to claim 43, characterized in that, The model-related configurations include: Information on the applicable conditions of the model; and / or, The startup conditions information of the model.

45. The terminal device according to claim 44, characterized in that, The applicable conditions information includes one or more of the following: Applicable prediction scenarios; Applicable forecast types; Applicable movement speed information.

46. ​​The terminal device according to claim 45, characterized in that, The predicted scenarios include one or more of the following: Time-domain prediction; Airspace prediction; Frequency domain prediction.

47. The terminal device according to claim 46, characterized in that, The time-domain prediction includes: Predicting future Radio Resource Management (RRM) measurements; or, Predict RRM measurements at unmeasured time locations; The RRM measurement results are used to predict measurement events.

48. The terminal device according to claim 47, characterized in that, The time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes the measurement reduction amount MRRT predicted by the time-domain prediction.

49. The terminal device according to any one of claims 46 to 48, characterized in that, The prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: Input frequency information; Output frequency information; Frequency prediction direction.

50. The terminal device according to claim 49, characterized in that, The input frequency information and / or the output frequency information include: Frequency point; or, Frequency band; or, A combination of multiple frequency bands.

51. The terminal device according to any one of claims 46 to 50, characterized in that, The prediction scenario includes spatial prediction, and the model-related configuration also includes the Measurement Reduction (MRRS) for the spatial prediction.

52. The terminal device according to any one of claims 45 to 51, characterized in that, The prediction types include: Direct prediction; and / or, Indirect prediction.

53. The terminal device according to claim 52, characterized in that, The prediction type includes direct prediction, and the model-related configurations also include one or more of the following: The type of the measurement event; Information about the trigger time (TTT) timer associated with the measurement event; The threshold information associated with the measurement event; The filter coefficients associated with the measured events.

54. The terminal device according to any one of claims 41 to 53, characterized in that, The input-related configuration includes one or more of the following: The length of the observation window OW for the input data of the model; The time interval between adjacent measurement results within the OW; The number of input data for the model; RRM measurement configuration information; The type of input data for the model.

55. The terminal device according to claim 54, characterized in that, The input data for the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; Beam-level measurement; Community-level measurement; Filtered data; Unfiltered data.

56. The terminal device according to claim 54 or 55, characterized in that, The model is applicable to time-domain prediction scenarios, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations. The input-related configuration also includes a measurement reduction mode; and / or, The model is applicable to spatial domain prediction scenarios, and the input-related configurations also include a measurement reduction mode; and / or, The model is applicable to frequency domain prediction scenarios, and the input-related configurations also include input frequency information and / or frequency prediction direction.

57. The terminal device according to any one of claims 41 to 56, characterized in that, The output-related configuration includes one or more of the following: The length of the prediction window PW for the output data of the model; The time interval between adjacent prediction results within the PW; The number of output data of the model; Cell information associated with measurement events.

58. The terminal device according to any one of claims 41 to 57, characterized in that, The first information is carried in a Radio Resource Control (RRC) message; or, The first information is carried in the Media Access Control (MAC) control element CE.

59. The terminal device according to any one of claims 41 to 58, characterized in that, The transceiver unit is also used for: The network device reports capability information, including the ability to predict measurement events.

60. The terminal device according to any one of claims 41 to 59, characterized in that, The transceiver unit is also used for: The network device reports the functional information supported by the model, which is used to determine the inference configuration.

61. A network device, characterized in that, include: A transceiver unit is used to send first information to a terminal device, wherein the first information is used to determine one or more inference configurations, the inference configurations being used for model inference of the terminal device's model, and the model being used for prediction of measurement events.

62. The network device according to claim 61, characterized in that, The first information includes the content of the one or more inference configurations; or, The first information includes the index of the one or more inference configurations.

63. The network device according to claim 61 or 62, characterized in that, The inference configuration includes one or more of the following: The model-related configuration of the model; The input-related configuration of the model; The output-related configuration of the model.

64. The network device according to claim 63, characterized in that, The model-related configurations include: Information on the applicable conditions of the model; and / or, The startup conditions information of the model.

65. The network device according to claim 64, characterized in that, The applicable conditions information includes one or more of the following: Applicable prediction scenarios; Applicable forecast types; Applicable movement speed information.

66. The network device according to claim 65, characterized in that, The predicted scenarios include one or more of the following: Time-domain prediction; Airspace prediction; Frequency domain prediction.

67. The network device according to claim 66, characterized in that, The time-domain prediction includes: Predicting future Radio Resource Management (RRM) measurements; or, Predict RRM measurements at unmeasured time locations; The RRM measurement results are used to predict measurement events.

68. The network device according to claim 67, characterized in that, The time-domain prediction includes predicting RRM measurements at unmeasured time locations, and the model-related configuration also includes the measurement reduction MRRS predicted by the time-domain prediction.

69. The network device according to any one of claims 66 to 68, characterized in that, The prediction scenario includes frequency domain prediction, and the model-related configurations also include one or more of the following: Input frequency information; Output frequency information; Frequency prediction direction.

70. The network device according to claim 69, characterized in that, The input frequency information and / or the output frequency information include: Frequency point; or, Frequency band; or, A combination of multiple frequency bands.

71. The network device according to any one of claims 66 to 70, characterized in that, The prediction scenario includes spatial prediction, and the model-related configuration also includes the Measurement Reduction (MRRS) for the spatial prediction.

72. The network device according to any one of claims 65 to 71, characterized in that, The prediction types include: Direct prediction; and / or, Indirect prediction.

73. The network device according to claim 72, characterized in that, The prediction type includes direct prediction, and the model-related configurations also include one or more of the following: The type of the measurement event; Information about the trigger time (TTT) timer associated with the measurement event; The threshold information associated with the measurement event; The filter coefficients associated with the measured events.

74. The network device according to any one of claims 61 to 73, characterized in that, The input-related configuration includes one or more of the following: The length of the observation window OW for the input data of the model; The time interval between adjacent measurement results within the OW; The number of input data for the model; RRM measurement configuration information; The type of input data for the model.

75. The network device according to claim 74, characterized in that, The input data for the model includes one or more of the following types: Layer 1 measurement; Layer 3 measurement; Beam-level measurement; Community-level measurement; Filtered data; Unfiltered data.

76. The network device according to claim 74 or 75, characterized in that, The model is applicable to time-domain prediction scenarios, and the time-domain prediction includes predicting RRM measurement results at unmeasured time locations. The input-related configuration also includes a measurement reduction mode; and / or, The model is applicable to spatial domain prediction scenarios, and the input-related configurations also include a measurement reduction mode; and / or, The model is applicable to frequency domain prediction scenarios, and the input-related configurations also include input frequency information and / or frequency prediction direction.

77. The network device according to any one of claims 61 to 76, characterized in that, The output-related configuration includes one or more of the following: The length of the prediction window PW for the output data of the model; The time interval between adjacent prediction results within the PW; The number of output data of the model; Cell information associated with measurement events.

78. The network device according to any one of claims 61 to 77, characterized in that, The first information is carried in a Radio Resource Control (RRC) message; or, The first information is carried in the Media Access Control (MAC) control element CE.

79. The network device according to any one of claims 61 to 78, characterized in that, The transceiver unit is also used for: The terminal device receives capability information, including measurement event prediction capability.

80. The network device according to any one of claims 61 to 79, characterized in that, The transceiver unit is also used for: The terminal device receives information on the functions supported by the model, and this information is used to determine the inference configuration.

81. 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 according to any one of claims 1 to 20.

82. 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 according to any one of claims 21 to 40.

83. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the apparatus to perform the method according to any one of claims 1 to 40.

84. 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 according to any one of claims 1 to 40.

85. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method according to any one of claims 1 to 40.

86. A computer program product, characterized in that, Includes a program that causes a computer to perform the method according to any one of claims 1 to 40.

87. A computer program, characterized in that, The computer program causes the computer to perform the method according to any one of claims 1 to 40.

Images