Wireless communication method, terminal device, and network device

Abstract

Provided are a wireless communication method, a terminal device, and a network device. The method comprises: a terminal device receives first configuration information sent by a network device, wherein the first configuration information is used for configuring the terminal device to monitor one or more performance indexes of a first model, the performance indexes are used for indicating the performance of predicted valuesobtained on the basis of the first model, and the first model is deployed on the terminal device. On the basis of the first configuration information, the terminal device can explicitly perform performance monitoring on the first model, so that the terminal device or the network device can determine whether the prediction performance of the first model is good, and adjust or replace the model on the basis of performance indexes, thereby improving the accuracy of prediction.

Description

Wireless communication method, terminal device, and network device TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and more particularly, to a wireless communication method, a terminal device, and a network device. BACKGROUND

[0002] With the development of technology, a prediction function is introduced into a communication system. For example, channel prediction and / or traffic prediction can be implemented based on a model. Whether the prediction performance of the model meets the requirements can be achieved through performance monitoring. Based on the performance monitoring, the model can be replaced or the parameters of the model can be adjusted, so that the prediction is more accurate. SUMMARY

[0003] The present application provides a wireless communication method, a terminal device, and a network device. The various aspects involved in the present application are introduced below.

[0004] In a first aspect, a wireless communication method is provided. The method includes: receiving, by a terminal device, first configuration information transmitted by a network device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of a first model, the performance indicators being used to indicate the performance of a prediction value based on the first model, the first model being deployed in the terminal device.

[0005] In a second aspect, a wireless communication method is provided. The method includes: transmitting, by a network device, first configuration information to a terminal device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of a first model, the performance indicators being used to indicate the performance of a prediction value based on the first model, the first model being deployed in the terminal device.

[0006] In a third aspect, a terminal device is provided. The terminal device includes: a receiving unit configured to receive first configuration information transmitted by a network device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of a first model, the performance indicators being used to indicate the performance of a prediction value based on the first model, the first model being deployed in the terminal device.

[0007] In a fourth aspect, a network device is provided. The network device includes: a transmitting unit configured to transmit first configuration information to a terminal device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of a first model, the performance indicators being used to indicate the performance of a prediction value based on the first model, the first model being deployed in the terminal device.

[0008] In a fifth aspect, a terminal device is provided, which includes a processor and a memory. The memory is configured to store one or more computer programs. The processor is configured to invoke the computer programs in the memory to cause the terminal device to perform some or all of the steps in the method of the first aspect.

[0009] In a sixth aspect, a network device is provided, which includes a processor, a memory and a transceiver. The memory is configured to store one or more computer programs. The processor is configured to invoke the computer programs in the memory to cause the network device to perform some or all of the steps in the method of the second aspect.

[0010] In a seventh aspect, a communication system is provided, which includes the terminal device and / or the network device described above. In another possible design, the system can further include other devices interacting with the terminal device or the network device in the solutions provided by the embodiments of the present application.

[0011] In an eighth aspect, a computer-readable storage medium is provided, which stores a computer program. The computer program causes a terminal device and / or a network device to perform some or all of the steps in the methods of the above aspects.

[0012] In a ninth aspect, a computer program product is provided, which includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a terminal device and / or a network device to perform some or all of the steps in the methods of the above aspects. In some implementations, the computer program product can be a software installation package.

[0013] In a tenth aspect, a chip is provided, which includes a memory and a processor. The processor can invoke and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0014] Based on the first configuration information, the terminal device can explicitly monitor the performance of the first model, so that the terminal device or the network device can determine whether the prediction performance of the first model is good, and adjust or replace the model according to the performance index, thereby improving the prediction accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0015] FIG. 1 is a schematic diagram of a wireless communication system to which embodiments of the present application are applied.

[0016] FIG. 2 is an example diagram of a measurement model.

[0017] FIG. 3 is an example diagram of an observation window and a prediction window.

[0018] FIG. 4 is a schematic flowchart of a wireless communication method according to an embodiment of the present application.

[0019] FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

[0020] FIG. 6 is a schematic structural diagram of a network device according to an embodiment of the present application.

[0021] FIG. 7 is a schematic structural diagram of an apparatus for communication according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the present application will be described below with reference to the drawings.

[0023] Communication system

[0024] FIG. 1 is a wireless communication system 100 to which embodiments of the present application are applied. The wireless communication system 100 can include communication devices. The communication devices can include a network device 110 and a terminal device 120. The network device 110 can be a device that communicates with the terminal device 120.

[0025] FIG. 1 exemplarily shows one network device and two terminals. Optionally, the wireless communication system 100 can include multiple network devices and each network device can include other numbers of terminal devices within its coverage, which is not limited in the embodiments of the present application.

[0026] Optionally, the wireless communication system 100 can further include a network controller, a mobile management entity, and other network entities, which are not limited in the embodiments of the present application.

[0027] It should be understood that the technical solutions in the embodiments of the present application can be applied to various communication systems, for example, a 5th generation (5G) system or new radio (NR), a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), and the like. The technical solutions provided in the present application can also be applied to future communication systems, such as a 6th generation mobile communication system, a satellite communication system, and the like.

[0028] The terminal device in the embodiments of the present application can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station (MS), a mobile terminal (MT), a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user apparatus. The terminal device in the embodiments of the present application can refer to a device providing voice and / or data connectivity for a user, and can be used to connect people, things and machines, such as handheld devices with wireless connection functions, vehicle-mounted devices, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer (Pad), a notebook computer, a palm computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity, which provides sidelink signals between UEs in vehicle-to-everything (V2X) or device to device (D2D), etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and the smart home device communicate with each other without relaying the communication signals through the base station.

[0029] The network device in the embodiments of the present application can be a device for communicating with a terminal device. The network device can also include an access network device. The access network device can provide communication coverage for a specific geographic area and can communicate with terminal devices 120 located within the coverage area. The access network device can also be referred to as a radio access network device or a base station, etc. The access network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) that accesses a terminal device to a wireless network. The access network device can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master eNB (MeNB), secondary eNB (SeNB), multi-standard 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. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station can also refer to a communication module, modem, or chip used in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs the function of a base station in D2D, V2X, machine-to-machine (M2M) communication, a network side device in a 6G network, a device that performs the function of a base station in a future communication system, etc. The base station can support networks of the same or different access technologies. The embodiments of the present application do not limit the specific technology and specific device form adopted by the access network device.

[0030] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, a helicopter or a drone can be configured to serve as a device that communicates with another base station.

[0031] The communication devices involved in the wireless communication system can include not only access network devices and terminal devices, but also core network elements. The core network elements can be implemented by devices, that is, the core network elements are core network devices. It can be understood that the core network devices can also be a kind of network devices.

[0032] The core network element in the embodiment of the present application can include a network element that processes and forwards signaling and data of a user. For example, the core network device can include core network access and mobility management function (core access and mobility management function, AMF), session management function (session management function, SMF), and user plane gateway, location management function (location management function, LMF) and other core network devices. Among them, the user plane gateway can be a server with functions of mobility management, routing, forwarding and other functions of user plane data, generally located on the network side, such as serving gateway (serving gateway, SGW) or packet data network gateway (packet data network gateway, PGW) or user plane function entity (user plane function, UPF) and the like. Of course, other network elements can also be included in the core network, which are not listed here.

[0033] In some deployments, the network device in the embodiment of the present application can refer to CU or DU, or the network device includes CU and DU. The gNB can also include AAU.

[0034] The network device and the terminal device can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; can also be deployed on the water surface; can also be deployed on the aircraft, balloon and satellite in the air. The scene where the network device and the terminal device are located in the embodiment of the present application is not limited.

[0035] It should be understood that all or part of the functions of the communication device in the present application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform).

[0036] Measurement model

[0037] In some communication protocols (e.g. 3GPP standard specification 38.331 (radio resource control (RRC) standard protocol)), the measurement result used for measurement event decision is the result after RRC layer (layer 3 (L3)) filtering. The preliminary measurement result inside the terminal device is the physical layer (layer 1 (L1)) measurement result, and is the result of measuring a single beam. Taking L1 reference signal received power (L1-RSRP) and L3-RSRP as examples, the relationship between the L1 measurement result and the L3 measurement result is described below in combination with several reference points in the measurement model shown in FIG. 2.

[0038] Reference point A is the link at which the terminal device performs physical layer measurement sampling, and is performed according to the granularity of a beam, and the obtained result is a beam level L1-RSRP.

[0039] At reference point A 1 , the terminal device performs L1 filtering on the measured beam measurement result. Generally, the length of the measurement period under the specific RRC configuration can be specified. The measurement period can specify that the terminal device at least performs sampling once, and the beam measurement result after L1 filtering meets the performance requirement. The specific sampling times of the terminal device at reference point A within a measurement period are specified. In the test example, 4-5 oversampling is generally used. After reference point A 1 , the filtered beam-level L1-RSRP can be obtained.

[0040] At reference point B, the beam measurement result of a certain cell obtained at A 1 is subjected to a merging operation to synthesize the L1 cell level measurement result, and a cell level L1-RSRP is obtained.

[0041] At reference point C, the L1 cell level measurement result of a certain cell is sequentially subjected to L3 filtering to obtain the L3 cell level measurement result, i.e. a cell level L3-RSRP.

[0042] Channel prediction

[0043] With the development of technology, a prediction function is introduced into a communication system. For example, the prediction function can be implemented based on a model. The model can include an artificial intelligence (AI) / machine learning (ML) model. In the related art (e.g., R18), a scheme of channel prediction is proposed. The following describes the related art regulation on channel prediction, taking R18 and R19 as examples.

[0044] The prediction process of L1-RSRP is considered in R18 channel prediction, and the accuracy of prediction can be evaluated by some indicators, that is, the AI model performance monitoring can monitor the following indicators.

[0045] 1) Average L1-RSRP difference of Top-1 predicted beam.

[0046] 2) Beam prediction accuracy (%). The parameter can include Top-1 (%), Top-K / 1 (%), and Top-1 / K (%).

[0047] Top-1 (%): Percentage of "Top-1 assisted beam is Top-1 predicted beam".

[0048] Top-K / 1 (%): Percentage of "Top-1 assisted beam is one of Top-K predicted beams".

[0049] Top-1 / K (%) (optional): Percentage of "Top-1 predicted beam is one of Top-K assisted beams".

[0050] 3) Beam prediction accuracy (%) with ldB margin for Top-1 beam.

[0051] The main research in R18 is the beam-related content. The so-called Top-1 predicted beam is the beam with the largest predicted RSRP, and the Top-1 auxiliary beam is the beam with the largest actual RSRP. The Top-k predicted beam is the largest K predicted beams. The beam prediction accuracy under the 1dB margin describes the proportion of the difference between the predicted Top-1 beam and the actual Top-1 beam. For example, 10 times of prediction, 8 times of prediction value and actual value difference less than 1dB, then the prediction accuracy is 80%. It should be noted that R18 is a high-level research index, that is, L3, only considering the beam level L1-RSRP.

[0052] In the R19 AI mobility project, L3-RSRP difference is used as a performance evaluation index, and the following three types of indexes can be considered.

[0053] Average L3 cell RSRP difference (dB): The average L3 RSRP difference between the predicted and actual L3 cell-level measurement results for each individual point within the PW, and then averaged across all the points in the PW.

[0054] Last predicted point L3 cell RSRP difference (dB): The average L3 RSRP difference between the predicted and ideal L3 cell-level measurement result for the last point in PW.

[0055] Multiple predicted point L3 cell RSRP differences (dB): Average L3 RSRP difference between predicted and ideal L3 cell-level measurement result for each individual point in PW. Multiple values are provided if there are multiple points within the PW

[0056] The input of the prediction model can be the L3-RSRP situation in an observation window (OW), and the output is the L3-RSRP situation in a prediction window (PW). The observation window is a period of time before the current time, and the prediction window is a period of time after the current time. The observation window and the prediction window are described below in conjunction with FIG. 3.

[0057] As shown in FIG. 3, the black boxes are the L3-RSRP values detected at consecutive time points within the OW, and the gray boxes are the L3-RSRP values detected at consecutive time points within the PW. In FIG. 3, both the OW and the PW are taken as an example of 600 ms. As can be seen from FIG. 3, the PW can have multiple time instance L3-RSRP values, that is, the model monitoring can monitor the difference between the predicted value and the actual value of all L3-RSRP within the PW. The closer the time instance in the PW is to the end of the PW, the greater the L3-RSRP difference, that is, the farther the prediction time is from the current time, the worse the prediction effect. Therefore, the index "last predicted point L3 cell RSRP difference" also has a certain monitoring value.

[0058] The present application can not only be applied to channel prediction, but also to traffic prediction.

[0059] Traffic prediction

[0060] Traffic prediction has broad application prospects in communication systems. For example, traffic prediction (or data arrival prediction) for terminal devices can enable network devices to configure more reasonable DRX parameters (such as ondurationTime) for terminal devices, thereby saving energy consumption of terminal devices. Furthermore, traffic prediction can help network devices configure reasonable configured grant resources, reducing the occupation of invalid resources and improving resource utilization. AI-related research in related technologies has provided possibilities for traffic prediction. However, current AI research mainly focuses on channel prediction, and has not yet covered traffic prediction. However, the inventors of this application have analyzed that many channel prediction-related monitoring methods can actually be applied to traffic prediction. This is because, in existing uplink traffic reporting mechanisms, signaling transmission is carried out through RRC signaling, which is similar to channel reporting, both being higher-layer RRC reporting, so many technologies can be used interchangeably.

[0061] Figure 4 is a schematic flowchart of a wireless communication method provided in an embodiment of this application. The method shown in Figure 4 can be executed by a terminal device and a network device. The method shown in Figure 4 may include step S410.

[0062] In step S410, the network device sends the first configuration information. The terminal device receives the first configuration information.

[0063] The first configuration information is related to one or more performance metrics of the first model.

[0064] The first model can be used for prediction. For example, the first model can produce predicted values ​​(or prediction results). Exemplarily, the input to the first model can be measured values, and the output can be predicted values.

[0065] In some implementations, the first model can be used to predict one or more of the following: traffic, channel quality, etc. When the first model is used to predict traffic, the predicted value can include the predicted traffic value, and the measured value can include the measured traffic value. When the first model is used to predict channel quality, the predicted value can include the predicted channel quality measurement value, and the measured value can include the measured channel quality measurement value.

[0066] When the first model is used to predict channel quality, the technical solution provided in this application can be applied to the time-domain case A, time-domain case B, spatial-domain, and frequency-domain scenarios discussed in the AI ​​mobility project. In particular, for the spatial and frequency domains, it can be assumed that there is only one predicted value in the prediction window, that is, K is 1.

[0067] In some embodiments, the first model may be an AI / ML-based model.

[0068] Performance metrics are used to indicate the performance of predictions obtained based on a primary model. In other words, performance metrics can directly or indirectly reflect the accuracy of the primary model's predictions. For example, performance metrics may include intermediate variables for performance monitoring (such as high-level intermediate variables). Based on these intermediate variables, the accuracy of the primary model's predictions can be determined.

[0069] In some embodiments, some performance metrics may be obtained by monitoring or calculating the predicted values ​​of the first model. For example, performance metrics may include one or more of the following: average L1-RSRP difference of the Top-1 predicted beam, Top-1 (%), Top-K / 1 (%), Top-1 / K (%), and beam prediction accuracy (%) with a 1dB margin for the Top-1 beam.

[0070] In some embodiments, some performance metrics may be obtained based on other performance metrics. For example, performance metrics may include whether a target has been met. The target meeting result may include whether a certain performance metric meets the requirements of a performance decision threshold.

[0071] The terminal device or network device can monitor one or more performance indicators of the first model. That is, the monitoring of one or more performance indicators of the first model can be performed on the terminal device and / or the network device. For example, the terminal device can monitor all performance indicators of the first model. Alternatively, the network device can monitor all performance indicators of the first model. Or, the network device can monitor some performance indicators of the first model, and the terminal device can monitor some performance indicators of the first model.

[0072] This invention application reveals that, depending on the deployment location of the first model (e.g., deployed on a terminal device and / or deployed on a network device), the location of performance monitoring of the first model may have different impacts on the technical solution or protocol. See Table 1 for details.

[0073] Table 1

[0074] The technical solution provided in this application mainly addresses the scenario where the first model is deployed on the terminal device side. Performance monitoring can occur on network devices and / or terminal devices. From the perspective of channel measurement and data arrival, the terminal device side naturally obtains more information than the network side, so performance monitoring occurring on the terminal device side is particularly important.

[0075] In some embodiments, the first configuration information is used to configure the terminal device to monitor one or more performance metrics of the first model. For example, based on the received first configuration information, the terminal device can determine to perform performance monitoring for the first model. For example, the terminal device can monitor one or more performance metrics configured in the first configuration information. Alternatively, the terminal device can report one or more performance metrics configured in the first configuration information to the network device. The network device can further monitor one or more performance metrics of the first model based on the performance metrics reported by the terminal device (e.g., determine whether the performance metrics meet a decision threshold).

[0076] Based on the first configuration information, the terminal device can clearly monitor the performance of the first model, thereby enabling the terminal device or network device to determine whether the prediction performance of the first model is good, and adjust or replace the model according to the performance indicators, thereby improving the accuracy of the prediction.

[0077] In some embodiments, the first configuration information may be included in a measurement configuration (measConfig) message as defined in the related art. That is, the first configuration information may be a part of the measurement configuration message. In other words, the measurement configuration message of the related art can be improved so that the measurement configuration message can indicate the first configuration information. The measurement configuration message can be used to describe the performance metrics of a specific measurement object that needs to be monitored. Because it is tied to the ongoing measurement process, monitoring of the first model will continue unless explicitly declared to have ended.

[0078] In some embodiments, the first configuration information can be independent of the measurement configuration message. That is, the first configuration information exists in a different message than the measurement configuration message. The first configuration information can be associated with the measurement configuration message through a measurement object identifier (measObjectId), etc., in which case the monitoring process can be implemented independently of the measurement process.

[0079] In some embodiments, the first configuration information can be used to configure decision thresholds corresponding to performance metrics. The decision thresholds can be used to determine whether the corresponding performance metrics meet performance requirements. For example, when the first configuration information configures the terminal device to monitor one or more performance metrics of the first model, the first configuration information may include decision thresholds corresponding to all or some of the performance metrics. For instance, when the first configuration information configures the terminal device to monitor a first performance metric and a second performance metric of the first model, the first configuration information may include decision thresholds corresponding to the first performance metric and / or decision thresholds corresponding to the second performance metric.

[0080] Whether the performance of the first model (i.e., the overall performance of the first model) meets the performance requirements can be determined by whether one or more performance indicators of the first model meet the performance requirements. For example, if all performance indicators of the first model meet the performance requirements, the performance of the first model meets the performance requirements, that is, the performance is good. Alternatively, if the number of performance indicators that meet the performance requirements is greater than or equal to a first specific number, the performance of the first model meets the requirements. Here, the first specific number is a positive integer. Another example is that if at least one performance indicator does not meet the performance requirements, the performance of the first model does not meet the performance requirements, that is, the performance is poor. Yet another example is that if the number of performance indicators that do not meet the performance requirements is greater than or equal to a second specific number, the performance of the first model does not meet the performance requirements. Here, the second specific number is a positive number.

[0081] For example, if the terminal device determines whether one or more performance indicators meet the performance requirements, and / or the terminal device determines whether the performance of the first model meets the performance requirements, the first configuration information may include the decision threshold corresponding to the performance indicator for the terminal device to make a judgment.

[0082] For example, if the network device determines whether one or more performance metrics meet the performance requirements, and / or if the performance of the first model meets the performance requirements, the first configuration information may not include the decision threshold corresponding to that performance metric. Considering that the comparison based on the decision threshold only occurs on the network device side in this case, the terminal device only needs to detect the corresponding performance metric; therefore, the first configuration information may not include the corresponding decision threshold. For example, the network device may only need to provide the average prediction error for all times within the prediction window to be monitored, and have the terminal device report this average value. The network will then further determine whether the performance of the first model is good based on this average value.

[0083] For example, if one or more performance metric decision thresholds are predefined, preconfigured, or default values, the first configuration information may not include the performance metric decision threshold.

[0084] It should be noted that the decision threshold can be either a number threshold or a ratio threshold. A number threshold can be a threshold for the number of times performance meets the target. A ratio threshold can be a threshold for the percentage of times performance meets the target. Taking the ratio threshold as an example, a performance threshold can be a prediction accuracy threshold. For instance, with a prediction accuracy threshold of 80%, if more than 80% of the error values ​​meet the requirement, then the model's prediction accuracy meets the requirement. Similarly, with a number threshold, a performance threshold can be a threshold for the number of accurately predicted cells. For instance, with 8 accurately predicted cells, if 8 or more time-based error values ​​within the prediction window meet the requirement, then the model's prediction accuracy meets the requirement. Furthermore, in a multi-cell scenario, with 3 accurately predicted cells, if the number of accurately predicted cells is greater than or equal to 3, then the model's prediction accuracy meets the requirement.

[0085] In some embodiments, the first configuration information is further configured to: determine that the performance indicator meets the performance requirements when the performance indicator is greater than or equal to a decision threshold; or determine that the performance indicator meets the performance requirements when the performance indicator is less than or equal to a decision threshold. In other words, the first configuration information can be used to configure whether the condition for determining that the performance indicator meets the requirements is that the performance indicator is greater than or equal to the decision threshold or less than or equal to the decision threshold. For example, a single bit can be used to configure whether the condition for determining that the performance indicator meets the requirements is that the performance indicator is greater than or equal to the decision threshold. For instance, if the single bit is a first specific value, it can be configured that the condition for determining that the performance indicator meets the requirements is that the performance indicator is greater than or equal to the decision threshold; if the single bit is not a first specific value, it can be configured that the condition for determining that the performance indicator meets the requirements is that the performance indicator is less than or equal to the decision threshold. The first specific value can be 0 or 1.

[0086] In some embodiments, the performance metric can be determined based on an error value. The error value can be, for example, the difference between a predicted value and a measured value. The error can be achieved through subtraction. For example, the error can be equal to the predicted value minus the measured value. Alternatively, the error can be equal to the measured value minus the predicted value. Or, the error can be equal to the absolute value of the difference between the measured value and the predicted value.

[0087] Taking RSRP as an example, the error value can be the difference between the measured RSRP and the predicted RSRP. Similarly, taking RSRQ as an example, the error value can be the difference between the measured RSRQ and the predicted RSRQ. Taking SINR as an example, the error value can be the difference between the measured SINR and the predicted SINR. Finally, taking uplink data arrival volume as an example, the error value can be the difference between the measured uplink data arrival volume and the predicted uplink data arrival volume.

[0088] In some embodiments, the performance metrics monitored for the first model may include: performance metrics for a single cell and / or a single service, and / or performance metrics for multiple cells and / or multiple services. Examples are given below for different scenarios.

[0089] Performance metrics for a single cell / single service

[0090] In this application, a single cell can correspond to channel prediction, that is, predicting the future channel changes of a specific cell. A single service can correspond to service prediction, predicting the future data arrival status of a specific terminal device's service.

[0091] For performance metrics of a single cell and / or a single service, the predicted values ​​include predicted values ​​for one cell / single service at one or more time points. In other words, the predicted values ​​can include one or more predicted values ​​corresponding to one or more time points respectively. Therefore, a performance metric for a single cell / single service can be obtained based on monitoring one or more predicted values ​​corresponding to one or more time points.

[0092] As one implementation approach, performance metrics for a single cell and / or a single service can be determined based on the error values ​​at K time points within a first time window. Here, K is a positive integer, representing the number of specific time points.

[0093] As one implementation approach, performance metrics for a single cell and / or a single service can be determined based on the error values ​​of M% of moments within a first time window. Here, M is a positive number less than or equal to 100. M represents the proportion of the number of moments indicated by the performance metric within the total number of predicted moments in the first time window.

[0094] It should be noted that, in this application, the first time window is a time period. For example, the first model can be used to predict values ​​corresponding to one or more moments in a prediction window based on the observation window. The first time window can be this prediction window.

[0095] For example, the first time window may include multiple prediction times. At each prediction time, a predicted value can be obtained based on the first model. Some or all of the multiple prediction times can be K times or M% times. For example, K times are the K times with the largest error values ​​within the first time window; K times are the K times with the smallest error values ​​within the first time window; or K is specified. When K equals the maximum value of the prediction times within the first time window, K times can be all the prediction times within the first time window. Similarly, M% times are the M% times with the largest error values ​​within the first time window; or, M% times are the M% times with the smallest error values ​​within the first time window. When M equals 100, M% times can be all the prediction times within the first time window.

[0096] The K or M% moments with the smallest error value within the first time window can be determined based on the following methods: Arrange the predicted moments within the first time window in ascending order of error value, and the first K or M% moments are the K or M% moments with the smallest error value within the first time window; or, arrange the predicted moments within the first time window in descending order of error value, and the last K or M% moments are the K or M% moments with the smallest error value within the first time window.

[0097] The K or M% times with the largest error value within the first time window can be determined using the following methods: Arrange the predicted times within the first time window in ascending order of error value, and the last K or M% times are the K or M% times with the largest error value within the first time window; or, arrange the predicted times within the first time window in descending order of error value, and the first K or M% times are the K or M% times with the largest error value within the first time window.

[0098] The performance metrics for a single cell and / or a single service may include one or more of the following: metric 1, metric 2, metric 3, metric 4, metric 5, metric 6, metric 7, and metric 8. These will be explained below.

[0099] The first indicator is used to indicate the error values ​​corresponding to K times within the first time window. For example, the first indicator can indicate the K times with the smallest (or largest) prediction error within the prediction window, or the K error values ​​corresponding to a specified set of K times.

[0100] The second indicator is used to indicate the average error value corresponding to K times within the first time window. For example, the second indicator can indicate the average of the K error values ​​corresponding to the K times with the smallest (or largest) prediction error within the prediction window, or a specified K times.

[0101] The third indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the first threshold among the K time points corresponding to the first time window. For example, the third indicator can indicate the number or percentage of error values ​​that are higher or lower than the first threshold among the K time points with the smallest (or largest) prediction error within the prediction window, or among the specified K time points (i.e., the number / percentage of predictions that meet or fail to meet the accuracy target).

[0102] For example, the ratio of error values ​​at K times in the first time window that are higher or lower than the first threshold can be: the number of error values ​​at K times in the first time window that are higher or lower than the first threshold divided by K.

[0103] The decision threshold corresponding to the third indicator can be, for example, the first quantity or the first ratio. The first quantity can be a positive integer. The first ratio can be a number greater than 0 and less than 1.

[0104] For example, if a third indicator is used to indicate the number of error values ​​below a first threshold among K time points in a first time window, and the number indicated by the third indicator is greater than or equal to the first number, then the third indicator can be considered to meet the performance requirements. Similarly, if a third indicator is used to indicate the number of error values ​​above a first threshold among K time points in a first time window, and the number indicated by the third indicator is less than or equal to the first number, then the third indicator can be considered to meet the performance requirements. Likewise, if a third indicator is used to indicate the percentage of error values ​​below a first threshold among K time points in a first time window, and the percentage indicated by the third indicator is greater than or equal to the first percentage, then the third indicator can be considered to meet the performance requirements. Finally, if a third indicator is used to indicate the percentage of error values ​​above a first threshold among K time points in a first time window, and the number indicated by the third indicator is less than or equal to the first percentage, then the third indicator can be considered to meet the performance requirements.

[0105] The fourth metric indicates whether the average error value corresponding to K times within the first time window is higher or lower than the second threshold. For example, the fourth metric can indicate whether the average error value of the K times with the smallest (or largest) prediction error within the prediction window, or a specified set of K times, is higher or lower than the second threshold. When K equals the maximum number of times within the prediction window, it means that the fourth metric is the average error of all prediction times within the prediction window.

[0106] Understandably, the second threshold can be the decision threshold corresponding to the second or fourth indicator.

[0107] The fifth indicator is used to indicate the error values ​​corresponding to the M% of time points in the first time window. For example, the fifth indicator can indicate the M% of time points with the smallest (or largest) prediction error within the prediction window, or the M% of time points with specified error values.

[0108] It should be noted that M% can be determined by using the total number of predicted moments within the first time window as the denominator. M can satisfy: 0 < M ≤ 100.

[0109] The sixth indicator is used to indicate the average error value corresponding to the M% of time points in the first time window. For example, the sixth indicator can indicate the average of the M% of time points with the smallest (or largest) prediction error within the prediction window, or the average of the M% of error values ​​corresponding to a specified M% of time points.

[0110] The seventh indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points. For example, the seventh indicator can indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points with the smallest (or largest) prediction error within the prediction window, or among the specified M% of time points (i.e., the number / percentage of prediction accuracy achieved).

[0111] For example, the ratio of error values ​​that are higher or lower than the third threshold among the M% of time points in the first time window can satisfy: the ratio = the number of error values ​​that are higher or lower than the third threshold among the M% of time points in the first time window ÷ (M% × the total number of prediction time points in the first time window).

[0112] The decision threshold corresponding to the seventh indicator can be, for example, a second quantity or a second ratio. The second quantity can be a positive integer. The second ratio can be a number greater than 0 and less than 1.

[0113] For example, if the seventh indicator is used to indicate the number of error values ​​lower than the seventh indicator among the M% of time points in the first time window, and the number indicated by the seventh indicator is greater than or equal to the second number, then the seventh indicator can be considered to meet the performance requirements. Similarly, if the seventh indicator is used to indicate the number of error values ​​higher than the seventh indicator among the M% of time points in the first time window, and the number indicated by the seventh indicator is less than or equal to the second number, then the seventh indicator can be considered to meet the performance requirements. Likewise, if the seventh indicator is used to indicate the percentage of error values ​​lower than the seventh indicator among the M% of time points in the first time window, and the percentage indicated by the seventh indicator is greater than or equal to the second percentage, then the seventh indicator can be considered to meet the performance requirements. Finally, if the seventh indicator is used to indicate the percentage of error values ​​higher than the seventh indicator among the M% of time points in the first time window, and the number indicated by the seventh indicator is less than or equal to the second percentage, then the seventh indicator can be considered to meet the performance requirements.

[0114] The eighth metric indicates whether the average error value corresponding to the M% of time points is higher or lower than the fourth threshold. For example, the eighth metric can indicate whether the average error value of the M% of time points with the smallest (or largest) prediction error within the prediction window, or a specified M% of time points, is higher or lower than the fourth threshold. When M equals 100, it means that the eighth metric is the average error of all prediction time points within the prediction window.

[0115] Understandably, the fourth threshold can be the decision threshold corresponding to the sixth or eighth indicator.

[0116] The first configuration information allows you to configure the above metrics. An example is provided below.

[0117] In some embodiments, the first configuration information can be used to configure how the K time points are determined. For example, the first configuration information can be used to configure one of the following: the K time points are the K time points with the largest error values ​​within the first time window; the K time points are the K time points with the smallest error values ​​within the first time window; and the positions of the K time points within the first time window.

[0118] In some embodiments, the first configuration information can be used to configure how the M% time points are determined. For example, the first configuration information can be used to configure one of the following: the M% time points are the M% time points with the largest error values ​​within the first time window; the M% time points are the M% time points with the smallest error values ​​within the first time window.

[0119] In some embodiments, the first configuration information can be used to configure whether the monitored data is the error value at multiple time points or the average of the error values ​​at multiple time points. For example, the first configuration information is used to configure one or more of the following: one or more performance metrics for one or more error values; one or more performance metrics for the average of one or more error values.

[0120] In some embodiments, the first configuration information can be used to configure whether the number of monitored time points is M% of time points or K time points, that is, the first configuration information is used to configure whether the number of monitored time points is expressed as a quantity or a proportion. For example, the first configuration information can be used to configure one or more of the following: one or more performance metrics corresponding to error values ​​for M% of time points; one or more performance metrics corresponding to error values ​​for K time points.

[0121] In some embodiments, the first configuration information can be used to configure the values ​​of K and / or M. For example, when the number of monitored moments is represented by K, the first configuration information can be used to configure the value of K. Similarly, when the number of monitored moments is represented by M% of the total monitored moments, the first configuration information can be used to configure the value of M.

[0122] In some embodiments, the first configuration information can be used to configure the values ​​of each threshold. For example, the first configuration information can be used to configure one or more of the following: a first threshold, a second threshold, a third threshold, and a fourth threshold.

[0123] In some embodiments, the first configuration information can be used to configure whether the error value comparison is above or below a threshold. For example, the first configuration information can be used to configure one or more of the following: a third indicator to indicate the number or percentage of error values ​​above the first threshold corresponding to K time points; a fourth indicator to indicate that the average error values ​​at the K time points are above a second threshold; a fourth indicator to indicate that the average error values ​​at the K time points are below the second threshold; a seventh indicator to indicate the number or percentage of error values ​​above the third threshold corresponding to M% time points; a seventh indicator to indicate the number or percentage of error values ​​below the third threshold corresponding to M% time points; and a third indicator to indicate the number or percentage of error values ​​below the first threshold corresponding to K time points.

[0124] In some embodiments, the first configuration information can be used to configure whether the performance metric indicates a ratio or a quantity. For example, the first configuration information can be used to indicate one or more of the following: a third metric indicating a quantity; a third metric indicating a ratio; a seventh metric indicating a quantity; or a seventh metric indicating a ratio.

[0125] In some embodiments, the first configuration information can be used to configure whether the monitored case is the one with the largest error value (or the worst predicted performance) or the smallest error value (or the best predicted performance). For example, the first configuration information can be used to configure one of the following: K time points are the K time points with the largest error value within the first time window; K time points are the K time points with the smallest error value within the first time window; M% time points are the M% time points with the largest error value within the first time window; M% time points are the M% time points with the smallest error value within the first time window.

[0126] To facilitate understanding, the following examples 1 to 3 illustrate the performance metrics for a single cell / single service.

[0127] Example 1: Within the prediction window, there are 10 prediction times. The terminal device monitoring metric is the 3 times with the largest RSRP prediction error for a single cell / single service. The number of times the corresponding error value is lower than a given threshold (i.e., the first threshold or the third threshold) is 2. Here, K = 3 or M = 30. The network-configured prediction accuracy threshold (i.e., decision threshold) Q = 2. In this case, the model performance is good.

[0128] Example 2: Within the prediction window, there are 10 prediction times. The terminal device monitoring metric is the 10 times (i.e., all times) with the smallest prediction error for uplink data arrivals per cell / service. The number of these 10 times with error values ​​exceeding a given threshold (i.e., the first or third threshold) is 7. Here, K = 10, or M = 100. The network-configured prediction accuracy threshold is Q = 5. In this case, if the number of prediction errors exceeding the given threshold is greater than the network-configured allowable prediction accuracy threshold, it indicates poor model performance.

[0129] Example 3: There are 10 prediction times within the prediction window. The terminal device monitoring metric is the RSRP prediction error at times 1, 3, and 7 (the specified K times) for a single cell / single service. The number of error values ​​below a given threshold (first or third threshold) is 3. The network is configured with a prediction accuracy threshold of Q = 3. In this case, the model performs well.

[0130] Performance metrics for multiple cells / multiple services

[0131] In this application, multiple cells can correspond to channel prediction, that is, predicting the future channel changes of specific multiple cells. Multiple services can correspond to service prediction, that is, predicting the future data arrival status of multiple services for a specific terminal device.

[0132] For performance metrics of multiple cells and / or multiple services, the predicted values ​​include multiple predicted values ​​for multiple cells and / or multiple predicted values ​​for multiple services.

[0133] As one implementation approach, performance metrics for multiple cells and / or multiple services can be determined based on the error values ​​of P cells / services. Here, P is a positive integer, representing the number of specific cells or services.

[0134] As one implementation approach, performance metrics for multiple cells and / or multiple services can be determined based on the error values ​​of R% of cells / services. Here, R is a positive number less than or equal to 100. R represents a proportion. Specifically, R represents the proportion of the number of cells / services indicated by the performance metrics to the total number of cells / services.

[0135] Multiple cells / services can be partially or entirely represented by P cells / services or R% cells / services. For example, P cells / services can be the P cells / services with the largest error value among the multiple cells / services; P cells / services can be the P cells / services with the smallest error value among the multiple cells / services; or, P can be specified. For another example, when P equals the total number of multiple cells / services, P cells / services represent all cells / services. Similarly, R% cells / services can be the R% cells / services with the largest error value among the multiple cells / services; R% cells / services can be the R% cells / services with the smallest error value among the multiple cells / services; or, R can be specified. For yet another example, when R equals 100, R% cells / services represent all cells / services.

[0136] The P or R% cells / services with the smallest error values ​​can be determined based on the following methods: arranging all cells / services in ascending order of error value, the first P or R% cells / services are the P or R% times with the smallest error values; or arranging all cells / services in descending order of error value, the last P or R% cells / services are the P or R% times with the smallest error values.

[0137] The P or R% cells / services with the largest error values ​​can be determined using the following methods: Arrange all cells / services in ascending order of error value, and the last P or R% cells / services will be the P or R% times with the largest error values; or, arrange all cells / services in descending order of error value, and the first P or R% cells / services will be the P or R% times with the largest error values.

[0138] Performance metrics for multiple cells and / or multiple services may include one or more of the following: Ninth metric, Tenth metric, Eleventh metric, Twelfth metric, Thirteenth metric, Fourteenth metric, Fifteenth metric, Sixteenth metric, Seventeenth metric, Nineteenth metric, Twentieth metric, Twenty-first metric, and Twenty-second metric.

[0139] The ninth indicator is used to indicate the average error value of P cells / services. For example, the ninth indicator can be used to indicate the average error value of the P cells / services with the smallest (or largest) error value.

[0140] The tenth indicator is used to indicate the error values ​​of P cells / services. For example, the tenth indicator can be used to indicate the error values ​​of the P cells / services with the smallest (or largest) error values.

[0141] The eleventh indicator is used to indicate the number or percentage of error values ​​in P cells / services that are higher or lower than the fifth threshold. For example, the eleventh indicator can be used to indicate the number or percentage of error values ​​in the P cells / services with the smallest (or largest) error values ​​that are higher or lower than the fifth threshold.

[0142] For example, the number or ratio of error values ​​above or below the fifth threshold among P cells / services can be: the number of cells / services above or below the fifth threshold divided by P.

[0143] The decision threshold corresponding to the eleventh indicator can be, for example, the third quantity or the third ratio. The third quantity can be a positive integer. The third ratio can be a number greater than 0 and less than 1.

[0144] For example, if the eleventh indicator is used to indicate the number of error values ​​below the fifth threshold among P cells / services, then if the number indicated by the eleventh indicator is greater than or equal to the third number, the eleventh indicator can be considered to meet the performance requirements. Similarly, if the eleventh indicator is used to indicate the number of error values ​​above the fifth threshold among P cells / services, then if the number indicated by the eleventh indicator is less than or equal to the third number, the eleventh indicator can be considered to meet the performance requirements. Likewise, if the eleventh indicator is used to indicate the percentage of error values ​​below the fifth threshold among P cells / services, then if the percentage indicated by the eleventh indicator is greater than or equal to the third percentage, the eleventh indicator can be considered to meet the performance requirements. Finally, if the eleventh indicator is used to indicate the percentage of error values ​​above the fifth threshold among P cells / services, then if the percentage indicated by the eleventh indicator is less than or equal to the third percentage, the eleventh indicator can be considered to meet the performance requirements.

[0145] The twelfth indicator is used to indicate whether the average error value of P cells / services is higher or lower than the sixth threshold. For example, the twelfth indicator can be used to indicate whether the average error value of the P cells / services with the smallest (or largest) error value is higher or lower than the sixth threshold. The sixth threshold can be a positive number.

[0146] It is understandable that the sixth threshold can be the decision threshold corresponding to the ninth or twelfth indicator.

[0147] The thirteenth metric indicates the average error value of R% of cells / services. For example, the thirteenth metric can be used to indicate the average error value of the R% of cells / services with the smallest (or largest) error values.

[0148] The fourteenth indicator is used to indicate the error value of R% of cells / services. For example, the fourteenth indicator can be used to indicate the error value of the R% of cells / services with the smallest (or largest) error value.

[0149] The fifteenth indicator is used to indicate the number or percentage of error values ​​above or below the seventh threshold among R% of cells / services with the smallest (or largest) error values. For example, the fifteenth indicator can be used to indicate the number or percentage of error values ​​above or below the seventh threshold among the R% of cells / services with the smallest (or largest) error values. The percentage can be calculated using the total number of error values ​​as the denominator. When the seventh threshold corresponds to a quantity, the seventh threshold can be a positive integer. When the seventh threshold corresponds to a percentage, the seventh threshold can be a positive number less than or equal to 100%.

[0150] For example, the ratio of error values ​​of R% cells / services that are higher or lower than the seventh threshold can satisfy: the ratio = the number of error values ​​of R% cells / services that are higher or lower than the seventh threshold ÷ (R% × total number of cells or services).

[0151] The decision threshold corresponding to the fifteenth indicator could be, for example, the fourth quantity or the fourth ratio. The fourth quantity can be a positive integer. The fourth ratio can be a number greater than 0 and less than 1.

[0152] For example, if the fifteenth indicator is used to indicate the number of error values ​​below the seventh threshold among R% of cells / services, and the number indicated by the fifteenth indicator is greater than or equal to the fourth number, then the fifteenth indicator can be considered to meet the performance requirements. Similarly, if the fifteenth indicator is used to indicate the number of error values ​​above the seventh threshold among R% of cells / services, and the number indicated by the fifteenth indicator is less than or equal to the fourth number, then the fifteenth indicator can be considered to meet the performance requirements. Likewise, if the fifteenth indicator is used to indicate the percentage of error values ​​below the seventh threshold among R% of cells / services, and the percentage indicated by the fifteenth indicator is greater than or equal to the fourth percentage, then the fifteenth indicator can be considered to meet the performance requirements. Finally, if the fifteenth indicator is used to indicate the percentage of error values ​​above the seventh threshold among R% of cells / services, and the percentage indicated by the fifteenth indicator is less than or equal to the fourth percentage, then the fifteenth indicator can be considered to meet the performance requirements.

[0153] The sixteenth indicator is used to indicate whether the average error value of R% of cells / services is higher or lower than the eighth threshold. For example, the sixteenth indicator can be used to indicate whether the average error value of the R% of cells / services with the smallest (or largest) error value is higher or lower than the eighth threshold. The eighth threshold can be a positive number.

[0154] Understandably, the eighth threshold could be the decision threshold corresponding to the thirteenth or sixteenth indicator.

[0155] The seventeenth indicator is used to indicate the first set and the second set. The first set includes the Q1 or Q2% of cells with the largest or smallest predicted values ​​among multiple cells / services. That is, the first set includes one or more cells with the best (or worst) predicted performance. The second set includes the Q1 or Q2% of cells with the largest or smallest actual measured values ​​among multiple cells / services. That is, the second set includes one or more cells with the best actual performance.

[0156] The eighteenth metric indicates the number or ratio of cells / services in the first set that have the same identifier as cells / services in the second set. Alternatively, the eighteenth metric can indicate the number or ratio of cells / services in the second set that have the same identifier as cells / services in the first set. It is understood that the eighteenth metric can also indicate the number or ratio of cells / services that overlap or are identical with one or more of the predicted best (or worst) performing cells / services and the actual best performing cells / services. The ratio can be calculated with the number of cells / services in the first set as the denominator or with the number of cells / services in the second set as the denominator.

[0157] For example, if the index of the cell or service contained in the first set is {1,2,3}, and the index of the cell or service contained in the second set is {1,3,2}, then the eighteenth index can indicate that the number of identical identifiers in the first set and the second set is 3 or 100%.

[0158] The nineteenth indicator is used to indicate the first sequence and the second sequence. The first sequence includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the cells / services in the first sequence are sorted according to the size of the predicted values. For example, the cells / services in the first sequence are arranged from largest to smallest predicted values. Alternatively, the cells / services in the first sequence are arranged from smallest to largest predicted values. The second sequence includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services, and the cells / services in the second sequence are sorted according to the size of the measured values. For example, the cells / services in the second sequence are arranged from largest to smallest measured values. Alternatively, the cells / services in the second sequence are arranged from smallest to largest measured values.

[0159] It should be noted that the first and second sequences must be sorted in the same way. Either the first and second sequences must be arranged in ascending order, or both must be arranged in descending order.

[0160] The twentieth metric is used to indicate the number or ratio of cells / services in the first sequence that have the same identifier and location as those in the second sequence. It can be understood that the twentieth metric can be used to indicate the number or ratio of cells that overlap with and are arranged in the same position among one or more predicted best (or worst) performing cells and one or more actually best performing cells. The ratio can be calculated using either the number in the first sequence or the number in the second sequence as the denominator.

[0161] For example, the first sequence contains cells or services with indices {1,2,3}, and the second sequence contains cells or services with indices {1,3,2}. It can be seen that only cells or services with index 1 are included in both the first and second sequences and are located in the same position. Therefore, the twentieth index can indicate that the number of cells or services with the same identifier and location in both the first and second sequences is 1 or 33.3%.

[0162] The first configuration information can be used to configure parameters related to the above metrics. An example is provided below.

[0163] In some embodiments, the first configuration information can be used to configure whether the monitored data is the error value of multiple cells / services or the average error value of multiple cells / services. For example, the first configuration information is used to configure one or more of the following: the one or more performance metrics are for one or more error values; the one or more performance metrics are for the average of one or more error values.

[0164] In some embodiments, the first configuration information can be used to configure whether the number of monitored cells / services is R% or P, that is, the first configuration information is used to configure whether the number of monitored cells / services is expressed as a quantity or a proportion. For example, the first configuration information can be used to configure one or more of the following: one or more performance metrics for the error values ​​of the R% cells / services; one or more performance metrics for the error values ​​of the P cells / services.

[0165] In some embodiments, the first configuration information can be used to configure the values ​​of R and / or P. For example, when the number of monitored cells / services is represented by R% (R%), the first configuration information can configure the value of R. Similarly, when the number of monitored cells / services is represented by P, the first configuration information can configure the value of P.

[0166] In some embodiments, the first configuration information can be used to configure the values ​​of thresholds related to performance metrics. For example, the first configuration information can be used to configure one or more of the following: a fifth threshold; a sixth threshold; a seventh threshold; and an eighth threshold.

[0167] In some embodiments, the first configuration information can be used to configure whether the error value comparison is above or below a threshold. For example, the eleventh indicator is used to indicate the number or percentage of error values ​​of P cells / services that are above the fifth threshold; the eleventh indicator is used to indicate the number or percentage of error values ​​of P cells / services that are below the fifth threshold; the twelfth indicator is used to indicate that the average error value of P cells / services is above the sixth threshold; the twelfth indicator is used to indicate that the average error value of P cells / services is below the sixth threshold.

[0168] In some embodiments, the first configuration information can be used to configure whether the performance metric indicates a ratio or a quantity. For example, the first configuration information can be used to indicate one or more of the following: the eleventh metric indicates a quantity; the eleventh metric indicates a ratio; the twelfth metric indicates a quantity; the twelfth metric indicates a ratio; the eighteenth metric indicates a quantity; the eighteenth metric indicates a ratio; the twentieth metric indicates a quantity; the twentieth metric indicates a ratio.

[0169] In some embodiments, the first configuration information can be used to configure whether the monitored case is the one with the largest error value (e.g., the worst predicted performance) or the one with the smallest error value (e.g., the best predicted performance). For example, the first configuration information can be used to configure one of the following: P cells / services are the multiple cells / services with the largest error values; P cells / services are the multiple cells / services with the smallest error values; R% cells / services are the multiple cells / services with the largest error values; R% cells / services are the multiple cells / services with the smallest error values.

[0170] In some embodiments, the first configuration information can be used to configure how to determine the P cells. For example, the first configuration information is used to configure any of the following: the P cells / services are the P cells / services with the largest error among multiple cells / services; the P cells / services are the P cells / services with the smallest error among multiple cells / services; the identifiers of the specified P cells / services; or the P cells are randomly selected.

[0171] The twenty-first indicator is used to indicate the ratio of cells / services with the largest or smallest measured values ​​contained in the first set or the first sequence.

[0172] The twenty-second indicator is used to indicate the ratio of cells / services with the largest or smallest predicted values ​​contained in the second set or second sequence.

[0173] To facilitate understanding, the following examples 4 to 6 illustrate the performance metrics for multiple cells / services.

[0174] Example 4: There are currently 3 monitored cells, each with a prediction window of 10 time points. The percentage of time points meeting the prediction error requirement is 80% (cell 1), 60% (cell 2), and 90% (cell 3). The first configuration indicates that monitoring needs to be done on the two cells with the largest prediction errors (P=2). Therefore, cells 1 and 3 are selected for monitoring. The average prediction accuracy of cells 1 and 3 is 85%. 85% is higher than the prediction accuracy threshold of 80%. In this case, the model performance can be judged to be good.

[0175] Example 5: Currently, there are 4 UE services, each with 10 prediction windows. Among the 5 prediction windows with the smallest errors, the number of times the prediction error requirement is met is 4 (Service 1), 5 (Service 2), 2 (Service 3), and 3 (Service 4). The first configuration information indicates that the service with the best prediction error performance (M2% = 50%) needs to be monitored. Therefore, Services 1 and 2 are selected for monitoring. The average number of times Services 1 and 2 meet the prediction error requirement is 4.5. 4.5 is not lower than the given decision threshold of 4. In this case, the model performance can be judged to be good.

[0176] Example 6: Currently, there are 4 monitored cells. The set of cells with the best predicted channel conditions (P=3) is {cell 1, cell 3, cell 4}. The cells with the best actual channel conditions are {cell 1, cell 2, cell 3}, resulting in a prediction accuracy of 2 / 3. 2 / 3 is higher than the network's pre-configured prediction accuracy threshold of 60%. In this case, the model performance is considered good.

[0177] As mentioned above, in related technologies (such as the R18AI / ML for air project), model monitoring metrics only include physical layer-related metrics, i.e., only beam-level results. With technological advancements, some technologies (such as the R19AI mobility project) have proposed higher-level performance metrics for model performance evaluation, but these are relatively limited in number and currently seem to favor single-cell performance prediction, i.e., monitoring the prediction performance within a single cell and a single power wave (PW). This application, however, not only proposes higher-level performance metrics but also extends these metrics to more likely multi-cell / service scenarios, thereby broadening the applicable scenarios for performance monitoring.

[0178] It should be noted that performance metrics for multiple cells / multiple services and performance metrics for a single cell / single service can be used together or separately. For example, one or more of metrics nine through sixteen can be used together with performance metrics for a single cell / single service. Conversely, metrics seventeen through twenty-two can be used independently.

[0179] In some embodiments, the first configuration information is used to configure total duration information. The total duration information is the total duration for which the terminal device needs to monitor. The total duration indicated by the total duration information may include one or more prediction windows. For example, in a single-cell / single-service scenario, the first configuration information can be used to configure the total duration information.

[0180] In some implementations, the initial configuration information can be used to configure monitoring statistics. Monitoring statistics can be used to indicate whether monitoring is based on an average over the total monitoring duration or on the number or percentage of monitoring targets met across all prediction windows during the total monitoring duration (e.g., RSRP prediction error is less than 1 dB at all times within the prediction window).

[0181] Based on the total duration information and / or monitoring statistics, the terminal device can calculate statistical values ​​for the monitored duration, such as calculating the average value. These statistical values ​​may include one or more of the following: predicted values, measured values, and error values. The terminal device can then report the calculated statistical values ​​to the network device.

[0182] For example, a network device can be configured to indicate a total duration of 1 second. The prediction window contains 10 time points, each spaced 10ms apart, for a total of 100ms. The terminal device monitors the average of the predicted values ​​at the 10 time points within the prediction window, and then averages the average values ​​of all calculated prediction windows within 1 second to calculate the average value over the total monitoring time.

[0183] For example, network devices can be configured to monitor terminal devices within 1 second, meaning the total duration indicated by the total duration information is 1 second. Furthermore, the monitoring metric remains the number or percentage of devices that meet the monitoring criteria within each prediction window, rather than averaging the statistical values ​​within the total duration information.

[0184] In some embodiments, the first configuration information is used to configure performance metrics for a channel. When the performance metrics are channel-specific, the performance metrics may include one or more of the following: RSRP, reference signal received quality (RSRQ), received signal strength indicator (RSSI), signal to interference plus noise ratio (SINR), etc. In this case, the first configuration information may be used to configure the monitored performance metrics for one or more of the following: RSRP, RSRQ, SINR, etc.

[0185] In some embodiments, the first configuration information can be used to configure performance metrics for the services of the terminal device. When the performance metrics are for the services of the terminal device, the performance metrics may include uplink data arrivals. In this case, the first configuration information can be used to configure the monitored performance metrics for uplink data arrivals.

[0186] In some embodiments, the terminal device may send first information. This first information indicates whether one or more performance indicators meet performance requirements. Alternatively, the first information may indicate whether a first model meets performance requirements (i.e., whether the performance of the first model is good). Whether the first model meets performance requirements is determined based on whether each performance indicator meets the performance requirements. For example, if all performance indicators meet their corresponding performance requirements, the first model meets the performance requirements, meaning the first model performs well. Furthermore, if the number of performance indicators that meet the performance requirements is greater than a first threshold, the first model meets the performance requirements. Here, the first threshold is a positive integer.

[0187] As mentioned above, the terminal device can determine whether the performance indicators meet the performance requirements (e.g., based on the performance indicators), meaning that the determination of performance indicators can occur on the terminal device side. In this case, the terminal device can send a first message to report the terminal device's determination result to the network device.

[0188] For example, the first piece of information can be indicated by one or more indicator bits corresponding to the performance indicator. The indicator bits can be used to indicate whether the corresponding performance indicator meets the performance requirements. An indicator bit of the first value indicates that the corresponding performance indicator meets the performance requirements, i.e., the performance is good; an indicator bit of a non-first value indicates that the corresponding performance indicator does not meet the performance requirements, i.e., the performance is poor. Here, the first value can be, for example, 1 or 0.

[0189] For example, the first information can be indicated by a single first indicator bit. The first indicator bit can be used to indicate whether the performance of the first model is good. A first value for the first indicator bit indicates that the performance of the first model is good, while a non-first value indicates that the performance of the first model is poor. The first value can be, for example, 1 or 0.

[0190] In some embodiments, the terminal device may send some or all of one or more performance metrics to the network device. That is, the terminal device may send some or all of the monitored performance metrics to the network device. Here, "all performance metrics" may refer to all performance metrics configured by the network device (e.g., all performance metrics configured through the first configuration information), or it may be all performance metrics monitored by the terminal device. For example, the terminal device may send some or all of the first to twenty-second metrics described above to the network device. Exemplarily, the terminal device may send the average error value at multiple times within a prediction window to the network device.

[0191] As mentioned above, network devices can determine whether performance metrics meet performance requirements; that is, performance metric determination can occur at the network device level. In this case, the terminal device can send the performance metrics it has monitored, allowing the network device to further determine whether the performance metrics meet the requirements.

[0192] In some embodiments, the terminal device may send difference value information to the network device. This difference value information indicates the difference between a performance metric and its corresponding decision threshold. For example, the terminal device may send difference value information if the performance metric or the first model does not meet performance requirements. Exemplarily, the difference value information may be used to indicate the difference between the average prediction error at multiple times within a prediction window and a decision threshold for the average prediction error configured by the network device.

[0193] Understandably, the difference value information can be used to characterize the gap between the performance of the first model and the expected performance. When the decision threshold is the network device configuration, the difference value information can characterize the gap between the performance of the first model and the expected performance of the network device.

[0194] The information sent by the terminal device can be included in the measurement results (measResults) in the relevant technology. For example, the measurement results may include one or more of the following: primary information, difference value information, and some or all performance indicators.

[0195] The method embodiments of this application have been described in detail above. The apparatus embodiments of this application are described in detail below. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments. Therefore, any parts not described in detail can be referred to the foregoing method embodiments.

[0196] Figure 5 is a schematic structural diagram of a terminal device 500 provided in an embodiment of this application. The terminal device 500 includes a receiving unit 510.

[0197] The receiving unit 510 is used to receive first configuration information sent by the network device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, the performance indicators being used to indicate the performance of the predicted values ​​obtained based on the first model, and the first model being deployed on the terminal device.

[0198] In some embodiments, the first configuration information is further used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

[0199] In some embodiments, the first configuration information is further configured to: determine that the performance indicator meets the performance requirements when the performance indicator is greater than or equal to the decision threshold; or determine that the performance indicator meets the performance requirements when the performance indicator is less than or equal to the decision threshold.

[0200] In some embodiments, the one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

[0201] In some embodiments, the error between the predicted value and the measured value is an error value, and the one or more performance indicators include one or more of the following: a first indicator for indicating the error values ​​corresponding to K times in a first time window; a second indicator for indicating the average value of the error values ​​corresponding to the K times; a third indicator for indicating the number or ratio of error values ​​corresponding to the K times that are higher or lower than a first threshold; a fourth indicator for indicating whether the average value of the error values ​​corresponding to the K times is higher or lower than a second threshold; a fifth indicator for indicating the error values ​​corresponding to M% times in the first time window; a sixth indicator for indicating the average value of error values ​​corresponding to M% times in the first time window; a seventh indicator for indicating the number or ratio of error values ​​corresponding to the M% times that are higher or lower than a third threshold; and an eighth indicator for indicating whether the average value of the error values ​​corresponding to the M% times is higher or lower than a fourth threshold.

[0202] In some embodiments, the first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

[0203] In some embodiments, the K times are the K times with the largest error values ​​within the first time window; the K times are the K times with the smallest error values ​​within the first time window; or, K is specified.

[0204] In some embodiments, the first configuration information is used to configure one of the following: the K moments are the K moments with the largest error values ​​within the first time window; the K moments are the K moments with the smallest error values ​​within the first time window; and the position of the K moments within the first time window.

[0205] In some embodiments, the M% of moments are the M% of moments with the largest error value within the first time window; or, the M% of moments are the M% of moments with the smallest error value within the first time window.

[0206] In some embodiments, the first configuration information is used to configure that: the M% of time points are the M% of time points with the largest error values ​​within the first time window; or, the M% of time points are the M% of time points with the smallest error values ​​within the first time window.

[0207] In some embodiments, the first configuration information is used to configure one or more of the following: the one or more performance metrics are for one or more error values; the one or more performance metrics are for the average of one or more error values; the one or more performance metrics are for the error values ​​corresponding to the M% time points; the one or more performance metrics are for the error values ​​corresponding to the K time points; the value of M; the value of K; a first threshold; a second threshold; a third threshold; a fourth threshold; a third indicator is used to indicate the number or ratio of error values ​​corresponding to the K time points that are higher than the first threshold; a third indicator is used to indicate the number or ratio of error values ​​corresponding to the K time points that are lower than the first threshold; a third indicator is used to indicate the number; a third indicator is used to indicate the ratio; a fourth indicator is used to indicate that the average of error values ​​corresponding to the K time points is higher than the second threshold; a fourth indicator is used to indicate that the average of error values ​​corresponding to the K time points is lower than the second threshold; a seventh indicator is used to indicate the number or ratio of error values ​​corresponding to the M% time points that are higher than the third threshold; a seventh indicator is used to indicate the number or ratio of error values ​​corresponding to the M% time points that are lower than the third threshold; a seventh indicator is used to indicate the number; a seventh indicator is used to indicate the ratio.

[0208] In some embodiments, the one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

[0209] In some embodiments, the error between the predicted value and the measured value is an error value, and the one or more performance indicators include one or more of the following: a ninth indicator, used to indicate the average error value of P cells / services; a tenth indicator, used to indicate the error value of P cells / services; an eleventh indicator, used to indicate the number or percentage of error values ​​of the P cells / services that are higher or lower than a fifth threshold; a twelfth indicator, used to indicate whether the average error value of the P cells / services is higher or lower than a sixth threshold; a thirteenth indicator, used to indicate the average error value of R% cells / services; a fourteenth indicator, used to indicate the error value of R% cells / services; a fifteenth indicator, used to indicate the number or percentage of error values ​​of the R% cells / services that are higher or lower than a seventh threshold; a sixteenth indicator, used to indicate whether the average error value of the R% cells / services is higher or lower than an eighth threshold; a seventeenth indicator, used to indicate a first set and a second set, the first set including Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the second set including multiple The eighteenth indicator indicates the number or ratio of cells / services in the first set that have the same identifier as cells / services in the second set; the nineteenth indicator indicates the first sequence and the second sequence, wherein the first sequence includes the Q1 or Q2% cells with the largest or smallest predicted value among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted value, and the second sequence includes the Q1 or Q2% cells with the largest or smallest measured value among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured value; the twentieth indicator indicates the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; the twenty-first indicator indicates the ratio of cells / services with the largest or smallest measured value in the first set or the first sequence; and the twenty-second indicator indicates the ratio of cells / services with the largest or smallest predicted value in the second set or the second sequence.

[0210] In some embodiments, the P cells satisfy any of the following: the P cells / services are the cells with the largest errors among multiple cells / services; the P cells / services are the cells with the smallest errors among multiple cells / services; the P cells / services are designated; the P cells / services are randomly selected.

[0211] In some embodiments, the first configuration information is used to configure any one of the following: the P cells / services are the P cells / services with the largest error among multiple cells / services; the P cells / services are the P cells / services with the smallest error among multiple cells / services; and the identifier of the specified P cells / services.

[0212] In some embodiments, the R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or, the R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

[0213] In some embodiments, the first configuration information is used to configure: R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or, R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

[0214] In some embodiments, the first configuration information is used to configure one or more of the following: the one or more performance metrics for one or more error values; the one or more performance metrics for the average of one or more error values; the one or more performance metrics for the error values ​​of the R% cells / services; the one or more performance metrics for the error values ​​of the P cells / services; the value of R; the value of P; the fifth threshold; the sixth threshold; the seventh threshold; the eighth threshold; the eleventh indicator is used to indicate the number or percentage of error values ​​of the P cells / services that are higher than the fifth threshold; the eleventh indicator... The first indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; the eleventh indicator is used to indicate the number; the eleventh indicator is used to indicate the percentage; the twelfth indicator is used to indicate that the average error value of the P cells / services is higher than the sixth threshold; the twelfth indicator is used to indicate that the average error value of the P cells / services is lower than the sixth threshold; the twelfth indicator is used to indicate the number; the twelfth indicator is used to indicate the percentage; the eighteenth indicator is used to indicate the number; the eighteenth indicator is used to indicate the percentage; the twentieth indicator is used to indicate the number; the twentieth indicator is used to indicate the percentage.

[0215] In some embodiments, the first configuration information is used to configure one or more of the following: the performance metrics are for the channel;

[0216] Whether the performance metric is specific to the service of the terminal device; total duration information, used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

[0217] In some embodiments, the terminal device 500 is further configured to: send first information; wherein the first information is configured to indicate whether the one or more performance indicators meet the performance requirements.

[0218] In some embodiments, the terminal device 500 is further configured to: send some or all of the one or more performance metrics.

[0219] In some embodiments, the terminal device 500 is further configured to: send difference value information; wherein the difference value information is used to indicate the difference between the performance metric and the corresponding decision threshold.

[0220] In some embodiments, the first model is an AI / ML model.

[0221] In an optional embodiment, the receiving unit 510 may be a transceiver 730. The terminal device 500 may also include a processor 710 and a memory 720, as shown in FIG7.

[0222] Figure 6 is a schematic structural diagram of a network device 600 provided in an embodiment of this application. The network device 600 may include a transmitting unit 610.

[0223] The sending unit 610 is used to send first configuration information to the terminal device; wherein the first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, the performance indicators being used to indicate the performance of the predicted values ​​obtained based on the first model, the first model being deployed on the terminal device.

[0224] In some embodiments, the first configuration information is further used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

[0225] In some embodiments, the first configuration information is further configured to: determine that the performance indicator meets the performance requirements when the performance indicator is greater than or equal to the decision threshold; or determine that the performance indicator meets the performance requirements when the performance indicator is less than or equal to the decision threshold.

[0226] In some embodiments, the one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

[0227] In some embodiments, the error between the predicted value and the measured value is an error value, and the one or more performance indicators include one or more of the following: a first indicator for indicating the error values ​​corresponding to K times in a first time window; a second indicator for indicating the average value of the error values ​​corresponding to the K times; a third indicator for indicating the number or ratio of error values ​​corresponding to the K times that are higher or lower than a first threshold; a fourth indicator for indicating whether the average value of the error values ​​corresponding to the K times is higher or lower than a second threshold; a fifth indicator for indicating the error values ​​corresponding to M% times in the first time window; a sixth indicator for indicating the average value of error values ​​corresponding to M% times in the first time window; a seventh indicator for indicating the number or ratio of error values ​​corresponding to the M% times that are higher or lower than a third threshold; and an eighth indicator for indicating whether the average value of the error values ​​corresponding to the M% times is higher or lower than a fourth threshold.

[0228] In some embodiments, the first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

[0229] In some embodiments, the K times are the K times with the largest error values ​​within the first time window; the K times are the K times with the smallest error values ​​within the first time window; or K is specified.

[0230] In some embodiments, the first configuration information is used to configure one of the following: the K moments are the K moments with the largest error values ​​within the first time window; the K moments are the K moments with the smallest error values ​​within the first time window; and the position of the K moments within the first time window.

[0231] In some embodiments, the M% of moments are the M% of moments with the largest error value within the first time window; or, the M% of moments are the M% of moments with the smallest error value within the first time window.

[0232] In some embodiments, the first configuration information is used to configure that: the M% of time points are the M% of time points with the largest error values ​​within the first time window; or, the M% of time points are the M% of time points with the smallest error values ​​within the first time window.

[0233] In some embodiments, the first configuration information is used to configure one or more of the following: the one or more performance metrics are for one or more error values; the one or more performance metrics are for the average of one or more error values; the one or more performance metrics are for the error values ​​corresponding to the M% time points; the one or more performance metrics are for the error values ​​corresponding to the K time points; the value of M; the value of K; a first threshold; a second threshold; a third threshold; a fourth threshold; a third indicator is used to indicate the number or ratio of error values ​​corresponding to the K time points that are higher than the first threshold; a third indicator is used to indicate the number or ratio of error values ​​corresponding to the K time points that are lower than the first threshold; a third indicator is used to indicate the number; a third indicator is used to indicate the ratio; a fourth indicator is used to indicate that the average of error values ​​corresponding to the K time points is higher than the second threshold; a fourth indicator is used to indicate that the average of error values ​​corresponding to the K time points is lower than the second threshold; a seventh indicator is used to indicate the number or ratio of error values ​​corresponding to the M% time points that are higher than the third threshold; a seventh indicator is used to indicate the number or ratio of error values ​​corresponding to the M% time points that are lower than the third threshold; a seventh indicator is used to indicate the number; a seventh indicator is used to indicate the ratio.

[0234] In some embodiments, the one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

[0235] In some embodiments, the error between the predicted value and the measured value is an error value, and the one or more performance indicators include one or more of the following: a ninth indicator, used to indicate the average error value of P cells / services; a tenth indicator, used to indicate the error value of P cells / services; an eleventh indicator, used to indicate the number or percentage of error values ​​of the P cells / services that are higher or lower than a fifth threshold; a twelfth indicator, used to indicate whether the average error value of the P cells / services is higher or lower than a sixth threshold; a thirteenth indicator, used to indicate the average error value of R% cells / services; a fourteenth indicator, used to indicate the error value of R% cells / services; a fifteenth indicator, used to indicate the number or percentage of error values ​​of the R% cells / services that are higher or lower than a seventh threshold; a sixteenth indicator, used to indicate whether the average error value of the R% cells / services is higher or lower than an eighth threshold; a seventeenth indicator, used to indicate a first set and a second set, the first set including Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the second set including multiple The eighteenth indicator indicates the number or ratio of cells / services in the first set that have the same identifier as cells / services in the second set; the nineteenth indicator indicates the first sequence and the second sequence, wherein the first sequence includes the Q1 or Q2% cells with the largest or smallest predicted value among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted value, and the second sequence includes the Q1 or Q2% cells with the largest or smallest measured value among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured value; the twentieth indicator indicates the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; the twenty-first indicator indicates the ratio of cells / services with the largest or smallest measured value in the first set or the first sequence; and the twenty-second indicator indicates the ratio of cells / services with the largest or smallest predicted value in the second set or the second sequence.

[0236] In some embodiments, the P cells satisfy any of the following: the P cells / services are the cells with the largest errors among multiple cells / services; the P cells / services are the cells with the smallest errors among multiple cells / services; the P cells / services are designated; the P cells / services are randomly selected.

[0237] In some embodiments, the first configuration information is used to configure any one of the following: the P cells / services are the P cells / services with the largest error among multiple cells / services; the P cells / services are the P cells / services with the smallest error among multiple cells / services; and the identifier of the specified P cells / services.

[0238] In some embodiments, the R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or, the R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

[0239] In some embodiments, the first configuration information is used to configure: R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or, R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

[0240] In some embodiments, the first configuration information is used to configure one or more of the following: the one or more performance metrics for one or more error values; the one or more performance metrics for the average of one or more error values; the one or more performance metrics for the error values ​​of the R% cells / services; the one or more performance metrics for the error values ​​of the P cells / services; the value of R; the value of P; the fifth threshold; the sixth threshold; the seventh threshold; the eighth threshold; the eleventh indicator is used to indicate the number or percentage of error values ​​of the P cells / services that are higher than the fifth threshold; the eleventh indicator... The first indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; the eleventh indicator is used to indicate the number; the eleventh indicator is used to indicate the percentage; the twelfth indicator is used to indicate that the average error value of the P cells / services is higher than the sixth threshold; the twelfth indicator is used to indicate that the average error value of the P cells / services is lower than the sixth threshold; the twelfth indicator is used to indicate the number; the twelfth indicator is used to indicate the percentage; the eighteenth indicator is used to indicate the number; the eighteenth indicator is used to indicate the percentage; the twentieth indicator is used to indicate the number; the twentieth indicator is used to indicate the percentage.

[0241] In some embodiments, the first configuration information is used to configure one or more of the following: the performance metric is for a channel; the performance metric is for a service of the terminal device; and total duration information is used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

[0242] In some embodiments, the network device 600 is further configured to: receive first information sent by the terminal device; wherein the first information is used to indicate whether the one or more performance indicators meet the performance requirements.

[0243] In some embodiments, the network device 600 is further configured to: receive some or all of the one or more performance metrics sent by the terminal device.

[0244] In some embodiments, the network device 600 is further configured to: receive difference value information sent by the terminal device; wherein the difference value information is used to indicate the difference between the performance metric and the corresponding decision threshold.

[0245] In some embodiments, the first model is an AI / ML model.

[0246] In an optional embodiment, the transmitting unit 610 may be a transceiver 730. The network device 600 may also include a processor 710 and a memory 720, as shown in FIG7.

[0247] Figure 7 is a schematic structural diagram of a communication apparatus according to an embodiment of this application. The dashed lines in Figure 7 indicate that the unit or module is optional. This apparatus 700 can be used to implement the methods described in the above method embodiments. The apparatus 700 can be a chip, a terminal device, or a network device.

[0248] The apparatus 700 may include one or more processors 710. The processor 710 may support the apparatus 700 in implementing the methods described in the preceding method embodiments. The processor 710 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0249] The apparatus 700 may also include one or more memories 720. The memories 720 store a program that can be executed by the processor 710, causing the processor 710 to perform the methods described in the preceding method embodiments. The memories 720 may be independent of the processor 710 or integrated within the processor 710.

[0250] The device 700 may also include a transceiver 730. The processor 710 can communicate with other devices or chips via the transceiver 730. For example, the processor 710 can send and receive data with other devices or chips via the transceiver 730.

[0251] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0252] This application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0253] This application also provides a computer program. This computer program can be applied to the terminal or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0254] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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.

[0259] 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.

[0260] 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.

[0261] In the embodiments of this application, "comprising" can refer to direct inclusion or indirect inclusion. Optionally, "comprising" mentioned in the embodiments of this application can be replaced with "indicating" or "used to determine". For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B".

[0262] 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.

[0263] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0264] 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.

[0265] 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.

[0266] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs) or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0267] 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 technical scope 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 wireless communication method, characterized in that, include: The terminal device receives the first configuration information sent by the network device; The first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, wherein the performance indicators are used to indicate the performance of the predicted values ​​obtained based on the first model, and the first model is deployed on the terminal device.

2. The method according to claim 1, characterized in that, The first configuration information is also used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

3. The method according to claim 2, characterized in that, The first configuration information is also used to configure: If the performance index is greater than or equal to the decision threshold, the performance index is determined to meet the performance requirements; or, If the performance index is less than or equal to the decision threshold, the performance index is determined to meet the performance requirements.

4. The method according to any one of claims 1-3, characterized in that, The one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

5. The method according to claim 4, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The first indicator is used to indicate the error values ​​corresponding to K moments in the first time window; The second indicator is used to indicate the average value of the error values ​​corresponding to the K time points; The third indicator is used to indicate the number or ratio of error values ​​that are higher or lower than the first threshold at the K time points; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher or lower than the second threshold; The fifth indicator is used to indicate the error value corresponding to the M% of moments in the first time window; The sixth indicator is used to indicate the average error value corresponding to M% of the time points in the first time window; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points; The eighth indicator is used to indicate whether the average error value corresponding to the M% time points is higher or lower than the fourth threshold.

6. The method according to claim 5, characterized in that, The first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

7. The method according to claim 5 or 6, characterized in that, The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; or K is specified.

8. The method according to claim 7, characterized in that, The first configuration information is used to configure one of the following: The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; The positions of the K moments within the first time window.

9. The method according to any one of claims 5-8, characterized in that, The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

10. The method according to claim 9, characterized in that, The first configuration information is used to configure: The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

11. The method according to any one of claims 5-10, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance indicators correspond to the error values ​​at the M% time points; The one or more performance metrics correspond to the error values ​​at the K time points; The value of M; The value of K; The first threshold; The second threshold; The third threshold; The fourth threshold; The third indicator is used to indicate the number or percentage of error values ​​that are higher than the first threshold at the K time points; The third indicator is used to indicate the number or percentage of error values ​​that are lower than the first threshold at the K time points; The third indicator is used to indicate quantity; The third indicator is used to indicate the ratio; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher than the second threshold; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is lower than the second threshold; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher than the third threshold at the M% time points; The seventh indicator is used to indicate the number or percentage of error values ​​below the third threshold at the M% time points; The seventh indicator is used to indicate quantity; The seventh indicator is used to indicate the ratio.

12. The method according to any one of claims 1-11, characterized in that, The one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

13. The method according to claim 12, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The ninth indicator is used to indicate the average error value of P cells / services; The tenth indicator is used to indicate the error value of P cells / services; The eleventh indicator is used to indicate the number or ratio of error values ​​in the P cells / services that are higher or lower than the fifth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher or lower than the sixth threshold; The thirteenth indicator is used to indicate the average error value of R% of cells / services; The fourteenth indicator is used to indicate the error value of R% of cells / services; The fifteenth indicator is used to indicate the number or percentage of error values ​​in the R% cells / services that are higher or lower than the seventh threshold; The sixteenth indicator is used to indicate whether the average error value of the R% cells / services is higher or lower than the eighth threshold; The seventeenth indicator is used to indicate the first set and the second set, wherein the first set includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the second set includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services; the eighteenth indicator is used to indicate the number or ratio of cells / services with the same identifier in the first set and cells / services in the second set. The nineteenth indicator is used to indicate the first sequence and the second sequence. The first sequence includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted values. The second sequence includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured values. The twentieth indicator is used to indicate the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; The twenty-first indicator is used to indicate the ratio of cells / services with the largest or smallest measured values ​​contained in the first set or the first sequence; The twenty-second indicator is used to indicate the ratio of cells / services with the largest or smallest predicted values ​​contained in the second set or the second sequence.

14. The method according to claim 13, characterized in that, The P cells satisfy any one of the following: The P cells / services are the cells with the largest errors among multiple cells / services; The P cells / services are the cells with the smallest error among multiple cells / services; The P cells / services are specified; The P cells / services are selected randomly.

15. The method according to claim 14, characterized in that, The first configuration information is used to configure any one of the following: The P cells / services are the P cells / services with the largest errors among multiple cells / services; The P cells / services are the P cells / services with the smallest error among multiple cells / services; The identifiers of the specified P cells / services.

16. The method according to any one of claims 13-15, characterized in that, The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... The R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

17. The method according to claim 16, characterized in that, The first configuration information is used to configure: The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

18. The method according to any one of claims 13-17, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance metrics are for the error values ​​of the R% cells / services; The one or more performance metrics are for the P cell / service error values; The value of R; The value of P; The fifth threshold; The sixth threshold; The seventh threshold; The eighth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are higher than the fifth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; The eleventh indicator is used to indicate quantity; The eleventh indicator is used to indicate the ratio; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher than the sixth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is lower than the sixth threshold; The twelfth indicator is used to indicate quantity; The twelfth indicator is used to indicate the ratio; The eighteenth indicator is used to indicate quantity; The eighteenth indicator is used to indicate ratios. The twentieth indicator is used to indicate quantity; The twentieth indicator is used to indicate the ratio.

19. The method according to any one of claims 1-18, characterized in that, The first configuration information is used to configure one or more of the following: The performance metrics are for the channel; The performance metrics are for the services of the terminal device; Total duration information is used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

20. The method according to any one of claims 1-19, characterized in that, Also includes: The terminal device sends the first information; The first information is used to indicate whether the one or more performance indicators meet the performance requirements.

21. The method according to any one of claims 1-20, characterized in that, Also includes: The terminal device sends some or all of the one or more performance indicators.

22. The method according to any one of claims 1-21, characterized in that, Also includes: The terminal device sends the difference value information; The difference value information is used to indicate the difference between the performance index and the corresponding decision threshold.

23. The method according to any one of claims 1-22, characterized in that, The first model is an artificial intelligence (AI) / machine learning (ML) model.

24. A wireless communication method, characterized in that, include: The network device sends the first configuration information to the terminal device; The first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, wherein the performance indicators are used to indicate the performance of the predicted values ​​obtained based on the first model, and the first model is deployed on the terminal device.

25. The method according to claim 24, characterized in that, The first configuration information is also used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

26. The method according to claim 25, characterized in that, The first configuration information is also used to configure: If the performance index is greater than or equal to the decision threshold, the performance index is determined to meet the performance requirements; or, If the performance index is less than or equal to the decision threshold, the performance index is determined to meet the performance requirements.

27. The method according to any one of claims 24-26, characterized in that, The one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

28. The method according to claim 27, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The first indicator is used to indicate the error values ​​corresponding to K moments in the first time window; The second indicator is used to indicate the average value of the error values ​​corresponding to the K time points; The third indicator is used to indicate the number or ratio of error values ​​that are higher or lower than the first threshold at the K time points; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher or lower than the second threshold; The fifth indicator is used to indicate the error value corresponding to the M% of moments in the first time window; The sixth indicator is used to indicate the average error value corresponding to M% of the time points in the first time window; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points; The eighth indicator is used to indicate whether the average error value corresponding to the M% time points is higher or lower than the fourth threshold.

29. The method according to claim 28, characterized in that, The first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

30. The method according to claim 28 or 29, characterized in that, The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; or K is specified.

31. The method according to claim 30, characterized in that, The first configuration information is used to configure one of the following: The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; The positions of the K moments within the first time window.

32. The method according to any one of claims 28-31, characterized in that, The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

33. The method according to claim 32, characterized in that, The first configuration information is used to configure: The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

34. The method according to any one of claims 28-33, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance indicators correspond to the error values ​​at the M% time points; The one or more performance metrics correspond to the error values ​​at the K time points; The value of M; The value of K; The first threshold; The second threshold; The third threshold; The fourth threshold; The third indicator is used to indicate the number or percentage of error values ​​that are higher than the first threshold at the K time points; The third indicator is used to indicate the number or percentage of error values ​​that are lower than the first threshold at the K time points; The third indicator is used to indicate quantity; The third indicator is used to indicate the ratio; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher than the second threshold; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is lower than the second threshold; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher than the third threshold at the M% time points; The seventh indicator is used to indicate the number or percentage of error values ​​below the third threshold at the M% time points; The seventh indicator is used to indicate quantity; The seventh indicator is used to indicate the ratio.

35. The method according to any one of claims 24-34, characterized in that, The one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

36. The method according to claim 35, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The ninth indicator is used to indicate the average error value of P cells / services; The tenth indicator is used to indicate the error value of P cells / services; The eleventh indicator is used to indicate the number or ratio of error values ​​in the P cells / services that are higher or lower than the fifth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher or lower than the sixth threshold; The thirteenth indicator is used to indicate the average error value of R% of cells / services; The fourteenth indicator is used to indicate the error value of R% of cells / services; The fifteenth indicator is used to indicate the number or percentage of error values ​​in the R% cells / services that are higher or lower than the seventh threshold; The sixteenth indicator is used to indicate whether the average error value of the R% cells / services is higher or lower than the eighth threshold; The seventeenth indicator is used to indicate the first set and the second set, the first set including Q1 cells or Q2% cells with the largest or smallest predicted value among multiple cells / services, and the second set including Q1 cells or Q2% cells with the largest or smallest measured value among multiple cells / services. The eighteenth indicator is used to indicate the number or ratio of cells / services in the first set that have the same identifier as cells / services in the second set; The nineteenth indicator is used to indicate the first sequence and the second sequence. The first sequence includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted values. The second sequence includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured values. The twentieth indicator is used to indicate the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; The twenty-first indicator is used to indicate the ratio of cells / services with the largest or smallest measured values ​​contained in the first set or the first sequence; The twenty-second indicator is used to indicate the ratio of cells / services with the largest or smallest predicted values ​​contained in the second set or the second sequence.

37. The method according to claim 36, characterized in that, The P cells satisfy any one of the following: The P cells / services are the cells with the largest errors among multiple cells / services; The P cells / services are the cells with the smallest error among multiple cells / services; The P cells / services are specified; The P cells / services are selected randomly.

38. The method according to claim 37, characterized in that, The first configuration information is used to configure any one of the following: The P cells / services are the P cells / services with the largest errors among multiple cells / services; The P cells / services are the P cells / services with the smallest error among multiple cells / services; The identifiers of the specified P cells / services.

39. The method according to any one of claims 36-38, characterized in that, The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... The R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

40. The method according to claim 39, characterized in that, The first configuration information is used to configure: The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

41. The method according to any one of claims 36-40, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance metrics are for the error values ​​of the R% cells / services; The one or more performance metrics are for the P cell / service error values; The value of R; The value of P; The fifth threshold; The sixth threshold; The seventh threshold; The eighth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are higher than the fifth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; The eleventh indicator is used to indicate quantity; The eleventh indicator is used to indicate the ratio; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher than the sixth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is lower than the sixth threshold; The twelfth indicator is used to indicate quantity; The twelfth indicator is used to indicate the ratio; The eighteenth indicator is used to indicate quantity; The eighteenth indicator is used to indicate ratios. The twentieth indicator is used to indicate quantity; The twentieth indicator is used to indicate the ratio.

42. The method according to any one of claims 24-41, characterized in that, The first configuration information is used to configure one or more of the following: The performance metrics are for the channel; The performance metrics are for the services of the terminal device; Total duration information is used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

43. The method according to any one of claims 24-42, characterized in that, Also includes: The network device receives the first information sent by the terminal device; The first information is used to indicate whether the one or more performance indicators meet the performance requirements.

44. The method according to any one of claims 24-43, characterized in that, Also includes: The network device receives some or all of the one or more performance metrics sent by the terminal device.

45. The method according to any one of claims 24-44, characterized in that, Also includes: The network device receives the difference value information sent by the terminal device; The difference value information is used to indicate the difference between the performance index and the corresponding decision threshold.

46. ​​The method according to any one of claims 24-45, characterized in that, The first model is an artificial intelligence (AI) / machine learning (ML) model.

47. A terminal device, characterized in that, include: The receiving unit is used to receive the first configuration information sent by the network device; The first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, wherein the performance indicators are used to indicate the performance of the predicted values ​​obtained based on the first model, and the first model is deployed on the terminal device.

48. The terminal device according to claim 47, characterized in that, The first configuration information is also used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

49. The terminal device according to claim 48, characterized in that, The first configuration information is also used to configure: If the performance index is greater than or equal to the decision threshold, the performance index is determined to meet the performance requirements; or, If the performance index is less than or equal to the decision threshold, the performance index is determined to meet the performance requirements.

50. The terminal device according to any one of claims 47-49, characterized in that, The one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

51. The terminal device according to claim 50, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The first indicator is used to indicate the error values ​​corresponding to K moments in the first time window; The second indicator is used to indicate the average value of the error values ​​corresponding to the K time points; The third indicator is used to indicate the number or ratio of error values ​​that are higher or lower than the first threshold at the K time points; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher or lower than the second threshold; The fifth indicator is used to indicate the error value corresponding to the M% of moments in the first time window; The sixth indicator is used to indicate the average error value corresponding to M% of the time points in the first time window; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points; The eighth indicator is used to indicate whether the average error value corresponding to the M% time points is higher or lower than the fourth threshold.

52. The terminal device according to claim 51, characterized in that, The first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

53. The terminal device according to claim 51 or 52, characterized in that, The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; or K is specified.

54. The terminal device according to claim 53, characterized in that, The first configuration information is used to configure one of the following: The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; The positions of the K moments within the first time window.

55. The terminal device according to any one of claims 51-54, characterized in that, The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

56. The terminal device according to claim 55, characterized in that, The first configuration information is used to configure: The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

57. The terminal device according to any one of claims 51-56, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance indicators correspond to the error values ​​at the M% time points; The one or more performance metrics correspond to the error values ​​at the K time points; The value of M; The value of K; The first threshold; The second threshold; The third threshold; The fourth threshold; The third indicator is used to indicate the number or percentage of error values ​​that are higher than the first threshold at the K time points; The third indicator is used to indicate the number or percentage of error values ​​that are lower than the first threshold at the K time points; The third indicator is used to indicate quantity; The third indicator is used to indicate the ratio; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher than the second threshold; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is lower than the second threshold; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher than the third threshold at the M% time points; The seventh indicator is used to indicate the number or percentage of error values ​​below the third threshold at the M% time points; The seventh indicator is used to indicate quantity; The seventh indicator is used to indicate the ratio.

58. The terminal device according to any one of claims 47-57, characterized in that, The one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

59. The terminal device according to claim 58, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The ninth indicator is used to indicate the average error value of P cells / services; The tenth indicator is used to indicate the error value of P cells / services; The eleventh indicator is used to indicate the number or ratio of error values ​​in the P cells / services that are higher or lower than the fifth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher or lower than the sixth threshold; The thirteenth indicator is used to indicate the average error value of R% of cells / services; The fourteenth indicator is used to indicate the error value of R% of cells / services; The fifteenth indicator is used to indicate the number or percentage of error values ​​in the R% cells / services that are higher or lower than the seventh threshold; The sixteenth indicator is used to indicate whether the average error value of the R% cells / services is higher or lower than the eighth threshold; The seventeenth indicator is used to indicate the first set and the second set, wherein the first set includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the second set includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services; the eighteenth indicator is used to indicate the number or ratio of cells / services with the same identifier in the first set and cells / services in the second set. The nineteenth indicator is used to indicate the first sequence and the second sequence. The first sequence includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted values. The second sequence includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured values. The twentieth indicator is used to indicate the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; The twenty-first indicator is used to indicate the ratio of cells / services with the largest or smallest measured values ​​contained in the first set or the first sequence; The twenty-second indicator is used to indicate the ratio of cells / services with the largest or smallest predicted values ​​contained in the second set or the second sequence.

60. The terminal device according to claim 59, characterized in that, The P cells satisfy any one of the following: The P cells / services are the cells with the largest errors among multiple cells / services; The P cells / services are the cells with the smallest error among multiple cells / services; The P cells / services are specified; The P cells / services are selected randomly.

61. The terminal device according to claim 60, characterized in that, The first configuration information is used to configure any one of the following: The P cells / services are the P cells / services with the largest errors among multiple cells / services; The P cells / services are the P cells / services with the smallest error among multiple cells / services; The identifiers of the specified P cells / services.

62. The terminal device according to any one of claims 59-61, characterized in that, The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... The R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

63. The terminal device according to claim 62, characterized in that, The first configuration information is used to configure: The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

64. The terminal device according to any one of claims 59-63, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance metrics are for the error values ​​of the R% cells / services; The one or more performance metrics are for the P cell / service error values; The value of R; The value of P; The fifth threshold; The sixth threshold; The seventh threshold; The eighth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are higher than the fifth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; The eleventh indicator is used to indicate quantity; The eleventh indicator is used to indicate the ratio; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher than the sixth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is lower than the sixth threshold; The twelfth indicator is used to indicate quantity; The twelfth indicator is used to indicate the ratio; The eighteenth indicator is used to indicate quantity; The eighteenth indicator is used to indicate ratios. The twentieth indicator is used to indicate quantity; The twentieth indicator is used to indicate the ratio.

65. The terminal device according to any one of claims 47-64, characterized in that, The first configuration information is used to configure one or more of the following: The performance metrics are for the channel; The performance metrics are for the services of the terminal device; Total duration information is used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

66. The terminal device according to any one of claims 47-65, characterized in that, The terminal device is also used for: Send the first message; The first information is used to indicate whether the one or more performance indicators meet the performance requirements.

67. The terminal device according to any one of claims 47-66, characterized in that, The terminal device is also used for: Send some or all of the aforementioned performance metrics.

68. The terminal device according to any one of claims 47-67, characterized in that, The terminal device is also used for: Send difference value information; The difference value information is used to indicate the difference between the performance index and the corresponding decision threshold.

69. The terminal device according to any one of claims 47-68, characterized in that, The first model is an artificial intelligence (AI) / machine learning (ML) model.

70. A network device, characterized in that, include: The sending unit is used to send first configuration information to the terminal device; The first configuration information is used to configure the terminal device to monitor one or more performance indicators of the first model, wherein the performance indicators are used to indicate the performance of the predicted values ​​obtained based on the first model, and the first model is deployed on the terminal device.

71. The network device according to claim 70, characterized in that, The first configuration information is also used to configure the decision threshold corresponding to the performance indicator, and the decision threshold is used to determine whether the corresponding performance indicator meets the performance requirements.

72. The network device according to claim 71, characterized in that, The first configuration information is also used to configure: If the performance index is greater than or equal to the decision threshold, the performance index is determined to meet the performance requirements; or, If the performance index is less than or equal to the decision threshold, the performance index is determined to meet the performance requirements.

73. The network device according to any one of claims 70-72, characterized in that, The one or more performance metrics include performance metrics for a single cell and / or a single service, and the predicted values ​​include predicted values ​​for the single cell and / or the single service at one or more time points.

74. The network device according to claim 73, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The first indicator is used to indicate the error values ​​corresponding to K moments in the first time window; The second indicator is used to indicate the average value of the error values ​​corresponding to the K time points; The third indicator is used to indicate the number or ratio of error values ​​that are higher or lower than the first threshold at the K time points; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher or lower than the second threshold; The fifth indicator is used to indicate the error value corresponding to the M% of moments in the first time window; The sixth indicator is used to indicate the average error value corresponding to M% of the time points in the first time window; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher or lower than the third threshold among the M% of time points; The eighth indicator is used to indicate whether the average error value corresponding to the M% time points is higher or lower than the fourth threshold.

75. The network device according to claim 74, characterized in that, The first model is used to predict the predicted value corresponding to one or more times in the prediction window based on the observation window, wherein the first time window is the prediction window.

76. The network device according to claim 74 or 75, characterized in that, The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; or K is specified.

77. The network device according to claim 76, characterized in that, The first configuration information is used to configure one of the following: The K time points are the K time points with the largest error values ​​within the first time window; The K time points are the K time points with the smallest error values ​​within the first time window; The positions of the K moments within the first time window.

78. The network device according to any one of claims 74-77, characterized in that, The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

79. The network device according to claim 78, characterized in that, The first configuration information is used to configure: The M% of time points are the M% of time points with the largest error values ​​within the first time window; or... The M% moments are the M% moments with the smallest error values ​​within the first time window.

80. The network device according to any one of claims 74-79, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance indicators correspond to the error values ​​at the M% time points; The one or more performance metrics correspond to the error values ​​at the K time points; The value of M; The value of K; The first threshold; The second threshold; The third threshold; The fourth threshold; The third indicator is used to indicate the number or percentage of error values ​​that are higher than the first threshold at the K time points; The third indicator is used to indicate the number or percentage of error values ​​that are lower than the first threshold at the K time points; The third indicator is used to indicate quantity; The third indicator is used to indicate the ratio; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is higher than the second threshold; The fourth indicator is used to indicate whether the average error value corresponding to the K time points is lower than the second threshold; The seventh indicator is used to indicate the number or percentage of error values ​​that are higher than the third threshold at the M% time points; The seventh indicator is used to indicate the number or percentage of error values ​​below the third threshold at the M% time points; The seventh indicator is used to indicate quantity; The seventh indicator is used to indicate the ratio.

81. The network device according to any one of claims 70-80, characterized in that, The one or more performance metrics include performance metrics for multiple cells and / or performance metrics for multiple services, and the predicted values ​​include multiple predicted values ​​for the multiple cells and / or multiple predicted values ​​for the multiple services.

82. The network device according to claim 71, characterized in that, The error between the predicted value and the measured value is the error value, and the one or more performance indicators include one or more of the following: The ninth indicator is used to indicate the average error value of P cells / services; The tenth indicator is used to indicate the error value of P cells / services; The eleventh indicator is used to indicate the number or ratio of error values ​​in the P cells / services that are higher or lower than the fifth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher or lower than the sixth threshold; The thirteenth indicator is used to indicate the average error value of R% of cells / services; The fourteenth indicator is used to indicate the error value of R% of cells / services; The fifteenth indicator is used to indicate the number or percentage of error values ​​in the R% cells / services that are higher or lower than the seventh threshold; The sixteenth indicator is used to indicate whether the average error value of the R% cells / services is higher or lower than the eighth threshold; The seventeenth indicator is used to indicate the first set and the second set, the first set including Q1 cells or Q2% cells with the largest or smallest predicted value among multiple cells / services, and the second set including Q1 cells or Q2% cells with the largest or smallest measured value among multiple cells / services. The eighteenth indicator is used to indicate the number or ratio of cells / services in the first set that have the same identifier as cells / services in the second set; The nineteenth indicator is used to indicate the first sequence and the second sequence. The first sequence includes Q1 cells or Q2% cells with the largest or smallest predicted values ​​among multiple cells / services, and the multiple cells / services in the first sequence are sorted according to the size of the predicted values. The second sequence includes Q1 cells or Q2% cells with the largest or smallest measured values ​​among multiple cells / services, and the multiple cells / services in the second sequence are sorted according to the size of the measured values. The twentieth indicator is used to indicate the number or ratio of cells / services in the first sequence that have the same identifier and location as cells / services in the second sequence; The twenty-first indicator is used to indicate the ratio of cells / services with the largest or smallest measured values ​​contained in the first set or the first sequence; The twenty-second indicator is used to indicate the ratio of cells / services with the largest or smallest predicted values ​​contained in the second set or the second sequence.

83. The network device according to claim 82, characterized in that, The P cells satisfy any one of the following: The P cells / services are the cells with the largest errors among multiple cells / services; The P cells / services are the cells with the smallest error among multiple cells / services; The P cells / services are specified; The P cells / services are selected randomly.

84. The network device according to claim 83, characterized in that, The first configuration information is used to configure any one of the following: The P cells / services are the P cells / services with the largest errors among multiple cells / services; The P cells / services are the P cells / services with the smallest error among multiple cells / services; The identifiers of the specified P cells / services.

85. The network device according to any one of claims 82-84, characterized in that, The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... The R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

86. The network device according to claim 85, characterized in that, The first configuration information is used to configure: The R% cells / services are the R% cells with the largest error values ​​among the plurality of cells / services; or... R% cells / services are the R% cells with the smallest error values ​​among the plurality of cells / services.

87. The network device according to any one of claims 82-86, characterized in that, The first configuration information is used to configure one or more of the following: The one or more performance metrics are for one or more error values; The one or more performance metrics are averages of one or more error values; The one or more performance metrics are for the error values ​​of the R% cells / services; The one or more performance metrics are for the P cell / service error values; The value of R; The value of P; The fifth threshold; The sixth threshold; The seventh threshold; The eighth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are higher than the fifth threshold; The eleventh indicator is used to indicate the number or percentage of error values ​​in the P cells / services that are lower than the fifth threshold; The eleventh indicator is used to indicate quantity; The eleventh indicator is used to indicate the ratio; The twelfth indicator is used to indicate whether the average error value of the P cells / services is higher than the sixth threshold; The twelfth indicator is used to indicate whether the average error value of the P cells / services is lower than the sixth threshold; The twelfth indicator is used to indicate quantity; The twelfth indicator is used to indicate the ratio; The eighteenth indicator is used to indicate quantity; The eighteenth indicator is used to indicate ratios. The twentieth indicator is used to indicate quantity; The twentieth indicator is used to indicate the ratio.

88. The network device according to any one of claims 70-87, characterized in that, The first configuration information is used to configure one or more of the following: The performance metrics are for the channel; The performance metrics are for the services of the terminal device; Total duration information is used to indicate the total duration for which the terminal device monitors the one or more performance metrics.

89. The network device according to any one of claims 70-88, characterized in that, The network device is also used for: Receive the first information sent by the terminal device; The first information is used to indicate whether the one or more performance indicators meet the performance requirements.

90. The network device according to any one of claims 70-89, characterized in that, The network device is also used for: Receive some or all of the one or more performance indicators sent by the terminal device.

91. The network device according to any one of claims 70-90, characterized in that, The network device is also used for: Receive the difference value information sent by the terminal device; The difference value information is used to indicate the difference between the performance index and the corresponding decision threshold.

92. The network device according to any one of claims 70-91, characterized in that, The first model is an artificial intelligence (AI) / machine learning (ML) model.

93. A terminal device, characterized in that, It includes a memory and a processor, the memory being used to store a program, and the processor being used to invoke the program in the memory to cause the terminal device to perform the method as described in any one of claims 1-23.

94. A network device, characterized in that, It includes a memory and a processor, the memory being used to store a program, and the processor being used to invoke the program in the memory to cause the network device to perform the method as described in any one of claims 24-46.

95. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the device to perform the method as described in any one of claims 1-46.

96. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-46.

97. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-46.

98. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-46.

99. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-46.

Images