Wireless communication methods, terminal devices and network devices

Abstract

Provided are wireless communication methods, terminal devices and network devices. A method comprises: a terminal device transmits first information to a network device, the first information comprising a performance monitoring result for a first model, and the first model being used for beam measurement result prediction, wherein the first information comprises any one of the following information: one or multiple pieces of first indication information, and one of the one or multiple pieces of first indication information being used for indicating whether a prediction result is valid; second indication information, the second indication information being used for indicating first ratio information or being used for indicating a ratio range to which the first ratio information belongs, and the first ratio information comprising the ratio of the number of predictions with valid prediction results to the total number of predictions or comprising the ratio of the number of predictions with invalid prediction results to the total number of predictions; and information used for calculating second ratio information, the second ratio information comprising the ratio of the number of predictions with valid prediction results to the total number of predictions or comprising the ratio of the number of predictions with invalid prediction results to the total number of predictions.

Description

Wireless communication method, terminal device and network device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a wireless communication method, terminal equipment, and network equipment. Background Art

[0002] With the advancement of communication technology, artificial intelligence (AI) models have gradually been introduced into wireless communication systems to replace traditional non-AI methods. However, there is currently no effective solution for monitoring the performance of AI models to ensure the reliability of wireless communication systems.

[0003] Summary of the Invention

[0004] The present application provides a wireless communication method, terminal device, and network device. The following introduces various aspects of the present application.

[0005] In a first aspect, a wireless communication method is provided, including: a terminal device sends first information to a network device, the first information including a performance monitoring result for a first model, the first model being used to predict a beam measurement result, wherein the first information includes any one of the following information: one or more first indication information, one first indication information among the one or more first indication information being used to indicate whether a prediction result is valid; second indication information, the second indication information being used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions; information used to calculate the second proportion information, the second proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions.

[0006] In a second aspect, a wireless communication method is provided, including: a network device receives first information sent by a terminal device, the first information including performance monitoring results for a first model, the first model being used to predict beam measurement results, wherein the first information includes any one of the following information: one or more first indication information, one first indication information among the one or more first indication information being used to indicate whether a prediction result is valid; second indication information, the second indication information being used to indicate first proportion information or to indicate the proportion interval to which the first proportion information belongs, the first proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions; information used to calculate the second proportion information, the second proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions.

[0007] According to a third aspect, a terminal device is provided, including: a sending unit for sending first information to a network device, the first information including a performance monitoring result for a first model, the first model being used to predict a beam measurement result, wherein the first information includes any one of the following information: one or more first indication information, one first indication information among the one or more first indication information being used to indicate whether a prediction result is valid; second indication information, the second indication information being used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions; information for calculating the second proportion information, the second proportion information including the proportion of the number of valid prediction results to the total number of predictions, or the proportion of the number of invalid prediction results to the total number of predictions.

[0008] In a fourth aspect, a network device is provided, including: a receiving unit for receiving first information sent by a terminal device, the first information including performance monitoring results for a first model, the first model being used to predict beam measurement results, wherein the first information includes any one of the following information: one or more first indication information, one first indication information among the one or more first indication information being used to indicate whether a prediction result is valid; second indication information, the second indication information being used to indicate first proportion information or to indicate the proportion interval to which the first proportion information belongs, the first proportion information including the proportion of the number of valid prediction results to the total prediction times, or the proportion of the number of invalid prediction results to the total prediction times; information for calculating the second proportion information, the second proportion information including the proportion of the number of valid prediction results to the total prediction times, or the proportion of the number of invalid prediction results to the total prediction times.

[0009] In a fifth aspect, a terminal device is provided, comprising a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the method of the first aspect.

[0010] In a sixth aspect, a network device is provided, comprising a processor, a memory, and a transceiver, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the network device executes part or all of the steps in the method of the second aspect.

[0011] In a seventh aspect, a device is provided, comprising a processor for calling a program from a memory so that the device executes the method as described in the first aspect or the second aspect.

[0012] In an eighth aspect, a chip is provided, comprising a processor for calling a program from a memory so that a device equipped with the chip executes the method described in the first aspect or the second aspect.

[0013] In a ninth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0014] In a tenth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0015] In an eleventh aspect, a computer program is provided, wherein the computer program enables a computer to execute the method as described in the first aspect or the second aspect.

[0016] This application predicts the beam measurement results based on the AI ​​model (first model), and then the terminal device sends the performance monitoring results (first information) of the first model to the network device to monitor whether the first model is in a good working state. The first information may include information related to the validity of the prediction results. By sending information related to the validity of the prediction results to the network device, the network device can clarify the performance of the first model, thereby ensuring the reliability of the wireless communication system after the introduction of the AI ​​model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a system architecture diagram of a wireless communication system to which an embodiment of the present application may be applied.

[0018] FIG2 is a flow chart of a wireless communication method according to an embodiment of the present application.

[0019] FIG3 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application.

[0020] FIG4 is a schematic diagram of the structure of a network device provided in an embodiment of the present application.

[0021] FIG5 is a schematic structural diagram of a device to which an embodiment of the present application can be applied. DETAILED DESCRIPTION

[0022] The technical solution in this application will be described below with reference to the accompanying drawings.

[0023] Figure 1 illustrates a wireless communication system 100 used in an embodiment of the present application. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0024] FIG1 exemplarily shows a network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0025] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0026] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0027] The terminal device in the embodiments of the present application may also be referred to as a terminal device, 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 may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects, and machines, such as a handheld device or a vehicle-mounted device with a wireless connection function. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, 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 a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the terminal device can be used to act as a base station. For example, the terminal device can act as a scheduling entity that provides sidelink signals between terminal devices in V2X or D2D. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through a base station.

[0028] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station MeNB, secondary station 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. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof.

[0029] The foregoing article describes in detail a wireless communication system to which the embodiments of the present application can be applied. The air interface (Uu interface) system is an important component of the wireless communication system. With the development of technology, the industry has begun to study the application of AI models in air interface systems (such as 5G / 6G air interface systems). The study believes that for certain functions (functionality) of the air interface, the processing solution based on the AI ​​model (referred to as the AI ​​processing solution) may achieve certain performance gains compared with the traditional processing solution (i.e., the non-AI processing solution).

[0030] However, AI models do not always work well. For example, due to changes in environmental, configuration and other factors, the operating performance of AI models may decline significantly. To address this issue, it is necessary to introduce a model monitoring process, which is mainly used to monitor whether the model can work well and assist decision-makers (such as network equipment) to promptly judge the operation status of the model, so as to make timely management decisions based on the model monitoring results. In some embodiments, the AI ​​model can also be replaced by an AI function, and the two can be used interchangeably if there is no conflict.

[0031] However, existing air interface communication technologies lack standardized AI-enabled technologies, and therefore lack AI model monitoring (or surveillance) mechanisms. On the other hand, predicting measurement results, a key area of ​​integration between AI and communication technologies, holds promise for standardization and application. However, the industry remains concerned about how to effectively maintain AI models (i.e., ensuring the robustness of communication systems when using AI models). Existing communication technologies lack a suitable mechanism to address these concerns, hindering the commercialization of AI technology.

[0032] Based on this, an embodiment of the present application provides a wireless communication method that uses a first model to predict beam measurement results, and a terminal device sends the performance monitoring results to a network device, and specifically defines a method for sending the performance monitoring results. The following provides a detailed example of this embodiment of the application.

[0033] FIG2 is a flow chart of a wireless communication method according to an embodiment of the present application. The method of FIG2 can be performed by a terminal device and a network device. The terminal device can be, for example, the terminal device 120 mentioned above, and the network device can be, for example, the network device 110 mentioned above.

[0034] Referring to Figure 2, in step S210, the terminal device sends first information to the network device, where the first information includes a performance monitoring result for the first model. The first model mentioned here can be any model for predicting beam measurement results. Exemplarily, the first model can be an AI model or an ML model. The first information can also be referred to as (model) performance monitoring result information or (model) performance monitoring report.

[0035] The terminal device can obtain the performance monitoring results by monitoring the operation process of the first model. In other words, the terminal device can obtain the performance monitoring results by monitoring the operation process of the first function (the function of the first model). The first function can be an AI function or an ML function. By monitoring the first model and sending the performance monitoring results of the first model to the network device in a timely manner, the occurrence of a long-term communication performance degradation scenario caused by poor operation of the AI ​​function can be avoided. In other words, the operation of the AI ​​function can be effectively supervised through the performance monitoring mechanism, and timely countermeasures can be taken when it is determined that the AI ​​function is not operating well.

[0036] The first model is used to predict the beam measurement result, and the beam measurement result prediction may include performing beam measurement result prediction for the beams of one or more cells. The one or more cells include a serving cell of the terminal device and / or at least one neighboring cell.

[0037] In some implementations, one or more cells include a service cell (or one or more cells only include a service cell), and the first information only includes the performance monitoring results associated with the service cell. If one or more cells include a service cell, the terminal device may only predict the beam measurement results for the beam of the service cell, without predicting the beam measurement results for the beam of the neighboring cell. Alternatively, if one or more cells include a service cell, the terminal device may predict the beam measurement results for both the beam of the service cell and the beam of the neighboring cell. In this case, although the terminal device predicts the beam measurement results for the beam of the neighboring cell, the terminal device only sends the performance monitoring results associated with the service cell to the network device. For example, the terminal device performs beam measurement result prediction on both the service cell and the neighboring cell, but the protocol stipulates that the performance monitoring process only needs to monitor the service cell. Therefore, the performance monitoring results reported by the terminal only include the performance monitoring results associated with the service cell. Since there is no need to report the performance monitoring results associated with the neighboring cell, signaling overhead can be saved.

[0038] In some implementations, one or more cells include neighboring cells (or one or more cells only include neighboring cells), and the first information only includes performance monitoring results associated with neighboring cells. If one or more cells include neighboring cells, the terminal device can only predict the beam measurement results of the neighboring cells, but not the beam measurement results of the serving cell. Alternatively, if one or more cells include neighboring cells, the terminal device can predict the beam measurement results of both the serving cell and the neighboring cell. In this case, although the terminal device predicts the beam measurement results of the serving cell, the terminal device only sends the performance monitoring results associated with the neighboring cells to the network device. For example, the terminal device performs beam measurement result prediction on both the serving cell and the neighboring cell, but the protocol stipulates that the performance monitoring process only needs to monitor the neighboring cells. Therefore, the performance monitoring results reported by the terminal only include the performance monitoring results associated with the neighboring cells. Since there is no need to report the performance monitoring results associated with the serving cell, signaling overhead can be saved.

[0039] In some implementations, one or more cells may include both a serving cell and a neighboring cell, and the first information may include performance monitoring results associated with the serving cell and the neighboring cell. If one or more cells include both a serving cell and a neighboring cell, the terminal device may perform beam measurement result prediction on both the serving cell's beam and the neighboring cell's beam. In this case, the terminal device may send the performance monitoring results associated with the serving cell and the neighboring cell to the network device. The terminal device monitors the beam measurement result prediction behavior of both the serving cell and the neighboring cell, so the performance monitoring behavior under this method is optimal.

[0040] The embodiment of the present application does not specifically limit the content of the first information. The first information may include any of the following information: one or more first indication information, second indication information, and information used to calculate the second ratio information. The content of the first information is described in detail below.

[0041] In some implementations, the first information may include one or more first indication information, and one of the one or more first indication information is used to indicate whether a prediction result is valid. It can be understood that for each prediction behavior of the first model, a first indication information will be associated to indicate whether the prediction result is valid. The behavior of the terminal device using the first model to predict the beam measurement result is called a prediction behavior. This application does not specifically limit the content of the first indication information, as long as it can indicate the validity of a prediction result. For example, the first indication information can be represented by bits to indicate the validity of the prediction behavior.

[0042] Taking the example of using bits to represent the first indication information, each prediction action is associated with a corresponding bit, used to indicate whether the prediction result obtained from that prediction action is valid. In other words, if the terminal device performs N beam measurement result prediction actions, N bits can be used to indicate the validity of N prediction results, with each bit being associated with each of the N prediction results. The value of a bit is used to indicate whether the prediction result associated with that bit is valid.

[0043] As an example, a bit may take the value of "0" or "1". For example, "1" may be used to indicate that the prediction result is valid, and "0" may be used to indicate that the prediction result is invalid. Alternatively, "0" may be used to indicate that the prediction result is valid, and "1" may be used to indicate that the prediction result is invalid. This application does not make any specific limitations on this.

[0044] For example, assuming that the first information includes three pieces of first indication information, each of which is represented by three bits to indicate the validity of three prediction results. If the value of these three bits is "101," and these three bits correspond to prediction result 1, prediction result 2, and prediction result 3, respectively, and assuming that "1" indicates that the prediction result is valid and "0" indicates that the prediction result is invalid, then "101" indicates that prediction result 1 is valid, prediction result 2 is invalid, and prediction result 3 is valid. If "1" indicates that the prediction result is invalid and "0" indicates that the prediction result is valid, then "101" indicates that prediction result 1 is invalid, prediction result 2 is valid, and prediction result 3 is invalid.

[0045] This application does not specifically limit the order in which bits are associated with prediction results. As an example, the order in which bits are associated with prediction results can be determined based on the chronological order in which they occur. For example, still taking the value of the three bits as "101" as an example, for prediction result 1, prediction result 2, and prediction result 3, the order determined by the terminal device is: prediction result 1 → prediction result 2 → prediction result 3, or prediction result 3 → prediction result 2 → prediction result 1.

[0046] As another example, the order in which bits are associated with prediction results can be determined based on the validity of the prediction results. For example, the first few bits in the bit list are used to indicate a valid prediction result, and the last few bits are used to indicate an invalid prediction result. For another example, the first few bits in the bit list are used to indicate an invalid prediction result, and the last few bits are used to indicate a valid prediction result.

[0047] The prediction result mentioned in the embodiments of the present application may refer to the prediction result obtained after performing a beam measurement result prediction behavior on the beam. In some embodiments, the prediction result may also be referred to as a prediction behavior. A prediction result may correspond to a prediction behavior, or a prediction result may be obtained through a prediction behavior.

[0048] In embodiments of the present application, the validity of a prediction result may be determined each time a predicted beam measurement result is obtained and an actual beam measurement result corresponding to the predicted beam is obtained. Alternatively, the validity of the prediction result may be determined after multiple predicted beam measurement results and actual beam measurement results corresponding to the multiple predicted beams are obtained. As an example, a terminal device may determine the validity of each prediction result after obtaining n predicted beam measurement results and actual beam measurement results corresponding to the n predicted beams, where n is a positive integer.

[0049] In some implementations, the first information may include second indication information. The second indication information may be used to indicate the first proportion information or to indicate the proportion interval to which the first proportion information belongs. The first proportion information may include the proportion of the number of valid prediction results to the total number of predictions (hereinafter referred to as the effective rate of the prediction results), or the first proportion information may include the proportion of the number of invalid prediction results to the total number of predictions (hereinafter referred to as the ineffective rate of the prediction results).

[0050] In some implementations, the second indication information can directly indicate the first ratio information, so that the network device can directly obtain the first ratio information, thereby determining the effectiveness or inefficiency of the prediction result before the terminal device sends the first information. This indication method is relatively simple.

[0051] In some implementations, the second indication information may be used to indicate the scale interval to which the first scale information belongs. If the second indication information can be used to indicate the scale interval to which the first scale information belongs, the terminal device may determine a first association relationship, the first association relationship including a correspondence between values ​​of the second indication information and the scale interval, and determine the scale interval to which the first scale information belongs based on the first association relationship. In other words, the terminal device may determine the second indication information based on the first association relationship.

[0052] Taking the use of bits to represent the second indication information as an example, a value of the second indication information can correspond to a proportional interval, or in other words, the value of the second indication information and the proportional interval have a one-to-one correspondence. The terminal device can determine the value of the second indication information based on the proportional interval to which the first proportional information belongs.

[0053] Taking the example of the second indication information being represented by two bits, the values ​​of the second indication information can be: "00", "01", "10", and "11", and the proportion intervals can include: 0-25%, 25%-50%, 50%-75%, and 75%-100%. The first association relationship can be expressed as follows: the value "00" is associated with the interval 0-25%, the value "01" is associated with the interval 25%-50%, the value "10" is associated with the interval 50%-75%, and the value "11" is associated with the interval 75%-100%. If the value of the second indication information is "00", it means that as of the time the first information is sent, the effectiveness or inefficiency of the prediction result is in the range of 0-25%. If the value of the second indication information is "01", it means that before the first information is sent, the effectiveness or inefficiency of the prediction result is in the range of 25% to 50%; if the value of the second indication information is "10", it means that before the first information is sent, the effectiveness or inefficiency of the prediction result is in the range of 50% to 75%; if the value of the second indication information is "11", it means that before the first information is sent, the effectiveness or inefficiency of the prediction result is in the range of 75% to 100%.

[0054] The network device may determine the first association relationship and, based on the first association relationship, determine the ratio interval to which the first ratio information belongs. Alternatively, the network device may determine the ratio interval to which the first ratio information belongs based on the value of the second indication information and the first association relationship.

[0055] For example, if the value of the second indication information received by the network device is "00", then according to the first association relationship described above, the network device can determine that the effectiveness or inefficiency of the prediction result is in the range of 0% to 25%. For another example, if the value of the second indication information received by the network device is "01", then according to the first association relationship described above, the network device can determine that the effectiveness or inefficiency of the prediction result is in the range of 25% to 50%. For another example, if the value of the second indication information received by the network device is "10", then according to the first association relationship described above, the network device can determine that the effectiveness or inefficiency of the prediction result is in the range of 50% to 75%. For another example, if the value of the second indication information received by the network device is "11", then according to the first association relationship described above, the network device can determine that the effectiveness or inefficiency of the prediction result is in the range of 75% to 100%.

[0056] The above description is based on the example of using 2 bits for the second indication information, and the embodiments of the present application are not limited thereto. For example, the second indication information can be represented by 1 bit, or the second indication information can be represented by 3 bits or more.

[0057] The above ratio intervals are only examples, and the embodiments of the present application may also use a larger number of ratio intervals or a smaller number of ratio intervals.

[0058] The first association described above is merely an example, and the embodiments of the present application are not limited thereto. For example, the value "00" is associated with the interval 75% to 100%, the value "01" is associated with the interval 50% to 75%, the value "10" is associated with the interval 25% to 50%, and the value "11" is associated with the interval 0% to 25%.

[0059] The first association relationship may be an association relationship agreed upon in a protocol, or may be an association relationship configured by a network device for a terminal device.

[0060] In some implementations, the first information may include information used to calculate second ratio information, where the second ratio information includes the ratio of the number of valid prediction results to the total number of predictions, or the ratio of the number of invalid prediction results to the total number of predictions, wherein the information used to calculate the second ratio information includes the number of valid prediction results and the number of invalid prediction results; or the number of valid prediction results and the total number of predictions; or the number of invalid prediction results and the total number of predictions. If the second ratio information includes the ratio of the number of valid prediction results to the total number of predictions, then the information used to calculate the second ratio information includes the number of valid prediction results and the number of invalid prediction results; or the number of valid prediction results and the total number of predictions. If the second ratio information includes the ratio of the number of invalid prediction results to the total number of predictions, then the information used to calculate the second ratio information includes the number of valid prediction results and the number of invalid prediction results; or the number of invalid prediction results and the total number of predictions. Including the information used to calculate the second ratio information in the first information is simpler than directly reporting the second ratio information because the possible decimal places in the second ratio information do not need to be quantized. It is also more accurate than reporting the ratio interval to which the second ratio information belongs, because reporting the ratio interval method itself has systematic errors.

[0061] Optionally, if the first information includes performance monitoring results of beam prediction results for one or more cells, the first information also includes cell identification information of one or more cells, and the cell identification information is represented by frequency and physical cell identifier (PCI) information or by serving cell index or by global cell global identity (CGI) information.

[0062] The validity of the prediction result may be related to one or more of the following information: the predicted beam measurement result; the actual beam measurement result; the beam order determined based on the predicted beam measurement result; the beam set determined based on the predicted beam measurement result; the beam order determined based on the actual beam measurement result; and the beam set determined based on the actual beam measurement result. The following examples illustrate the above situations.

[0063] In some implementations, the validity of the prediction result is related to the absolute value of the difference between the predicted beam measurement result and the actual beam measurement result, or in other words, the validity of the prediction result can be determined based on the absolute value of the difference between the predicted beam measurement result and the actual beam measurement result. The absolute value of the difference between the predicted beam measurement result and the actual beam measurement result corresponding to the same beam can reflect the accuracy of the predicted beam measurement result. The smaller the absolute value of the difference between the predicted beam measurement result and the actual beam measurement result, the higher the accuracy of the predicted beam measurement result, and the larger the absolute value of the difference between the predicted beam measurement result and the actual beam measurement result, the lower the accuracy of the predicted beam measurement result. Determining the predicted beam measurement result in the above manner can ensure that the first model running on the terminal device is in a high-precision working state.

[0064] In some implementations, the validity of the prediction result is related to a beam order determined based on the predicted beam measurement result, or in other words, the validity of the prediction result can be determined based on the beam order determined based on the predicted beam measurement result. For example, the beam order determined based on the predicted beam measurement result can include determining the beam order in descending order of the predicted beam measurement result, or determining the beam order in descending order of the predicted beam measurement result.

[0065] In some implementations, the validity of the prediction result is related to the beam set determined based on the predicted beam measurement result and the beam set determined based on the actual beam measurement result, or in other words, the validity of the prediction result can be determined based on the beam set determined based on the predicted beam measurement result and the beam set determined based on the actual beam measurement result. For example, the beam set determined based on the predicted beam measurement result can include determining the beam set after filtering according to the predicted beam measurement result from high to low, or determining the beam set after filtering according to the predicted beam measurement result from low to high; the beam set determined based on the actual beam measurement result can include determining the beam set after filtering according to the actual beam measurement result from high to low, or determining the beam set after filtering according to the actual beam measurement result from low to high.

[0066] In some implementations, the validity of the prediction result is related to the beam ranking determined based on the predicted beam measurement result and the beam ranking determined based on the actual beam measurement result, or in other words, the validity of the prediction result can be determined based on the beam ranking determined based on the predicted beam measurement result and the beam ranking determined based on the actual beam measurement result. Exemplarily, the beam ranking determined based on the predicted beam measurement result may include ranking the beams from high to low according to the predicted beam measurement result, determining the beam ranking, or ranking the beams from low to high according to the predicted beam measurement result, determining the beam ranking; the beam ranking determined based on the actual beam measurement result may include ranking the beams from high to low according to the actual beam measurement result, determining the beam ranking, or ranking the beams from low to high according to the actual beam measurement result, determining the beam ranking.

[0067] In some implementations, the validity of the prediction result is related to a beam set determined based on the predicted beam measurement result. In other words, the validity of the prediction result can be determined based on the beam set determined based on the predicted beam measurement result. For example, determining the beam set based on the predicted beam measurement result can include determining the beam set by filtering the predicted beam measurement results from high to low, or by filtering the predicted beam measurement results from low to high.

[0068] In some implementations, the validity of the prediction result is related to a beam order determined based on actual beam measurement results. In other words, the validity of the prediction result can be determined based on the beam order determined based on the actual beam measurement results. For example, the beam order determined based on the actual beam measurement results can include a beam order determined in descending order of the actual beam measurement results, or a beam order determined in descending order of the actual beam measurement results.

[0069] In some implementations, the validity of the prediction result is related to the beam set determined based on the actual beam measurement result. In other words, the validity of the prediction result can be determined based on the beam set determined based on the actual beam measurement result. For example, determining the beam set based on the actual beam measurement result can include determining the beam set by filtering the beams from high to low based on the actual beam measurement result, or by filtering the beams from low to high based on the actual beam measurement result.

[0070] The following two examples illustrate how to judge the validity and invalidity of the prediction results.

[0071] Example 1: How to determine if a prediction result is valid

[0072] In some implementations, the terminal device determines that the prediction result is valid when a first condition is met. The first condition includes one or more of the following eight conditions. Each of the eight conditions is described below.

[0073] Condition 1: an absolute value of a difference between a predicted beam measurement result corresponding to a beam in the first beam set and an actual beam measurement result corresponding to the same beam is less than or equal to a first threshold.

[0074] Condition 2: The absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, and the ratio of the number of beams to the number of beams included in the first beam set or the second beam set is greater than or equal to the second threshold.

[0075] Condition 3: The beams included in the first beam set are the same as the beams included in the second beam set.

[0076] Condition 4: The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is the same as the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement result.

[0077] Condition 5: The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results.

[0078] Condition 6: a ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is greater than or equal to a third threshold.

[0079] Condition 7: The beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set.

[0080] Condition 8: The beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result belongs to the first beam set.

[0081] The first beam set is a beam set determined based on a predicted beam result, and the second beam set is a beam set determined based on an actual beam measurement result.

[0082] In some implementations, the first beam set may include all predicted beams, or some predicted beams, and the second beam set may include all actually measured beams, or some actually measured beams.

[0083] In some implementations, the first beam set may include the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set may include the top K beams with the best beam measurement results determined based on the actual beam measurement results, where K is an integer greater than or equal to 1. In some embodiments, the beam measurement result may also be referred to as beam quality. Beam quality can be measured by physical layer indicators. For example, the beam measurement result may be determined based on one or more of the following: reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), reference signal receiving quality (RSRQ), received signal strength indicator (RSSI), and signal to noise ratio (SNR). By determining the top K beams with the best beam measurement results, the accuracy of determining the validity or invalidity of the prediction result can be improved.

[0084] In some implementations, the value of K may be agreed upon by default, or predefined in the protocol (such as a predefined fixed value), or configured by the network device. For example, the value of K may be 1, 2, or 3 as agreed upon by the protocol. Configuring K by protocol agreement is simpler to implement and saves signaling overhead because it does not need to be configured to the terminal device through dedicated signaling. For another example, the value of K may be configured to the terminal device by the network device. The terminal device may receive configuration information sent by the network device, which is used to indicate the value of K. This approach is more flexible.

[0085] For example, assume that the network device configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1, and actually measure beam 2, beam 4, and beam 6 associated with cell 1 (the period of predicting the beam measurement results of beam 2, beam 4, and beam 6 associated with cell 1 can be shorter than the period of actually measuring the beam measurement results of beam 2, beam 4, and beam 6 associated with cell 1. For example, the terminal device predicts the beam measurement results of beam 2, beam 4, and beam 6 associated with cell 1 once every 40m, but actually measures the beam measurement results of cell 1 once every 160m. Assuming that the value of K is 2, during a performance monitoring process, the terminal device obtains through an actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4 and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the second beam set), and obtains through a prediction process that the top two beams with the best beam measurement results among beam 2, beam 4 and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the first beam set).

[0086] For condition 1, the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, or in other words, for the same beam in the first beam set, the absolute value of the difference between the corresponding predicted beam measurement and the actual beam measurement result is less than or equal to the first threshold. The absolute value of the difference between the predicted beam measurement result and the actual beam measurement result is less than or equal to the first threshold, indicating that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate, and therefore, the terminal device can determine that the prediction result is valid. The same beam mentioned above can be any beam in the first beam set. In some implementations, the absolute value of the difference between the predicted beam measurement result and the actual beam measurement result being less than or equal to the first threshold can be referred to as accuracy compliance.

[0087] For example, assuming that the first beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is less than or equal to the first threshold, the terminal device can determine that the prediction result is valid.

[0088] For example, assume that the network device configures a terminal device to actually measure Beam 1, Beam 3, and Beam 5 associated with Cell 1, and to predict Beam 2, Beam 4, and Beam 6 associated with Cell 1. At a certain moment (hereinafter referred to as moment t, e.g., a moment corresponding to every 160 ms interval), the network device configures the terminal device to both predict Beam 2, Beam 4, and Beam 6 associated with Cell 1 and actually measure Beam 2, Beam 4, and Beam 6 associated with Cell 1. During a performance monitoring process, the measurement results corresponding to Beam 2, Beam 4, and Beam 6 associated with Cell 1 obtained by the terminal device through the actual measurement process are -97 dBm, -98 dBm, and -99 dBm, respectively. The measurement results corresponding to Beam 2, Beam 4, and Beam 6 associated with Cell 1 obtained through the prediction process are -99 dBm, -102 dBm, and -100 dBm, respectively. The value of K is 2, and the value of the first threshold is 3 dB. According to the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (less than the first threshold), and the absolute value of the difference between the predicted result and the actual measurement result of beam 6 is equal to 1dB (less than the first threshold). Therefore, the terminal device can determine that the prediction result is valid.

[0089] By determining the validity of the prediction result according to condition 1, it is possible to ensure that the first model is in a high-precision working state, thereby improving the reliability of the wireless communication system.

[0090] In some implementations, the value of the first threshold may be agreed upon by default, or predefined in the protocol (such as a predefined fixed value), or configured by the network device. For example, the value of the first threshold agreed upon by the protocol may be 1dB, 2dB, or 3dB. Configuring the first threshold by means of protocol agreement is simpler to implement and can also save signaling overhead because it does not need to be configured to the terminal device through dedicated signaling. For another example, the value of the first threshold may be configured to the terminal device by the network device. The terminal device can receive configuration information sent by the network device, and the configuration information is used to indicate the value of the first threshold. This approach is more flexible.

[0091] For condition 2, if the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams at the first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to the second threshold, or in other words, for the same beam in the first beam set, the absolute value of the difference between the predicted beam measurement result corresponding to the same beam and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams at the first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to the second threshold, then a sufficient number of beams have similar predicted beam measurement results to the actual beam measurement results, which roughly reflects that the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid. The same beam mentioned above can be any beam in the first beam set. In some implementations, for the same beam in the first beam set, the number of beams for which the absolute value of the difference between the corresponding predicted beam measurement result and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to a second threshold, can be said to be that the beam measurement results corresponding to a certain proportion of beams meet the accuracy standard.

[0092] For example, assuming that the first beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 50%. Since the absolute value of the difference between the predicted beam measurement result corresponding to one of the two best beams and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, the 50% ratio requirement can be met, and the terminal device can determine that the prediction result is valid.

[0093] For example, assume that the network device configures the terminal device to actually measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. During a performance monitoring process, the terminal device obtains measurement results corresponding to beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process as -97dBm, -98dBm, and -99dBm, respectively. The measurement results corresponding to beam 2, beam 4, and beam 6 associated with cell 1 obtained through the prediction process are -99dBm, -102dBm, and -100dBm, respectively. The value of K is 3, and the value of the first threshold is 3dB. It can be seen that this The top three best beams in this prediction are beam 2, beam 6, and beam 4. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (less than the first threshold value), the absolute value of the difference between the predicted result and the actual measurement result of beam 6 is equal to 1dB (less than the first threshold value), and the absolute value of the difference between the predicted result and the actual measurement result of beam 4 is equal to 4dB (greater than the first threshold value). If the second threshold value is 50%, since the beam measurement result prediction results corresponding to two of the three best beams meet the prediction conditions, the 50% ratio requirement can be reached. Therefore, the terminal device can determine that the prediction result is valid.

[0094] By determining the validity of the prediction results through condition 2, it is possible to ensure that the first model is in a high-precision working state. By configuring the second threshold, the performance monitoring requirements can be relatively relaxed, thereby avoiding the blind deactivation of the AI ​​functions currently in use by network devices due to overly strict performance monitoring methods, thereby taking into account the reliability and flexibility of the wireless communication system.

[0095] In some implementations, the value of the second threshold may be agreed upon by default, or predefined in the protocol (such as a predefined fixed value), or configured by the network device. For example, the value of the second threshold agreed upon by the protocol may be 50%, 75%, or 90%. By configuring the second threshold in a manner agreed upon by the protocol, since it does not need to be configured to the terminal device through dedicated signaling, the implementation is relatively simple and signaling overhead can also be saved. For another example, the value of the second threshold may be configured to the terminal device by the network device. The terminal device can receive configuration information sent by the network device, and the configuration information is used to indicate the value of the second threshold. This approach is relatively flexible.

[0096] For condition 3, the beams included in the first beam set are the same as the beams included in the second beam set. In other words, any beam in the first beam set exists in the second beam set, and correspondingly, any beam in the second beam set also exists in the first beam set. The beams included in the first beam set are the same as the beams included in the second beam set, which means that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the prediction result is valid. In some implementations, the beams included in the first beam set are the same as the beams included in the second beam set, which can be said to be the beam identifications contained in the beam set meeting the standards.

[0097] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set also includes beam 2 and beam 6, the terminal device can determine that the prediction result is valid.

[0098] For example, assume that the network device configures the terminal device to measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains through the actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the second beam set). The top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 obtained through the prediction process are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the first beam set). Since the first beam set and the second beam set are the same, the terminal device can determine that the prediction result is valid.

[0099] By determining the validity of the prediction results through condition 3, it is possible to ensure that accurate beam set information consisting of the top K best beams is obtained from the predictable beams, which is conducive to the network equipment correctly executing resource scheduling operations related to the beam set consisting of the top K best beams (for example: beam management scheduling, configuration of non-competition-based random access resources), thereby improving the reliability of the wireless communication system.

[0100] For condition 4, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results, or in other words, for the same beam in the first beam set, the corresponding arrangement order determined based on the predicted beam measurement results is the same as the arrangement order determined based on the actual beam measurement results. The beam arrangement order determined based on the predicted beam measurement results is the same as the beam arrangement order determined based on the actual beam measurement results, indicating that the predicted beam measurement results are similar to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid. The same beam mentioned above can be any beam in the first beam set. In some implementations, the arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the arrangement order determined based on the actual beam measurement results, which can be called the relative ranking of the beams meeting the standard.

[0101] The embodiments of the present application do not specifically limit the order in which the beams in the first beam set are arranged based on the predicted beam measurement results and the order in which the beams in the first beam set are arranged based on the actual beam measurement results. For example, the order in which the beams are arranged based on the predicted beam measurement results may include an order in which the beams are determined in descending order according to the predicted beam measurement results, or an order in which the beams are determined in descending order according to the predicted beam measurement results. The order in which the beams are arranged based on the actual beam measurement results may also include an order in which the beams are determined in descending order according to the actual beam measurement results, or an order in which the beams are determined in descending order according to the actual beam measurement results. As long as the order in which the beams are arranged based on the predicted beam measurement results and the order in which the beams are arranged based on the actual beam measurement results are arranged according to the same rules, it is sufficient. For example, both the beam sorting based on the predicted beam measurement results and the beam sorting based on the actual beam measurement results determine the beam order in descending order according to the beam measurement results.

[0102] For example, assuming that the first beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2→beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2→beam 6, then the terminal device determines that the prediction result is valid.

[0103] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1 and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -99dBm, and -98dBm for beams 2, 4, and 6 associated with cell 1, respectively. The predicted measurement results for beams 2, 4, and 6 associated with cell 1 are -99dBm, -102dBm, and -100dBm, respectively. K is 2. Based on the descending order of the predicted results, the best two beams are beam 2 and beam 6. Next, let's look at the order of arrangement of beam 2 and beam 6 based on the descending order of actual measurement results. It can be seen that the order of arrangement of beam 2 and beam 6 based on the descending order of actual measurement results is exactly the first two best beams after the actual measurement results of all beams are arranged in descending order, and the relative order of beam 2 and beam 6 is also that beam 2 is ahead of beam 6. Therefore, the terminal device can determine that the prediction result is valid.

[0104] By determining the validity of the prediction results through condition 4, it can be ensured that the beam order of the K beams with the best prediction results after being ranked in descending order according to the beam measurement results is consistent with the relative order of the K beams with the best prediction results after being ranked in descending order based on the actual beam measurement results, which is conducive to the network equipment accurately executing resource scheduling operations related to the relative ranking of the beams, thereby improving the reliability of the wireless communication system.

[0105] For condition 5, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results, or in other words, for the same beam in the first beam set and the second beam set (the beams included in the first beam set are the same as the beams included in the second beam set), the corresponding beam arrangement order determined based on the predicted beam measurement results is the same as the beam arrangement order determined based on the actual beam measurement results. The corresponding beam arrangement order determined based on the predicted beam measurement results is the same as the beam arrangement order determined based on the actual beam measurement results, indicating that the predicted beam measurement results are close to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid. The same beam mentioned above can be any beam in the first beam set or any beam in the second beam set. In some implementations, for the same beam in the first beam set and the second beam set, the corresponding beam arrangement order determined based on the predicted beam measurement results is the same as the beam arrangement order determined based on the actual beam measurement results, which can be called the absolute ranking of the beams.

[0106] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 2 → beam 6, then the terminal device can determine that the prediction result is valid.

[0107] By determining the validity of the prediction results using condition 5, it is possible to ensure that the predicted beam ordering of the best K beams is consistent with the actual beam ordering based on the actual beam measurement results, thereby obtaining the correct absolute beam ranking. This helps network devices accurately execute resource scheduling operations related to beam ranking, thereby improving the reliability of the wireless communication system.

[0108] In some implementations, condition 5 can be combined with other conditions to determine whether the prediction result is valid. For example, condition 5 can be combined with condition 3, condition 5 can be combined with conditions 1 and 3, or condition 5 can be combined with conditions 2 and 3.

[0109] Taking the combination of conditions 5 and 3 as an example, the judgment condition is: the beams included in the first beam set are the same as the beams included in the second beam set, and the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results. In other words, the beam identifiers included in the first beam set and the second beam set meet the requirements and the absolute ranking of the beams meet the requirements. This implementation indicates that the predicted beam measurement results are close to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid.

[0110] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 2 → beam 6, then the terminal device can determine that the prediction result is valid.

[0111] For example, assume that the network device configures the terminal device to actually measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains through the actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the second beam set), and obtains through the prediction process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the first beam set). The order of the beams in the first beam set, determined based on the predicted beam measurement results, is beam 2 → beam 6. The order of the beams in the second beam set, determined based on the actual beam measurement results, is beam 2 → beam 6. The first and second beam sets contain the same beams and are arranged in the same order. Therefore, the terminal device can determine that the current prediction result is valid.

[0112] Taking the combination of condition 5 and conditions 1 and 3 as an example, the judgment condition is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, and the beams included in the first beam set are the same as the beams included in the second beam set, and the beam arrangement order determined based on the predicted beam measurement results for the beams in the first beam set is the same as the beam arrangement order determined based on the actual beam measurement results for the beams in the second beam set, or in other words, the beam measurement results corresponding to all beams in the first beam set meet the accuracy standard, and the beam identifiers included in the beam set meet the standard, and the absolute ranking of the beams meets the standard. This implementation method indicates that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate, so the terminal device can determine that the current prediction result is valid.

[0113] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is less than or equal to the first threshold, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 2 → beam 6, then the terminal device can determine that the prediction result is valid.

[0114] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -106dBm, and -99dBm for beams 2, 4, and 6 associated with cell 1, respectively. The terminal device obtains prediction results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively. K is 2, and the first threshold is 3dB. Based on the ranking of beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best predicted beams are beams 2 and beam 6, respectively. That is, the first beam set includes beams 2 and beam 6. The absolute value of the difference between the predicted result and the actual measurement result for beam 2 is 2 dB (less than the first threshold), and the absolute value of the difference between the predicted result and the actual measurement result for beam 6 is 1 dB (less than the first threshold), meeting condition 1. Through actual measurement, the terminal device obtains that the top two beams with the best beam measurement results among beams 2, 4, and 6 associated with cell 1 are beams 2 and beam 6 (beams 2 and beam 6 now form the second beam set). The beams in the first beam set, based on the predicted beam measurement results, are ordered as beam 2 → beam 6. The beams in the second beam set, based on the actual beam measurement results, are ordered as beam 2 → beam 6. Therefore, the terminal device can determine that the prediction result is valid.

[0115] Condition 5 can also be combined with Condition 2 and Condition 3. For related descriptions, please refer to the description of the combination of Condition 5 with Condition 1 and Condition 3 above, which will not be repeated here.

[0116] For condition 6, the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is greater than or equal to a third threshold. In other words, a certain proportion of beam identifiers (IDs) in the first beam set meet the threshold. This implementation indicates that the predicted beam measurement result is close to the actual beam measurement result, indicating that the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid.

[0117] For example, assuming that the first beam set includes beam 2, beam 8 and beam 6, the second beam set includes beam 2, beam 4 and beam 6, the number of beams contained in the intersection of the first beam set and the second beam set is 2, the third threshold is 50%, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is greater than 50%, then the terminal device can determine that the prediction result is valid.

[0118] For example, assume that the network device configures the terminal device to actually measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains through the actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 4 and beam 6 (at this time, beam 4 and beam 6 form the second beam set), and obtains through the prediction process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the first beam set). At this time, the beam included in the intersection of the first beam set and the second beam set is beam 6. If the third threshold is 50%, the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is 50%, which is equal to the third threshold. Therefore, the terminal device can determine that the prediction result is valid.

[0119] In some implementations, the value of the third threshold may be agreed upon by default, or predefined in the protocol (such as a predefined fixed value), or configured by the network device. For example, the value of the third threshold agreed upon by the protocol may be 50%, 75%, or 90%. By configuring the third threshold by means of protocol agreement, since it does not need to be configured to the terminal device through dedicated signaling, the implementation is relatively simple and signaling overhead can also be saved. For another example, the value of the third threshold may be configured to the terminal device by the network device. The terminal device can receive configuration information sent by the network device, and the configuration information is used to indicate the value of the third threshold. This method is relatively flexible.

[0120] In some implementations, a network device may send first configuration information to a terminal device, where the first configuration information is used to configure a threshold. The first configuration information includes threshold information used to determine whether a prediction result is valid. The threshold information may include one or more of the following: a first threshold, a second threshold, and a third threshold. For example, a terminal device may receive the first configuration information sent by the network device, where the first configuration information includes the value of the first threshold. Configuring threshold information through the first configuration information provides greater flexibility.

[0121] By determining the validity of the prediction results through condition 6, it is possible to ensure that the first model is in a high-precision working state. At the same time, the configuration of the third threshold can also make the performance monitoring requirements relatively relaxed, thereby avoiding the network equipment blindly deactivating the AI ​​functions in use due to overly strict performance monitoring methods, thereby taking into account the reliability and flexibility of the wireless communication system.

[0122] In some implementations, condition 6 can be combined with other conditions to determine whether the prediction result is valid. For example, condition 6 can be combined with condition 1, condition 6 can be combined with condition 2, and condition 6 can be combined with condition 4.

[0123] The judgment condition after combining condition 1 and condition 6 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is greater than or equal to the third threshold, or in other words, the beam measurement results corresponding to all beams contained in the first beam set meet the standard, and a certain proportion of beam identifiers meet the standard, indicating that the predicted beam measurement result is similar to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the prediction result is valid.

[0124] The judgment condition after combining condition 2 and condition 6 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is greater than or equal to the second threshold, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is greater than or equal to the third threshold, or in other words, the beam measurement results corresponding to some beams contained in the first beam set meet the standards, and a certain proportion of beam identifiers meet the standards, indicating that the predicted beam measurement results are close to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the current prediction results are valid.

[0125] The judgment condition after combining condition 4 and condition 6 is: the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is the same as the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement result, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is greater than or equal to the third threshold, or in other words, the relative ranking of the beams contained in the first beam set meets the standard, and a certain proportion of the beam identifiers meet the standard, indicating that the predicted beam measurement result is similar to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid.

[0126] For example, assuming that the first beam set includes beam 2, beam 4, and beam 6, and the second beam set includes beam 2, beam 4, and beam 8, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 4 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 4 → beam 6. If the number of beams included in the intersection of the first beam set and the second beam set is 2, and the third threshold is 50%, and the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is greater than 50%, then the terminal device can determine that the current prediction result is valid.

[0127] For example, assume that the network device configures the terminal device to measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains through the actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 4 and beam 6 (at this time, beam 4 and beam 6 constitute the second beam set), and obtains through the prediction process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 constitute the first beam set). The beams in the first beam set are arranged in descending order based on the actual measurement results as beam 2 and beam 6. The beams in the first beam set are also arranged in descending order based on the predicted beam measurement results as beam 2 and beam 6, meeting condition 4. At this point, the intersection of the first beam set and the second beam set includes beam 6. If the third threshold is 50%, the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is 50%, meeting condition 6. Therefore, the terminal device can determine that this prediction result is valid.

[0128] For condition 7, the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set, or in other words, the second beam set includes the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result, indicating that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the prediction result is valid.

[0129] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 4, and the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result is beam 2, then the terminal device can determine that the prediction result is valid.

[0130] For example, assume that the network device configures a terminal device to measure Beam 1, Beam 3, and Beam 5 associated with Cell 1, and predict Beam 2, Beam 4, and Beam 6 associated with Cell 1. At time t, the network device configures the terminal device to both predict Beam 2, Beam 4, and Beam 6 associated with Cell 1 and actually measure Beam 2, Beam 4, and Beam 6 associated with Cell 1. During a performance monitoring process, the terminal device obtains -97dBm, -103dBm, and -99dBm for Beam 2, Beam 4, and Beam 6 associated with Cell 1, respectively, through the prediction process. The terminal device obtains -99dBm, -100dBm, and -102dBm for Beam 2, Beam 4, and Beam 6 associated with Cell 1, respectively, through the actual measurement process. K is set to 2. The ranking of the beam sets associated with Cell 1 obtained through the prediction process shows that the two best predicted beams are Beam 2 and Beam 6, respectively. This means that the first beam set includes Beam 2 and Beam 6. The terminal device obtains the best beam measurement results for beams 2 and 4 among beams 2, 4, and 6 associated with cell 1 through actual measurement. (Beams 2 and 4 now form the second beam set.) The beam in the first beam set with the best beam measurement result, determined based on the predicted beam measurement results, is beam 2, which belongs to the second beam set. Therefore, the terminal device can determine that this prediction result is valid.

[0131] By determining the validity of the prediction results through condition 7, it can be ensured that the beam with the best predicted beam measurement result belongs to the top K beams with the best actual beam measurement results, reflecting the accuracy of the prediction results within an acceptable error range, which is conducive to the network equipment to correctly perform resource scheduling operations related to the best beam (for example: beam management scheduling, configuration of non-contention-based random access resources), thereby improving the reliability of the wireless communication system.

[0132] In some implementations, condition 7 can be combined with other conditions to determine whether the prediction result is valid. For example, condition 7 can be combined with condition 1.

[0133] Taking the combination of condition 7 and condition 1 as an example, the judgment condition is: the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set, and the absolute value of the difference between the predicted beam measurement result corresponding to the best beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, or in other words, the beam measurement result corresponding to the best beam in the first beam set meets the accuracy standard, and the second beam set contains the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result. This implementation method indicates that the beam measurement result corresponding to the predicted best beam is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the current prediction result is valid.

[0134] For example, assuming that the first beam set includes beam 2, beam 4 and beam 6, and the second beam set includes beam 2, beam 4 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result is beam 2, then the terminal device can determine that the prediction result is valid.

[0135] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains -97dBm, -103dBm, and -99dBm, respectively, for beams 2, 4, and 6 associated with cell 1, as measured through the prediction process. The terminal device obtains -99dBm, -100dBm, and -102dBm, respectively, for beams 2, 4, and 6 associated with cell 1, as measured through actual measurement. K is 2, and the first threshold is 3dB. According to the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6. The terminal device obtains the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process, which are beam 2 and beam 4 (at this time, beam 2 and beam 4 form the second beam set). The beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result is beam 2, which belongs to the second beam set. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (less than the first threshold value), which meets the judgment of the combination of condition 7 and condition 1. Therefore, the terminal device can determine that the prediction result is valid.

[0136] For condition 8, the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result belongs to the first beam set, or in other words, the first beam set contains the beam with the best beam measurement result determined based on the actual beam measurement result in the second beam set, which means that the top K beams with the best predicted beam measurement results include the beam with the best actual beam measurement result, that is, the beam with the best actual beam measurement result can be predicted relatively accurately. Therefore, the terminal device can determine that the prediction result is valid.

[0137] For example, assuming that the first beam set includes beam 2 and beam 4, and the second beam set includes beam 2 and beam 6, and the beam in the second beam set has the best beam measurement result determined based on the actual beam measurement result, the terminal device can determine that the prediction result is valid.

[0138] For example, assume that the network device configures a terminal device to measure Beam 1, Beam 3, and Beam 5 associated with Cell 1, and predict Beam 2, Beam 4, and Beam 6 associated with Cell 1. At time t, the network device configures the terminal device to both predict Beam 2, Beam 4, and Beam 6 associated with Cell 1 and actually measure Beam 2, Beam 4, and Beam 6 associated with Cell 1. During a performance monitoring process, the terminal device obtains -97dBm, -103dBm, and -99dBm for Beam 2, Beam 4, and Beam 6 associated with Cell 1, respectively, through the prediction process. The terminal device obtains -99dBm, -100dBm, and -102dBm for Beam 2, Beam 4, and Beam 6 associated with Cell 1, respectively, through the actual measurement process. K is set to 2. The ranking of the beam sets associated with Cell 1 obtained through the prediction process shows that the two best predicted beams are Beam 2 and Beam 6, respectively. This means that the first beam set includes Beam 2 and Beam 6. The terminal device obtains the best beam measurement results for beams 2, 4, and 6 associated with cell 1 through actual measurement. The top three beams are beams 2 and 4 (beams 2 and 4 now form the second beam set). The beam in the second beam set with the best beam measurement result, determined based on the actual beam measurement results, is beam 2, which belongs to the first beam set. Therefore, the terminal device can determine that the current prediction result is valid.

[0139] By determining the validity of the prediction results through condition 8, it can be ensured that the best beam of the actual beam measurement beam is accurately predicted within an acceptable error range, which is conducive to the network equipment to correctly perform resource scheduling operations related to the best beam (for example: beam management scheduling, configuration of non-contention-based random access resources), thereby improving the reliability of the wireless communication system.

[0140] In some implementations, condition 8 can be combined with other conditions to determine whether the prediction result is valid. For example, condition 8 can be combined with condition 1.

[0141] Taking the combination of condition 8 and condition 1 as an example, the judgment condition is: the beam with the best beam measurement result determined based on the actual beam measurement result of the beam in the second beam set belongs to the first beam set, and the absolute value of the difference between the predicted beam measurement result corresponding to the best beam in the second beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, or in other words, the accuracy of the predicted beam measurement result corresponding to the best beam in the second beam set meets the standard, and the first beam set contains the beam with the best beam measurement result determined based on the actual beam measurement result in the second beam set. This implementation method means that the beam with the best actual beam measurement result can be accurately predicted within the error range and the accuracy of the predicted beam measurement result of the beam also meets the standard. Therefore, the terminal device can determine that the current prediction result is valid.

[0142] For example, assuming that the first beam set includes beam 2, beam 4 and beam 6, and the second beam set includes beam 2, beam 4 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the beam in the second beam set has the best beam measurement result determined based on the actual beam measurement result, the terminal device can determine that the prediction result is valid.

[0143] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains -97dBm, -103dBm, and -99dBm, respectively, for beams 2, 4, and 6 associated with cell 1, as measured through the prediction process. The terminal device obtains -99dBm, -100dBm, and -102dBm, respectively, for beams 2, 4, and 6 associated with cell 1, as measured through actual measurement. K is 2, and the first threshold is 3dB. According to the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6. The terminal device obtains the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process, which are beam 2 and beam 4 (at this time, beam 2 and beam 4 form the second beam set). The beam in the second beam set with the best beam measurement result determined based on the actual beam measurement results is beam 2, which belongs to the first beam set. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (less than the first threshold value), which meets the judgment of the combination of condition 8 and condition 1. Therefore, the terminal device can determine that the current prediction result is valid.

[0144] The above conditions can be used individually or in combination. For example, conditions 1 and 4 can be combined, conditions 1 and 3 can be combined, or conditions 1, 3, and 4 can be combined. Another example is conditions 2 and 3 can be combined, conditions 2 and 4 can be combined, or conditions 2, 3, and 4 can be combined.

[0145] Condition 2, condition 1 and condition 4 are combined, condition 2, condition 1 and condition 3 are combined, and condition 2, condition 1, condition 3 and condition 5 are combined.

[0146] The combined determination condition of Condition 1 and Condition 4 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, and the beam arrangement order determined based on the predicted beam measurement result for the beams in the first beam set is the same as the beam arrangement order determined based on the actual beam measurement result for the beams in the first beam set. In other words, the beam measurement result corresponding to any beam included in the first beam set meets the accuracy standard and the relative ranking of the beams meets the standard. This implementation indicates that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the predicted result is valid.

[0147] For example, assuming that the first beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is less than or equal to the first threshold, the terminal device can determine that the prediction result is valid.

[0148] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At a certain moment (hereinafter referred to as moment t), the network device configures the terminal device to both predict beams 2, 4, and 6 associated with cell 1 and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -98dBm, and -99dBm for beams 2, 4, and 6 associated with cell 1, respectively. The terminal device obtains prediction results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively. K is 2, and the first threshold is 3dB. Based on the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, respectively. That is, the first beam set includes beam 2 and beam 6. The absolute value of the difference between the predicted result and the actual measurement result for beam 2 is equal to 2dB (less than the first threshold value), and the absolute value of the difference between the predicted result and the actual measurement result for beam 6 is equal to 1dB (less than the first threshold value), meeting condition 1. Based on the descending order of the predicted results, it can be seen that the best K beams are beam 2 and beam 6. Based on the descending order of the actual measurement results, it can be seen that the relative ranking of beam 2 and beam 6 is also beam 2 first and beam 6 last, meeting condition 4. Therefore, the terminal device can determine that the current prediction result is valid.

[0149] The combined determination condition of conditions 1 and 3 is: the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the beams included in the first beam set are the same as the beams included in the second beam set. In other words, the beam measurement results corresponding to the beams included in the first beam set meet the accuracy requirements, and all beam identifiers included in the beam set meet the requirements. This implementation indicates that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the predicted result is valid.

[0150] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, the beams included in the first beam set are the same as the beams included in the second beam set. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is less than or equal to the first threshold, the terminal device can determine that the prediction result is valid.

[0151] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At a certain moment (hereinafter referred to as moment t), the network device configures the terminal device to both predict beams 2, 4, and 6 associated with cell 1 and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results for beams 2, 4, and 6 associated with cell 1 of -97 dBm, -100 dBm, and -99 dBm, respectively. The terminal device obtains prediction results for beams 2, 4, and 6 associated with cell 1 of -99 dBm, -104 dBm, and -100 dBm, respectively. Furthermore, the value of K is 2, and the value of the first threshold is 3 dB. According to the beam set associated with cell 1 obtained during the prediction process, the two best predicted beams are beam 2 and beam 6. That is, the first beam set includes beams 2 and 6. The absolute value of the difference between the predicted result and the actual measurement result for beam 2 is 2 dB (less than the first threshold value), and the absolute value of the difference between the predicted result and the actual measurement result for beam 6 is 1 dB (less than the first threshold value), meeting condition 1. Through actual measurement, the terminal device obtains that the top two beams with the best measurement results among beams 2, 4, and 6 associated with cell 1 are beams 2 and 6. That is, the second beam set includes beams 2 and 6. Since the first and second beam sets are the same, the terminal device can determine that the current prediction result is valid.

[0152] Condition 2 can be combined with Condition 4 to determine the following: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is greater than or equal to the second threshold, and the beam arrangement order determined based on the predicted beam measurement result for the beams in the first beam set is the same as the beam arrangement order determined based on the actual beam measurement result for the beams in the first beam set, or in other words, the beam measurement results corresponding to some of the beams contained in the first beam set meet the accuracy requirements and the relative rankings of the beams meet the requirements. This implementation indicates that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the predicted result is valid.

[0153] The combined determination condition of conditions 2 and 3 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is greater than or equal to the second threshold, and the beams contained in the first beam set are the same as the beams contained in the second beam set, or in other words, the beam measurement results corresponding to some of the beams contained in the first beam set meet the accuracy standard and all beam identifiers contained in the beam set meet the standard. This implementation method indicates that the predicted beam measurement result is close to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the predicted result is valid.

[0154] The combined determination conditions of Condition 2, Condition 1, and Condition 4 are as follows: the absolute value of the difference between the predicted beam measurement results corresponding to the top m best beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to a first threshold, and the ratio of the number of beams in the first beam set for which the absolute value of the difference between the predicted beam measurement results and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold to the number of beams in the first beam set or the second beam set is greater than or equal to a second threshold, and the beam arrangement order determined for the beams in the first beam set based on the predicted beam measurement results is the same as the beam arrangement order determined for the beams in the first beam set based on the actual beam measurement results. In other words, the beam measurement results of some beams included in the first beam set meet the accuracy requirements, and the relative rankings of the beams meet the requirements, indicating that the predicted beam measurement results are close to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the prediction result is valid, and m is an integer greater than or equal to 1.

[0155] For example, assuming that the first beam set includes beam 2, beam 4 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 4 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 4 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 50%, then the terminal device can determine that the current prediction result is valid.

[0156] The judgment condition after combining condition 2, condition 1 and condition 3 is: the absolute value of the difference between the predicted beam measurement results corresponding to the first m best beams in the first beam set and the actual beam measurement results corresponding to the same beam is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement results corresponding to the beams in the first beam set and the actual beam measurement results corresponding to the same beam is less than or equal to the first threshold. The ratio of the number of beams less than or equal to the first threshold and the number of beams included in the first beam set or the second beam set is greater than or equal to the second threshold, and the beams included in the first beam set are the same as the beams included in the second beam set, or in other words, the beam measurement results of some beams included in the first beam set meet the standard, and the beam identifiers included in the beam set meet the standard, indicating that the predicted beam measurement results are close to the actual beam measurement results, that is, the predicted beam measurement results are relatively accurate. Therefore, the terminal device can determine that the prediction results are valid.

[0157] For example, assuming that the first beam set includes beam 2, beam 4, and beam 6, and the second beam set includes beam 2, beam 4, and beam 6, and the beams included in the first beam set are the same as the beams included in the second beam set. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to a first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 50%, then the terminal device can determine that the current prediction result is valid.

[0158] The judgment condition after combining condition 2, condition 1, condition 3 and condition 5 is: the absolute value of the difference between the predicted beam measurement results corresponding to the first m best beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement results corresponding to the beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold. The ratio of the number of beams whose absolute value is less than or equal to the first threshold to the number of beams included in the first beam set or the second beam set is greater than or equal to the second threshold, and the number of beams included in the first beam set is less than or equal to the second threshold. The beams included in the first beam set are the same as the beams included in the second beam set, and the beam arrangement order determined based on the predicted beam measurement results of the beams in the first beam set is the same as the beam arrangement order determined based on the actual beam measurement results of the beams in the second beam set. In other words, the beam measurement results of some beams included in the first beam set meet the accuracy, and the beam identifiers included in the beam set meet the standard, and the absolute ranking of the beams meets the standard, indicating that the predicted beam measurement result is similar to the actual beam measurement result, that is, the predicted beam measurement result is relatively accurate. Therefore, the terminal device can determine that the prediction result is valid.

[0159] For example, assume that the first beam set includes beam 2, beam 4, and beam 6, and the second beam set includes beam 2, beam 4, and beam 6. The beams included in the first beam set are the same as those included in the second beam set. The beam arrangement order of the beams in the first beam set, determined based on the predicted beam measurement results, is beam 2 → beam 4 → beam 6. The beam arrangement order of the beams in the second beam set, determined based on the actual beam measurement results, is beam 2 → beam 4 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to a first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 50%, then the terminal device can determine that the current prediction result is valid.

[0160] In this example, the terminal device determines whether the prediction result based on the first model is valid when the first condition is met, and then sends first information for the first model to the network device. The first information includes information related to the validity of the prediction result. By sending information related to the validity of the prediction result to the network device, the network device can clearly understand the performance of the first model, thereby improving the reliability of the wireless communication system.

[0161] Example 2: How to determine if a prediction result is invalid

[0162] In some implementations, if the second condition is met, the terminal device determines that the prediction result is invalid. The second condition includes one or more of the following eight conditions. The eight conditions are described below.

[0163] Condition 9: An absolute value of a difference between a predicted beam measurement result corresponding to at least one beam in the first beam set and an actual beam measurement result corresponding to the same beam is greater than a first threshold.

[0164] Condition 10: The absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold.

[0165] Condition 11: The beams included in the first beam set are not completely identical to the beams included in the second beam set.

[0166] Condition 12: The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is different from the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement result.

[0167] Condition 13: The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is different from the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement result.

[0168] Condition 14: a ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is less than a third threshold.

[0169] Condition 15: The beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result does not belong to the second beam set.

[0170] Condition 16: The beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result does not belong to the first beam set.

[0171] The first beam set is a beam set determined based on a predicted beam result, and the second beam set is a beam set determined based on an actual beam measurement result.

[0172] For condition 9, if the absolute value of the difference between a predicted beam measurement result corresponding to at least one beam in the first beam set and an actual beam measurement result corresponding to the same beam is greater than a first threshold, this indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, i.e., the predicted beam measurement result is not accurate. Therefore, the terminal device may determine that the prediction result is invalid. In some implementations, if the absolute value of the difference between the predicted beam measurement and the actual beam measurement result is greater than the first threshold, it may be referred to as substandard accuracy.

[0173] For example, assuming that the first beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, the terminal device can determine that the prediction result is invalid.

[0174] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -98dBm, and -99dBm for beams 2, 4, and 6 associated with cell 1, respectively. The terminal device obtains prediction results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively. K is 2, and the first threshold is 1dB. According to the ranking of the beam sets associated with cell 1 obtained in the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6, and the absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (greater than the first threshold value), and the absolute value of the difference between the predicted result and the actual measurement result of beam 6 is equal to 1dB (equal to the first threshold value). The terminal device can determine that the prediction result is invalid.

[0175] By determining the invalidity of the prediction result according to condition 9, it is possible to ensure that the first model is in a high-precision working state, thereby improving the reliability of the wireless communication system.

[0176] For condition 10, the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold, indicating that the predicted beam measurement result is significantly different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid. In some implementations, for the same beam in the first beam set, the absolute value of the difference between the corresponding predicted beam measurement result and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold, which can be called the beam measurement results corresponding to a certain proportion of beams do not meet the accuracy standards.

[0177] For example, assuming that the first beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 75%. Since the absolute value of the difference between the predicted beam measurement result corresponding to one of the two best beams and the corresponding actual beam measurement result is greater than the first threshold and does not meet the 75% ratio requirement, the terminal device can determine that the prediction result is invalid.

[0178] For example, assume that the network device configures the terminal device to measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. During a performance monitoring process, the terminal device obtains measurement results corresponding to beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process as -97dBm, -98dBm, and -99dBm, respectively. The measurement results corresponding to beam 2, beam 4, and beam 6 associated with cell 1 obtained through the prediction process are -99dBm, -102dBm, and -100dBm, respectively. The value of K is 3, and the value of the first threshold is 3dB. It can be seen that this time The top three best predicted beams are beam 2, beam 6 and beam 4 respectively. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (less than the first threshold value), the absolute value of the difference between the predicted result and the actual measurement result of beam 6 is equal to 1dB (less than the first threshold value), and the absolute value of the difference between the predicted result and the actual measurement result of beam 4 is equal to 4dB (greater than the first threshold value). If the second threshold value is 75%, since the beam measurement result prediction results corresponding to only two of the three best beams meet the accuracy requirements and fail to meet the 75% ratio requirement, the terminal device determines that the beam measurement result prediction behavior is invalid.

[0179] By determining the invalidity of the prediction result through condition 10, it is possible to ensure that the first model is in a high-precision working state. By configuring the second threshold, the performance monitoring requirements can be relatively relaxed, thereby avoiding the network equipment blindly deactivating the AI ​​function in use due to overly strict performance monitoring methods, thereby improving the reliability of the wireless communication system.

[0180] For condition 11, the beams included in the first beam set are not exactly the same as the beams included in the second beam set. For example, the first beam set contains at least one beam that does not exist in the second beam set, or the second beam set contains at least one beam that does not exist in the first beam set. If condition 11 is met, it means that the predicted beam measurement result is significantly different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate, and therefore, the terminal device can determine that the prediction result is invalid. In some implementations, the beams included in the first beam set are not exactly the same as the beams included in the second beam set, which can be referred to as the beam identification included in the beam set not meeting the standard.

[0181] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 4 and beam 6, the terminal device may determine that the prediction result is invalid.

[0182] For example, assume that the network device configures the terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beams 2, 4, and 6 associated with cell 1 and actually measure beams 2, 4, and 6 associated with cell 1. Assume that K is 2. During a performance monitoring process, the terminal device obtains through actual measurement the top two beams with the best beam measurement results among beams 2, 4, and 6 associated with cell 1, which are beams 4 and 6 (at this time, beams 4 and beam 6 form the second beam set). The prediction process obtains the top two beams with the best beam measurement results among beams 2, 4, and 6 associated with cell 1, which are beams 2 and 6 (at this time, beams 2 and beam 6 form the first beam set). Because the first beam set and the second beam set are not exactly the same, the terminal device determines that the prediction behavior of this beam measurement result is invalid.

[0183] By determining the invalidity of the prediction result through condition 11, it is possible to ensure that accurate beam set information consisting of the top K best beams is obtained from the predictable beams, which is conducive to the network equipment correctly executing resource scheduling operations related to the beam set consisting of the top K best beams, thereby improving the reliability of the wireless communication system.

[0184] For condition 12, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results, or in other words, there is at least one beam in the first beam set whose corresponding beam arrangement order determined based on the predicted beam measurement results is different from the beam arrangement order determined based on the actual beam measurement results. This implementation indicates that the predicted beam measurement results are significantly different from the actual beam measurement results, that is, the predicted beam measurement results are not very accurate, and therefore, the terminal device can determine that the prediction results are invalid. In some implementations, the beam arrangement order determined based on the predicted beam measurement results is different from the beam arrangement order determined based on the actual beam measurement results, which can be called the relative ranking of the beams not meeting the standards.

[0185] For example, assuming that the first beam set includes beam 2 and beam 6, the beam arrangement order in the first beam set based on the predicted beam measurement results is beam 2 → beam 6, and the arrangement order based on the actual beam measurement results is beam 6 → beam 2, then the terminal device can determine that the prediction result is invalid.

[0186] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1 and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -99dBm, -100dBm, and -97dBm for beams 2, 4, and 6 associated with cell 1, respectively. The predicted measurement results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively, are obtained. K is 2. Based on the predicted results, the best K beams are beams 2 and 6, in descending order from beam 2 to beam 6. Based on the actual measurement results, it can be seen that the beam measurement results of beam 2 and beam 6 are arranged in descending order as beam 6 → beam 2. Since the arrangement order of the beams is different, the terminal device determines that the prediction behavior of this beam measurement result is invalid.

[0187] By determining the invalidity of the prediction results through condition 12, it can be ensured that the beam order of the K beams with the best prediction results after being ranked in descending order according to the beam measurement results is consistent with the relative order of the K beams with the best prediction results after being ranked in descending order based on the actual beam measurement results, which is conducive to the network equipment accurately executing resource scheduling operations related to the relative ranking of the beams, thereby improving the reliability of the wireless communication system.

[0188] For condition 13, the beam arrangement order determined based on the predicted beam measurement results for the beams in the first beam set is different from the beam arrangement order determined based on the actual beam measurement results for the beams in the second beam set, or in other words, there is at least one beam whose ranking in the arrangement order determined based on the predicted beam measurement results for the first beam set is different from the ranking in the arrangement order determined based on the actual beam measurement results for the second beam set, indicating that the predicted beam measurement results differ greatly from the actual beam measurement results, that is, the predicted beam measurement results are not very accurate. Therefore, the terminal device can determine that the predicted results are invalid. In some implementations, the beam arrangement order determined based on the predicted beam measurement results for the beams in the first beam set is different from the beam arrangement order determined based on the actual beam measurement results for the beams in the second beam set, which can be called the absolute ranking of the beams not meeting the standard.

[0189] For example, assuming that the first beam set includes beam 2, beam 4 and beam 6, and the second beam set includes beam 2, beam 4 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 4 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 4 → beam 2 → beam 6, then the terminal device can determine that the prediction result is invalid.

[0190] By determining the invalidity of the prediction results through condition 13, it can be ensured that the beam ordering of the predicted best K beams is consistent with the actual beam ordering based on the actual beam measurement results, so as to obtain the correct absolute beam ranking. This is conducive to the network equipment to accurately perform resource scheduling operations related to the relative ranking of beams, thereby improving the reliability of the wireless communication system.

[0191] In some implementations, condition 13 can be combined with other conditions to determine whether the prediction result is invalid. For example, condition 13 can be combined with condition 11, condition 13 can also be combined with conditions 9 and 11, or condition 13 can also be combined with conditions 10 and 11.

[0192] Taking the combination of Condition 13 and Condition 11 as an example, the judgment condition is: the beams included in the first beam set differ from the beams included in the second beam set, or the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results differs from the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results. The terminal device determines that the predicted behavior of the current beam measurement result is invalid, or in other words, the beams included in the first beam set do not meet the standard or the absolute ranking does not meet the standard. In other words, as long as either Condition 13 or Condition 11 is met, it indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the prediction result is invalid.

[0193] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 6 → beam 2, then the terminal device can determine that the prediction result is invalid.

[0194] For example, assume that the network device configures the terminal device to measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains through the actual measurement process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 6 and beam 2 (at this time, beam 6 and beam 2 form the second beam set), and obtains through the prediction process that the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the first beam set). The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results is beam 6 → beam 2, then the terminal device determines that the prediction behavior of this beam measurement result is invalid.

[0195] Taking the combination of condition 13, condition 9 and condition 11 as an example, the judgment condition is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than the first threshold, or the beams included in the first beam set are not exactly the same as the beams included in the second beam set, or the beam arrangement order determined based on the predicted beam measurement result of the beams in the first beam set is different from the beam arrangement order determined based on the actual beam measurement result of the beams in the second beam set, or the beam measurement result corresponding to the beam in the first beam set is not up to standard, or the beams included in the set are not up to standard, or the absolute ranking of the beams is not up to standard. That is to say, as long as any one of conditions 13, condition 9 and condition 11 is met, it means that the predicted beam measurement result is significantly different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid.

[0196] For example, assuming that the first beam set includes beam 2 and beam 6, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is less than or equal to the first threshold, the second beam set includes beam 2 and beam 6, the beam arrangement order determined based on the predicted beam measurement result in the first beam set is beam 2 → beam 6, and the beam arrangement order determined based on the actual beam measurement result in the second beam set is beam 6 → beam 2, then the terminal device can determine that the prediction result is invalid.

[0197] Condition 13 can also be combined with conditions 10 and 11. For related descriptions, please refer to the description of the combination of condition 13 with conditions 9 and 11 above, which will not be repeated here.

[0198] For condition 14, the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is less than a third threshold. In other words, a certain proportion of beam identifiers in the first beam set fails to meet the criteria. This failure of a certain proportion of beam identifiers can indicate a poor predicted beam measurement result, indicating that the terminal device has determined that the predicted beam measurement result for the first cell is invalid.

[0199] For example, assuming that the first beam set includes beam 2, beam 8 and beam 6, the second beam set includes beam 2, beam 4 and beam 6, the number of beams contained in the intersection of the first beam set and the second beam set is 2, the third threshold is 75%, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than 75%, then the terminal device can determine that the prediction result is invalid.

[0200] For example, assume that the network device configures the terminal device to measure beam 1, beam 3, and beam 5 associated with cell 1, and configures the terminal device to predict beam 2, beam 4, and beam 6 associated with cell 1. At time t, the network device configures the terminal device to both predict beam 2, beam 4, and beam 6 associated with cell 1 and actually measure beam 2, beam 4, and beam 6 associated with cell 1. Assume that the value of K is 2. During a performance monitoring process, the terminal device obtains the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 through actual measurement, and they are beam 4 and beam 6. (At this time, beams 4 and 6 form the second beam set.) The top two beams with the best beam measurement results among beams 2, 4, and 6 associated with cell 1 obtained through the prediction process are beams 2 and 6 (at this time, beams 2 and 6 form the first beam set). At this time, the beam included in the intersection of the first beam set and the second beam set is beam 6. If the third threshold is 75% and the ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is 50%, the terminal device determines that the current beam measurement result prediction behavior is invalid.

[0201] By determining the invalidity of the prediction result through condition 14, it is possible to ensure that the first model is in a high-precision working state. At the same time, the configuration of the third threshold can also make the performance monitoring requirements relatively relaxed, thereby avoiding the network equipment blindly deactivating the AI ​​function in use due to overly strict performance monitoring methods, thereby taking into account the reliability and flexibility of the wireless communication system.

[0202] In some implementations, condition 14 can be combined with other conditions to determine whether the prediction result is invalid. For example, condition 14 can be combined with condition 9, condition 14 can also be combined with condition 10, and condition 14 can also be combined with condition 12.

[0203] The judgment condition after combining condition 9 and condition 14 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than the first threshold, or the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than the third threshold, or, in other words, the beam measurement results corresponding to some beams contained in the first beam set are not up to standard, or a certain proportion of beam identifiers are not up to standard, indicating that the predicted beam measurement result is quite different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid.

[0204] The judgment condition after combining condition 10 and condition 14 is: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold, or the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than the third threshold, or the beam measurement result corresponding to some beams contained in the first beam set is not up to standard, or a certain proportion of beam identifiers are not up to standard, indicating that the predicted beam measurement result is quite different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the current prediction result is invalid.

[0205] The judgment condition after combining condition 12 and condition 14 is: the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is different from the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement result, or the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than the third threshold, or, in other words, the relative ranking of the beams contained in the first beam set does not meet the standard, or a certain proportion of the beam identifiers do not meet the standard, indicating that the predicted beam measurement result is quite different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the current prediction result is invalid. For example, assuming that the first beam set includes beam 2, beam 8, and beam 6, and the second beam set includes beam 2, beam 4, and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 6. If the intersection of the first beam set and the second beam set contains two beams, and the third threshold is 75%, and the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than 75%, then the terminal device determines that the current prediction result is invalid.

[0206] For condition 15, the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result does not belong to the second beam set, or in other words, the second beam set does not include the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result, indicating that the predicted beam measurement result is quite different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid.

[0207] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 4, the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result is beam 6, and beam 6 is not included in the second beam set, then the terminal device can determine that the prediction result is invalid.

[0208] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -99dBm, and -103dBm for beams 2, 4, and 6 associated with cell 1, respectively. The prediction results for beams 2, 4, and 6 associated with cell 1 are -100dBm, -101dBm, and -99dBm, respectively, and K is 2. The ranking of the beam sets associated with cell 1 obtained through the prediction process shows that the two best predicted beams are beams 2 and 6, respectively. This means that the first beam set includes beams 2 and 6. The terminal device obtains, through actual measurement, the top two beams with the best beam measurement results among beams 2, 4, and 6 associated with cell 1, as beams 2 and 4 (at this point, beams 2 and 4 form the second beam set). The beam with the best beam measurement result determined based on the predicted beam measurement result among the beams in the first beam set is beam 6, which does not belong to the second beam set. Therefore, the terminal device can determine that this prediction result is invalid.

[0209] By determining the invalidity of the prediction result through condition 15, it can be ensured that the beam with the best predicted beam measurement result belongs to the top K beams with the best actual beam measurement result, reflecting the accuracy of the prediction result within an acceptable error range, which is conducive to the network equipment to correctly perform resource scheduling operations related to the best beam (for example: beam management scheduling, configuration of non-contention-based random access resources), thereby improving the reliability of the wireless communication system.

[0210] In some implementations, condition 15 can be used in combination with other conditions to determine whether the prediction result is invalid. For example, condition 15 can be combined with condition 9.

[0211] Taking the combination of condition 15 and condition 9 as an example, the judgment condition is: the beam with the best beam measurement result determined based on the predicted beam measurement result of the beam in the first beam set does not belong to the second beam set, or the absolute value of the difference between the predicted beam measurement result corresponding to the best beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than the first threshold, or in other words, the beam measurement result corresponding to the best beam in the first beam set does not meet the accuracy standard, or the second beam set does not contain the beam with the best beam measurement result determined based on the predicted beam measurement result in the first beam set. This implementation method indicates that the beam measurement result corresponding to the predicted best beam differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the current prediction result is invalid.

[0212] For example, assuming the first beam set includes beams 2 and beam 6, and the second beam set includes beams 2 and beam 4, the beam in the first beam set with the best beam measurement result, determined based on the predicted beam measurement results, is beam 2, and belongs to the second beam set. However, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is greater than a first threshold, the terminal device may determine that the current prediction result is invalid.

[0213] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -104dBm, and -103dBm for beams 2, 4, and 6 associated with cell 1, respectively. The terminal device obtains prediction results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively. K is 2, and the first threshold is 1dB. According to the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6. The terminal device obtains the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process, which are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the second beam set). The beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result is beam 2, which belongs to the second beam set. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (greater than the first threshold value), which does not meet the judgment of the combination of conditions 15 and 9. Therefore, the terminal device can determine that the prediction result is invalid.

[0214] For condition 16, the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result does not belong to the first beam set, or in other words, the first beam set does not include the beam with the best beam measurement result determined based on the actual beam measurement result in the second beam set, which means that the top K beams with the best predicted beam measurement results do not include the beam with the best actual beam measurement result, that is, the beam with the best actual beam measurement result cannot be predicted relatively accurately. Therefore, the terminal device can determine that the prediction result is invalid.

[0215] For example, assuming that the first beam set includes beam 2 and beam 4, and the second beam set includes beam 2 and beam 6, the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result is beam 6, and beam 6 does not belong to the first beam set, the terminal device can determine that the prediction result is invalid.

[0216] For example, assume that the network device configures a terminal device to measure Beams 1, 3, and 5 associated with Cell 1, and predict Beams 2, 4, and 6 associated with Cell 1. At time t, the network device configures the terminal device to both predict and actually measure Beams 2, 4, and 6 associated with Cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -99dBm, -103dBm, and -97dBm for Beams 2, 4, and 6 associated with Cell 1, respectively. The prediction results of -99dBm, -100dBm, and -102dBm for Beams 2, 4, and 6 associated with Cell 1, respectively, and K is 2. The ranking of the beam sets associated with Cell 1 obtained through the prediction process shows that the two best predicted beams are Beams 2 and 4, respectively. This means that the first beam set includes Beams 2 and 4. The terminal device obtains the best beam measurement results for beams 2, 4, and 6 associated with cell 1 through actual measurement. The first two beams are beams 2 and 6 (beams 2 and 6 now form the second beam set). The beam in the second beam set with the best beam measurement result, determined based on the actual beam measurement results, is beam 6, which does not belong to the first beam set. Therefore, the terminal device can determine that the current prediction result is invalid.

[0217] By determining the invalidity of the prediction result through condition 16, it can be ensured that the best beam of the actual beam measurement beam is accurately predicted within an acceptable error range, which is conducive to the network equipment to correctly perform resource scheduling operations related to the best beam (for example: beam management scheduling, configuration of non-contention-based random access resources), thereby improving the reliability of the wireless communication system.

[0218] In some implementations, condition 16 can be used in combination with other conditions to determine whether the prediction result is invalid. For example, condition 16 can be combined with condition 9.

[0219] Taking the combination of condition 16 and condition 9 as an example, the judgment condition is: the beam with the best beam measurement result determined based on the actual beam measurement result in the second beam set does not belong to the first beam set, or the absolute value of the difference between the predicted beam measurement result corresponding to the best beam in the second beam set and the actual beam measurement result corresponding to the same beam is greater than the first threshold, or the accuracy of the predicted beam measurement result corresponding to the best beam in the second beam set does not meet the standard, or the first beam set does not contain the beam with the best beam measurement result determined based on the actual beam measurement result in the second beam set. This implementation method indicates that the beam with the best actual beam measurement result cannot be accurately predicted within the error range or the accuracy of the predicted beam measurement result of the beam with the best actual beam measurement result does not meet the standard. Therefore, the terminal device can determine that the current prediction result is invalid.

[0220] For example, assuming that the first beam set includes beams 2 and 6, and the second beam set also includes beams 2 and 6, the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result is beam 2, which belongs to the first beam set. However, if the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is greater than a first threshold, the terminal device may determine that the current prediction result is invalid.

[0221] For example, assume that the network device configures a terminal device to measure beams 1, 3, and 5 associated with cell 1, and predict beams 2, 4, and 6 associated with cell 1. At time t, the network device configures the terminal device to both predict and actually measure beams 2, 4, and 6 associated with cell 1. During a performance monitoring process, the terminal device obtains actual measurement results of -97dBm, -104dBm, and -103dBm for beams 2, 4, and 6 associated with cell 1, respectively. The terminal device obtains prediction results of -99dBm, -102dBm, and -100dBm for beams 2, 4, and 6 associated with cell 1, respectively. K is 2, and the first threshold is 1dB. According to the ranking of the beam sets associated with cell 1 obtained during the prediction process, it can be seen that the two best beams predicted this time are beam 2 and beam 6, that is, the first beam set includes beam 2 and beam 6. The terminal device obtains the top two beams with the best beam measurement results among beam 2, beam 4, and beam 6 associated with cell 1 through the actual measurement process, which are beam 2 and beam 6 (at this time, beam 2 and beam 6 form the second beam set). The beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result is beam 2, which belongs to the first beam set. The absolute value of the difference between the predicted result and the actual measurement result of beam 2 is equal to 2dB (greater than the first threshold value), which does not meet the judgment of the combination of conditions 16 and 9. Therefore, the terminal device can determine that the prediction result is invalid.

[0222] The above conditions can be used individually or in combination. For example, conditions 9 and 12 can be combined, conditions 9 and 11 can be combined, or conditions 9, 11, and 12 can be combined. Another example is conditions 10 and 11, conditions 10 and 12 can be combined, or conditions 10, 11, and 12 can be combined.

[0223] Condition 10, condition 9 and condition 12 are combined, condition 10, condition 9 and condition 11 are combined, and condition 10, condition 9, condition 11 and condition 13 are combined.

[0224] Condition 9 can be combined with Condition 12 to determine the following: the absolute value of the difference between the predicted beam measurement result corresponding to at least one beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than a first threshold; or the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is different from the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement result; or, in other words, the beam measurement results corresponding to the beams included in the first beam set do not meet the accuracy standard or the relative ranking of the beams does not meet the standard. In other words, as long as either Condition 12 or Condition 9 is met, it indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the predicted result is invalid.

[0225] For example, assuming that the first beam set includes beam 2 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, the terminal device can determine that the prediction result is invalid.

[0226] The combined determination condition of conditions 9 and 11 is: the absolute value of the difference between the predicted beam measurement result corresponding to at least one beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than a first threshold, or the beams included in the first beam set are not completely identical to the beams included in the second beam set, or in other words, the beam measurement results corresponding to the beams included in the first beam set do not meet the accuracy requirements, or the beam identifiers included in the beam set do not meet the requirements. In other words, as long as either condition 9 or condition 11 is met, it indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the predicted result is invalid.

[0227] For example, assuming that the first beam set includes beam 2 and beam 6, and the second beam set includes beam 2 and beam 6, the beams included in the first beam set are the same as the beams included in the second beam set. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, the terminal device can determine that the prediction result is invalid.

[0228] The combined determination conditions of conditions 10 and 12 are: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams of the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold; or the beam arrangement order determined based on the predicted beam measurement result for the beams in the first beam set is different from the beam arrangement order determined based on the actual beam measurement result for the beams in the first beam set; or, in other words, the beam measurement results corresponding to some of the beams contained in the first beam set do not meet the accuracy standard or the relative ranking of the beams does not meet the standard. This implementation indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the current prediction result is invalid.

[0229] The combined determination conditions of conditions 10 and 11 are: the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the number of beams at the first threshold, and the ratio of the number of beams contained in the first beam set or the second beam set is less than the second threshold; or the beams contained in the first beam set are not completely identical to the beams contained in the second beam set; or, in other words, the beam measurement results corresponding to some beams contained in the first beam set do not meet the accuracy requirements, or the identifiers of some beams contained in the beam set do not meet the requirements. This indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, that is, the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the current prediction result is invalid.

[0230] The combined determination conditions of conditions 10, 9, and 12 are: the absolute value of the difference between the predicted beam measurement results corresponding to the first m best beams in the first beam set and the actual beam measurement results corresponding to the same beams is greater than a first threshold, or the absolute value of the difference between the predicted beam measurement results corresponding to the beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold; the ratio of the number of beams in the first beam set or the second beam set is less than a second threshold, or the beams in the first beam set are based on the predicted beam measurement results. The beam arrangement order determined by the measured beam measurement results is different from the beam arrangement order determined based on the actual beam measurement results of the beams in the first beam set. In other words, the beam measurement results corresponding to some beams included in the first beam set are not up to standard in accuracy, or the relative rankings are not up to standard. That is to say, as long as any one of conditions 9, 10 and 12 is met, it means that the predicted beam measurement result is significantly different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid, and m is an integer greater than or equal to 1.

[0231] For example, assuming that the first beam set includes beam 2, beam 4 and beam 6, the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is beam 2 → beam 4 → beam 6, and the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results is beam 2 → beam 4 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 75%, then the terminal device can determine that the current prediction result is invalid.

[0232] The combined determination conditions of conditions 10, 9, and 11 are: the absolute value of the difference between the predicted beam measurement results corresponding to the top m best beams in the first beam set and the actual beam measurement results corresponding to the same beams is greater than a first threshold; or the absolute value of the difference between the predicted beam measurement results corresponding to beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold; the ratio of the number of beams in the first beam set to the number of beams in the first beam set or the second beam set is less than a second threshold; or the beams in the first beam set are not completely identical to the beams in the second beam set; or the beam measurement results corresponding to some beams in the first beam set do not meet the accuracy standard, or the beams in the beam set do not meet the accuracy standard. In other words, if any one of conditions 10, 9, and 11 is met, it indicates that the predicted beam measurement result differs significantly from the actual beam measurement result, i.e., the predicted beam measurement result is not accurate. Therefore, the terminal device can determine that the predicted result is invalid.

[0233] For example, assuming that the first beam set includes beam 2, beam 4, and beam 6, and the second beam set includes beam 2, beam 4, and beam 6, and the beams included in the first beam set are the same as the beams included in the second beam set. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to a first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 75%, then the terminal device can determine that the current prediction result is invalid.

[0234] The combined determination conditions of Condition 10, Condition 9, Condition 11, and Condition 13 are as follows: the absolute value of the difference between the predicted beam measurement results corresponding to the top m best beams in the first beam set and the actual beam measurement results corresponding to the same beams is greater than a first threshold; or the absolute value of the difference between the predicted beam measurement results corresponding to the beams in the first beam set and the actual beam measurement results corresponding to the same beams is less than or equal to the first threshold; the ratio of the number of beams included in the first beam set and the number of beams included in the first beam set or the second beam set is less than a second threshold; or the beams included in the first beam set are not completely identical to the beams included in the second beam set; or the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; or in other words, the beam measurement result accuracy of some beams included in the first beam set does not meet the standard; or the beam identifiers included in the beam set do not meet the standard; or the absolute ranking of the beams does not meet the standard. That is to say, as long as any one of conditions 10, 9, 11 and 13 is met, it means that the predicted beam measurement result is significantly different from the actual beam measurement result, that is, the predicted beam measurement result is not very accurate. Therefore, the terminal device can determine that the prediction result is invalid.

[0235] For example, assume that the first beam set includes beam 2, beam 4, and beam 6, and the second beam set includes beam 2, beam 4, and beam 6. The beams included in the first beam set are the same as the beams included in the second beam set. The beam arrangement order of the beams in the first beam set, determined based on the predicted beam measurement results, is beam 2 → beam 4 → beam 6. The beam arrangement order of the beams in the second beam set, determined based on the actual beam measurement results, is beam 2 → beam 4 → beam 6. If the absolute value of the difference between the predicted beam measurement result corresponding to beam 2 and the actual beam measurement result corresponding to beam 2 is less than or equal to a first threshold, the absolute value of the difference between the predicted beam measurement result corresponding to beam 4 and the actual beam measurement result corresponding to beam 4 is less than or equal to the first threshold, and the absolute value of the difference between the predicted beam measurement result corresponding to beam 6 and the actual beam measurement result corresponding to beam 6 is greater than the first threshold, and the second threshold is 75%, then the terminal device may determine that the predicted result is invalid.

[0236] In this example, the terminal device determines whether the prediction result based on the first model is invalid when the second condition is met, and then the terminal device sends first information for the first model to the network device. The first information includes information related to the invalidity of the prediction result. By sending information related to the invalidity of the prediction result to the network device, the network device can clarify the performance of the first model, thereby improving the reliability of the wireless communication system.

[0237] The sending of the first information may be triggered by a first event, or in other words, when the first event is triggered, the terminal device sends the first information to the network device.

[0238] The first event may be associated with one or more of the following information: a first timer; the number of times the validity of the predicted beam measurement result is judged; a first moment; the number of times the prediction result is invalid; the number of times the first information is sent.

[0239] The first event is described below. It may include one or more of the following: a first timer expiration; the number of times the validity of the predicted beam measurement result is determined to have reached a fourth threshold; the first moment arrives; the number of consecutive invalid prediction results determinations reaches a fifth threshold; or the number of first information transmissions does not reach a sixth threshold.

[0240] In some implementations, the first event may include a first timer expiration. When the first timer expires, the first event may be triggered. The first timer may be a periodic reporting timer or a single reporting timer.

[0241] Taking the single reporting timer as an example, a single reporting can be understood as a single reporting, that is, based on the first timer, the terminal device only sends the first information once. When the first timer times out, that is, when the maximum running time corresponding to the first timer is reached, the terminal device sends the first information to the network device.

[0242] The duration of the first timer is obtained by protocol default, or may be configured by the network device to the terminal device. For example, the network device may configure the duration of the first timer to the terminal device through dedicated signaling or a system broadcast message.

[0243] In some embodiments (applicable to the above-mentioned single reporting timer), the start condition of the first timer may include the terminal device receiving third configuration information sent by the network device, where the third configuration information includes a duration parameter for configuring the first timer. In other words, if the network device configures the duration parameter of the first timer for the terminal device, the terminal device starts the first timer, and when the first timer times out, the terminal device sends the first information to the network device, where the duration of the first timer may be the duration indicated by the duration parameter.

[0244] In other embodiments (adapted to the above-mentioned single reporting timer), the starting condition of the first timer may include that the terminal device continuously determines that the prediction result is invalid for k1 times. That is, if the terminal device continuously determines that the prediction result is invalid for k1 times, the terminal device starts the first timer, and when the first timer times out, the terminal device sends the first information to the network device. Optionally, the stopping condition of the first timer may include that the terminal device continuously determines that the prediction result is valid for k2 times during the operation of the first timer. That is, if the terminal device continuously determines that the prediction result is valid for k2 times during the operation of the first timer, the terminal device stops the operation of the first timer, wherein k1 and k2 are both integers greater than or equal to 1, the duration of the first timer may be the duration indicated by the duration parameter, and the parameters k1 and k2 are obtained by protocol default, or may be configured to the terminal device by the network device, for example, the network device may configure the parameters k1 and k2 to the terminal device through dedicated signaling or through a system broadcast message.

[0245] In some implementations, the network device may send the third configuration information to the terminal device through dedicated signaling or through a system broadcast message.

[0246] The first timer may also be a periodic reporting timer. Whenever the first timer reaches a corresponding maximum running time or times out, the terminal device sends the first information to the network device. After the first timer times out, the first timer may be restarted, so that the terminal device can periodically send the first information to the network device.

[0247] The duration of the first timer is obtained by protocol default, or may be configured by the network device to the terminal device. For example, the network device may configure the duration of the first timer to the terminal device through dedicated signaling or a system broadcast message.

[0248] In some embodiments, the starting conditions of the first timer include one or more of the following: the terminal device receives the third configuration information sent by the network device, and the third configuration information includes the duration parameter for configuring the first timer; the first timer times out; the terminal device sends the first information to the network device; the number of times the first information is sent does not exceed the sixth threshold; the number of consecutive determinations that the prediction results are invalid reaches the fifth threshold.

[0249] For example, if the terminal device receives the third configuration information sent by the network device, the terminal device starts the first timer for the first time, and the value of the first timer is equal to the duration indicated by the third configuration information. When the first timer times out, and the terminal device has sent the first information to the network device, the terminal device starts the first timer again.

[0250] Optionally, if the network device further limits the maximum number of reports Q for periodically reporting the first information (for example, configured to the terminal device through dedicated signaling), then each time the first timer times out and the terminal device sends the first information to the network device, the terminal device also needs to additionally determine whether the total number of times P of the first information that the terminal device has reported in the previous process, including the first information reported this time, is equal to the Q value. If the P value is less than the Q value, the first timer is started again, and the above behavior is performed again (the first information is reported after the first timer times out and the latest P value is determined to be equal to Q); if the P value is equal to the Q value, the first timer is no longer started because the periodic event has been executed, where P and Q are both positive integers greater than or equal to 1.

[0251] In some implementations, when the number of times the terminal device determines the validity of the predicted beam measurement result reaches a fourth threshold, the terminal device sends the first information to the network device. In other words, each round of performance monitoring process needs to meet the fourth threshold when the number of times the validity of the predicted beam measurement result is determined can trigger a performance monitoring result (i.e., the first information) to be reported. By limiting the frequency of the terminal device reporting the performance monitoring result by the number of times the terminal device determines whether the prediction result is valid, the problem of excessive reporting overhead caused by the terminal device irregularly sending the performance monitoring result can be avoided.

[0252] For example, if the network device configures the terminal device to determine whether a prediction result is valid once every four predictions, and the fourth threshold is set to 5, the terminal device will trigger the first information reporting only after performing 20 beam measurement result predictions. The terminal device will determine whether a prediction result is valid once during the 4th, 8th, 12th, 16th, and 20th predictions, respectively. Therefore, during the 20 beam measurement result predictions, the terminal device will determine whether a prediction result is valid five times in total.

[0253] The fourth threshold may be agreed upon by default, or configured by the network device to the terminal device through dedicated signaling, or configured by the network device to the terminal device through a system broadcast message.

[0254] In some implementations, reporting of the first information can be triggered by the number of times the terminal device sends the first information falling short of a sixth threshold. Each time the terminal device sends the first information to the network device, the performance monitoring process does not cease. Instead, the terminal device determines whether to continue the performance monitoring process by comparing the number of times the first information has been sent with the sixth threshold.

[0255] For example, if the terminal device receives the Q1 configuration sent by the network as the sixth threshold, after the terminal device sends the performance monitoring result (i.e., the first information) to the network device for the first time, it will not stop the performance monitoring process, but will continue to perform (Q1-1) first information reporting according to the indication of the Q1 value. Each time the terminal device sends the first information to the network device, it needs to calculate the number of times the information has been reported (hereinafter referred to as P1) and compare it with Q1. The embodiment of the present application does not specifically limit the comparison method.

[0256] As an example, the terminal device can compare with Q1 in the following manner: each time the terminal device sends the first information to the network device, it needs to calculate whether the number of times P1 of the first information reported by the terminal device since the first information was reported is equal to Q1. If P1 is less than Q1, the terminal device continues to perform the performance monitoring process; if P1 is equal to Q1, it indicates that the entire performance monitoring task has been completed and the performance monitoring process is no longer performed. In this method, the terminal device reports the first information a total of Q1 times.

[0257] In some implementations, the first event is a composite event composed of multiple single events, such as combining the event of the number of first information transmissions not reaching the sixth threshold with other events. For example, the first event may include the number of first information transmissions not reaching the sixth threshold and the number of validity determinations of the predicted beam measurement results reaching the fourth threshold. For another example, the first event may include the number of first information transmissions not reaching the sixth threshold and the expiration of the first timer.

[0258] Take the case where the number of times the first information is sent does not reach the sixth threshold and the number of times the validity of the predicted beam measurement result is judged reaches the fourth threshold as an example. If the network device configures the terminal device to determine whether the prediction result is valid once every 4 prediction processes, the fourth threshold is 5, and the sixth threshold is 3, then the terminal device will trigger the first first information report only after executing 20 beam measurement result predictions (corresponding to the 1st to 20th predictions after the start of the performance monitoring task); then, the terminal device will continue to execute 20 beam measurement result predictions (corresponding to the 21st to 40th predictions after the start of the performance monitoring task) to trigger the second first information report; and finally, it will trigger the third (i.e., the last) first information report only after executing 20 beam measurement result predictions (corresponding to the 41st to 60th predictions after the start of the performance monitoring task). In this method, since the sixth threshold is 3, the terminal device reports the first information a total of 3 times.

[0259] Take the case where the number of times the first information is sent does not reach the sixth threshold and is combined with the first timer as an example. If the terminal device receives the duration parameter of the periodic timer configured by the network device through dedicated signaling, and the network device further limits the maximum number of information reports Q for periodic events, then each time the first timer T times out and the terminal device sends the first information to the network device, the terminal device needs to additionally calculate whether the total number of times P of the first information reported by the terminal device in the previous process after the first information is reported this time is equal to the Q value. If the P value is less than the Q value, the first timer T is started again and the above behavior is executed again; if the P value is equal to the Q value, the first timer T is no longer started because the periodic event has been executed, where P and Q are both positive integers greater than or equal to 1.

[0260] The fifth threshold may be agreed upon by default, or configured to the terminal device by the network device through dedicated signaling, or configured to the terminal device through a system broadcast message.

[0261] In some implementations, when a first moment arrives (hereinafter referred to as t1), the terminal device sends the first information to the network device. The first moment can be understood as a specific moment or an absolute moment. When the first moment arrives, the terminal device sends the first information to the network device. By triggering the terminal device to send the performance monitoring results at a specific moment, the terminal device can avoid irregular transmission of the first information, thereby reducing the overhead caused by information reporting.

[0262] In some implementations, the network device may send second configuration information to the terminal device, and the second configuration is used to determine whether the first event is triggered. The second configuration information includes parameter information for determining whether the first event is triggered, and the parameter information may include one or more of the following information: the duration of the first timer, the fourth threshold, the first moment, the fifth threshold, and the sixth threshold. For example, the terminal device may receive the second configuration information sent by the network device, and the second configuration information includes the duration of the first timer. The duration of the first timer can be defined in the UTC time format or in a relative time manner, wherein the relative time manner includes one or more of a specified system frame number, a subframe number, a time slot number, and a symbol number. Configuring parameter information through the second configuration information is more flexible to implement.

[0263] For example, when the terminal device receives the time t1 configured for the first time, when the time t1 is reached, the terminal device sends the first information to the network device.

[0264] In some implementations, when the number of times the terminal device continuously determines that the prediction result is invalid reaches a fifth threshold, the terminal device sends the first information to the network device. That is, when the number of times the prediction result is continuously determined to be invalid reaches the fifth threshold, the terminal device can send the first information to the network device at any time. By triggering the reporting of the first information in this way, on the one hand, the frequency of the terminal device reporting the first information can be limited, thereby avoiding the information reporting overhead caused by the terminal device irregularly sending the first information; on the other hand, when the terminal device continuously determines that the prediction result is invalid, it means that the operating performance of the AI ​​model has significantly declined, and by promptly notifying the network device, the network device is triggered to perform some actions to improve communication performance. For example, the network device deactivates the currently executed AI function and falls back to traditional communication technology to ensure that the communication performance remains in an effective state, thereby improving the reliability of the wireless communication system.

[0265] In other implementations, within the first time window, when the number of times the terminal device continuously determines that the prediction result is invalid reaches a fifth threshold, the terminal device may also send the first information to the network device.

[0266] The fifth threshold may be agreed upon by default, or configured to the terminal device by the network device through dedicated signaling, or configured to the terminal device through a system broadcast message.

[0267] The first time window length configuration may be agreed upon by default, or configured by the network device to the terminal device through dedicated signaling, or configured to the terminal device through a system broadcast message.

[0268] The above-mentioned first events can be used alone or in combination with each other, and the embodiments of the present application do not specifically limit this.

[0269] In some implementations, before the terminal device sends the first information to the network device, the terminal device may receive fifth configuration information sent by the network device. The fifth configuration information is used to configure relevant parameters of the reference signal, which may include the first period parameter and / or the third beam set information.

[0270] The third beam set information is the set of beams that the terminal device needs to predict based on the beam measurement result. This information can be understood as indicating the range of beams included in the beam measurement result prediction. A beam range can also be understood as a beam set. A beam set can include both the beam set predicted by the beam measurement result and the beam set actually required for measurement.

[0271] For example, the network indicates through the third beam set information that the beam sets for the predicted behavior of the terminal device beam measurement results are beam 2, beam 4 and beam 6, and at the same time indicates through the fourth beam set that the beam sets that actually need to be measured are beam 1, beam 3 and beam 5.

[0272] The first period parameter is used to indicate the transmission period of the reference signal associated with the beams in the third beam set. The second period parameter is used to indicate the transmission period of the reference signal associated with the beams in the fourth beam set. The fourth beam set is a set of beam components for which the beam measurement results need to be obtained through an actual measurement process. That is, the beam measurement results of the corresponding beams are always obtained through the actual measurement process of the terminal device.

[0273] The relevant parameters of the reference signal may include a first period parameter and a second period parameter.

[0274] In some implementations, the first and second periodic parameters can be defined using different parameters. Generally, the first periodic parameter takes a greater value than the second periodic parameter. For example, the first periodic parameter can be an integer multiple of the second periodic parameter. In this manner, the measurement reference signal associated with the first periodic parameter can be configured at either a terminal device or cell granularity. The following describes these two implementations.

[0275] In one implementation, the measurement reference signal associated with the predicted beam associated with the first period parameter is nominally (from the perspective of a specific terminal device) and actually (from the perspective of the actual transmission of the reference signal by the network device) configured according to the terminal device granularity. In other words, the measurement reference signal associated with the predicted beam associated with the first period parameter is only periodically sent in the time domain constrained by the first period parameter, and cannot be actually measured by the terminal device using AI function (hereinafter referred to as the first type of terminal device) outside the time domain constrained by the first period parameter.

[0276] For example, suppose the network device configures the terminal device to measure frequency 1. The network device further indicates that the beam set actually required to be measured by the terminal device at frequency 1 is Beam 1, Beam 3, and Beam 5 associated with frequency 1. The network device also indicates that the transmission period of the measurement reference signal associated with the beam set actually required to be measured by the terminal device (configured via the second period parameter) is 40 ms. In other words, the terminal device can actually measure a round of beam measurement results corresponding to Beam 1, Beam 3, and Beam 5 every 40 ms at frequency 1. If the first period parameter is 160 ms, the terminal device can actually measure a round of beam measurement results corresponding to Beam 2, Beam 4, and Beam 6 every 160 ms at frequency 1. Because the network device does not actually transmit the measurement reference signal associated with the predicted beam outside the time domain constrained by the first period parameter, the beam measurement results corresponding to Beam 2, Beam 4, and Beam 6 outside the time domain constrained by the first period parameter cannot be actually measured (even if the beam measurement results corresponding to Beam 1, Beam 3, and Beam 5 can be actually measured) and can only be obtained through inference.

[0277] By adopting the solution of this example, the resource overhead of the network device in sending the measurement reference signal associated with the predicted beam can be saved.

[0278] In another implementation, the measurement reference signal associated with the predicted beam associated with the first periodic parameter is nominally configured according to the terminal device granularity but is actually configured according to the cell granularity. In other words, in addition to being periodically sent in the time domain constrained by the first periodic parameter, the measurement reference signal associated with the predicted beam associated with the first periodic parameter can also be actually measured by the first type of terminal device outside the time domain constrained by the first periodic parameter. However, because the terminal device only performs performance monitoring and judgment actions in the time domain constrained by the first periodic parameter and there is no need to perform performance monitoring and judgment actions at other times, the first type of terminal device will not actively measure the measurement reference signal associated with the predicted beam outside the time domain constrained by the first periodic parameter (even if it can be actually measured). In other words, the first type of terminal device only actually measures the beam measurement result corresponding to the predicted beam in the time domain constrained by the first periodic parameter.

[0279] However, for terminal devices that do not use the AI ​​function (hereinafter referred to as the second type of terminal devices), since the second type of terminal devices do not perform the beam measurement result prediction function and can only rely on the actual measurement process to obtain the beam measurement results corresponding to each beam of the cell, the second type of terminal devices will attempt to receive the measurement reference signal associated with any beam actually sent by the cell. To address this situation, the embodiment of the present application configures different measurement configurations for different types of terminal devices by the network device to solve the coexistence problem of different types of terminal devices in the same cell.

[0280] For example, for the first type of terminal device, the network device configures the following parameters for the terminal device: the beam set that actually needs to be measured (beam 1, beam 3 and beam 5), the second period parameter of the measurement reference signal sending period parameter associated with the beam set parameter that actually needs to be measured, the predicted beam set parameter (beam 2, beam 4 and beam 6) and the first period parameter of the measurement reference signal sending period parameter associated with the predicted beam set parameter. The reference signal associated with the predicted beam set sent in the time domain constrained by the first period parameter is used for the terminal device to perform performance monitoring.

[0281] For the second type of terminal device, the network device configures the following parameters for the terminal device: the beam set parameters that actually need to be measured (beam 1, beam 2, beam 3, beam 4, beam 5 and beam 6), and the measurement reference signal sending period parameters associated with the beam set parameters that actually need to be measured (i.e., the second period parameters).

[0282] Although the network device configures different measurement configurations for different types of terminal devices, since the measurement reference signals are actually sent at the cell granularity, from the network device's perspective, the measurement reference signals associated with these beams are actually always being sent (that is, beam 1, beam 2, beam 3, beam 4, beam 5, and beam 6 are all being sent at all times). It's just that different types of terminal devices selectively perform measurement behaviors based on the measurement configurations they obtain. For example, the first type of terminal device measures the measurement reference signals associated with the predicted beam set parameters at different periods, while the second type of terminal device measures the measurement reference signals associated with all actually sent beams at the same period.

[0283] The solution of this example can effectively solve the coexistence problem of different types of terminal devices in the same cell, thereby avoiding the impact of the introduction of AI functions on the functions of existing non-AI terminal devices.

[0284] In other implementations, the first period parameter and the second period parameter can be defined by the same parameter, or in other words, the first period parameter and the second period parameter can be defined by the same parameter. That is to say, the transmission period of the measurement reference signals associated with all beams associated with any frequency point (including beams that need to be actually measured and beams that need to be predicted) is the same. It can be understood that the network equipment configures the transmission period parameters corresponding to all measurement reference signals according to the frequency strength, and correspondingly, the parameter is applicable to any beam sent on the corresponding frequency point. In this way, the measurement requirements of the first type of terminal equipment and the second type of terminal equipment can be met at the same time.

[0285] The following takes all beams associated with frequency 1 as an example to describe in detail the different configurations of the network device for the first type of terminal devices and the second type of terminal devices.

[0286] For the first type of terminal devices, the actual measurement beam range configured by the network device includes beam 1, beam 3 and beam 5, and the configured beam range that needs to be predicted includes beam 2, beam 4 and beam 6. Beam 1, beam 2, beam 3, beam 4, beam 5 and beam 6 are associated with the same measurement reference signal sending period parameter.

[0287] For the second type of terminal devices, the actual measurement beam range configured by the network device includes beam 1, beam 2, beam 3, beam 4, beam 5, and beam 6. These beams are associated with the same measurement reference signal sending period parameter. The second type of terminal devices can obtain the beam measurement results corresponding to these beams based on the traditional actual beam measurement process.

[0288] From the perspective of the network device, all beam-associated measurement reference signals will be periodically sent according to the same measurement reference signal transmission period parameter requirement. However, for the first type of terminal devices, only the beam range that needs to be actually measured will be periodically measured, that is, beam 1, beam 3, and beam 5. The measurement of beam 2, beam 4, and beam 6 depends on the performance monitoring execution process. For example, the terminal device can be based on implementation selection, and for example, the terminal device can be determined based on the performance period parameter configured by the network device. The embodiments of the present application do not specifically limit this.

[0289] By receiving configuration information from the network device, the terminal device can assist in obtaining the ground truth measurement result label corresponding to the predicted beam, making it possible for the terminal device to determine whether the prediction result is valid. In other words, this can improve the effectiveness of the terminal device's judgment of the prediction result.

[0290] In some implementations, the terminal device may send the first capability information to the network device. By sending the first capability information to the network device, the network device may be informed whether the terminal device supports performance monitoring of the first model.

[0291] The capability information may include various contents, which are not specifically limited in the embodiments of the present application. The capability information may be indicated at one or more of the following information granularities: carrier granularity, band granularity, band combination granularity, and frequency range granularity.

[0292] The terminal device may report the first capability information according to a single granularity, such as reporting according to carrier granularity, reporting according to frequency band granularity, reporting according to frequency band combination granularity, or reporting according to frequency range granularity. The terminal device may also report the first capability information according to a composite granularity consisting of at least two single granularities, such as reporting according to frequency band granularity and frequency band combination granularity, reporting according to carrier granularity and frequency band granularity, reporting according to carrier granularity and frequency band combination granularity, reporting according to carrier granularity and frequency band granularity and frequency band combination granularity, reporting according to frequency band granularity and frequency range granularity, reporting according to carrier granularity and frequency range granularity, reporting according to carrier granularity and frequency band granularity and frequency range granularity.

[0293] The first capability information is used to indicate whether the terminal device supports the performance monitoring function, which is used to monitor the performance of the AI ​​function in the beam measurement result prediction.

[0294] The method embodiment of the present application is described in detail above in conjunction with Figures 1 and 2. The device embodiment of the present application is described in detail below in conjunction with Figures 3 to 5. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment. Therefore, for parts not described in detail, reference can be made to the above method embodiment.

[0295] Figure 3 is a structural diagram of a terminal device provided by an embodiment of the present application. The terminal device 300 shown in Figure 3 may include a sending unit 310. The sending unit 310 may be used to send first information to a network device, wherein the first information includes a performance monitoring result for a first model, and the first model is used to predict a beam measurement result, wherein the first information includes any one of the following information: one or more first indication information, wherein one first indication information of the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, wherein the second indication information is used to indicate first proportion information or to indicate the proportion interval to which the first proportion information belongs, wherein the first proportion information includes the proportion of the number of times the prediction result is valid to the total number of predictions, or the proportion of the number of times the prediction result is invalid to the total number of predictions; information used to calculate the second proportion information, wherein the second proportion information includes the proportion of the number of times the prediction result is valid to the total number of predictions, or the proportion of the number of times the prediction result is invalid to the total number of predictions.

[0296] In some implementations, the information used to calculate the second ratio information includes any one of the following information: the number of times the prediction results are valid and the number of times the prediction results are invalid; the number of times the prediction results are valid and the total number of predictions; the number of times the prediction results are invalid and the total number of predictions.

[0297] In some implementations, if the second indication information is used to indicate the proportion interval to which the first proportion information belongs, the terminal device 300 also includes: a determination unit, used to determine a first association relationship, the first association relationship including a correspondence between the value of the second indication information and the proportion interval; the determination unit determines the proportion interval to which the first proportion information belongs based on the first association relationship.

[0298] In some implementations, the validity of the prediction result is related to one or more of the following information: predicted beam measurement results; actual beam measurement results; beam order determined based on the predicted beam measurement results; beam set determined based on the predicted beam measurement results; beam order determined based on the actual beam measurement results; beam set determined based on the actual beam measurement results.

[0299] In some implementations, when a first condition is met, the terminal device further includes: a determination unit for determining whether the prediction result is valid, wherein the first condition includes one or more of the following: the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold; the number of beams for which the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to a second threshold; the beams included in the first beam set are the same as the beams included in the second beam set; the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement result is the same as that of the beams in the first beam set. The beams in the first beam set have the same beam arrangement order determined based on the actual beam measurement results; the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is greater than or equal to a third threshold; the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set; the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result belongs to the first beam set; wherein, the first beam set is a beam set determined based on the predicted beam measurement result, and the second beam set is a beam set determined based on the actual beam measurement result.

[0300] In some implementations, when a second condition is met, the determination unit is used to determine that the prediction result is invalid, and the determination unit is used to determine that the prediction result is invalid, and the second condition includes one or more of the following: the absolute value of the difference between the predicted beam measurement result corresponding to at least one beam in the first beam set and the actual beam measurement result corresponding to the same beam is greater than a first threshold; the absolute value of the difference between the predicted beam measurement result corresponding to the beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to the first threshold; the ratio of the number of beams included in the first beam set or the second beam set is less than a second threshold; the beams included in the first beam set are not completely the same as the beams included in the second beam set; the beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from that in the first beam set; The beams in the beam set have different beam arrangement orders determined based on actual beam measurement results; the beam arrangement order of the beams in the first beam set determined based on predicted beam measurement results is different from the beam arrangement order of the beams in the second beam set determined based on actual beam measurement results; the ratio of the number of beams contained in the intersection of the first beam set and the second beam set to the number of beams contained in the second beam set is less than a third threshold; the beam in the first beam set with the best beam measurement result determined based on the predicted beam measurement result does not belong to the second beam set; the beam in the second beam set with the best beam measurement result determined based on the actual beam measurement result does not belong to the first beam set; wherein, the first beam set is a beam set determined based on the predicted beam result, and the second beam set is a beam set determined based on the actual beam measurement result.

[0301] In some implementations, the terminal device 300 also includes: a receiving unit for receiving first configuration information sent by the network device, the first configuration information including threshold information for determining whether the prediction result is valid, the threshold information including one or more of the following information: the first threshold, the second threshold, and the third threshold.

[0302] In some implementations, the first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results, where K is an integer greater than or equal to 1.

[0303] In some implementations, the receiving unit is configured to receive the parameter K sent by the network device.

[0304] In some implementations, the sending unit is used to send first information to the network device, including: when a first event is triggered, the sending unit is used to send the first information to the network device, and the first event is associated with one or more of the following information: a first timer; the number of times the validity of the predicted beam measurement results is judged; the first moment; the number of times the prediction results are invalid; the number of times the first information is sent.

[0305] In some implementations, the sending unit is used to send first information to the network device, including: when a first event is triggered, the sending unit is used to send the first information to the network device, and the first event includes one or more of the following: the first timer times out; the number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; the first moment arrives; the number of consecutive judgments that the prediction result is invalid reaches a fifth threshold; the number of times the first information is sent does not reach a sixth threshold.

[0306] In some implementations, the receiving unit is used to receive second configuration information sent by the network device, the second configuration information including parameter information for determining whether the first event is triggered, the parameter information including one or more of the following: the duration of the first timer, the fourth threshold, the first moment, the fifth threshold, and the sixth threshold.

[0307] In some implementations, the number of times the prediction result is continuously determined to be invalid reaches a fifth threshold includes: within the first time window, the number of times the prediction result is continuously determined to be invalid reaches the fifth threshold.

[0308] In some implementations, the start conditions of the first timer include one or more of the following: the terminal device receives the third configuration information sent by the network device, and the third configuration information includes a duration parameter for configuring the first timer; the first timer times out; the terminal device sends the first information to the network device; the number of times the first information is sent does not exceed the sixth threshold; the number of consecutive determinations that the prediction results are invalid reaches the fifth threshold.

[0309] In some implementations, the conditions for the first timer to stop running include: during the operation of the first timer, the number of consecutive times the prediction result is determined to be valid reaches a seventh threshold; or, during the operation of the first timer, the terminal device receives a third indication information sent by the network device, and the third indication information is used to update or delete the previously configured duration parameter of the first timer.

[0310] In some implementations, the terminal receiving unit is used to receive fourth configuration information sent by the network device, where the fourth configuration information includes the seventh threshold and / or the third indication information.

[0311] In some implementations, the receiving unit is used to receive fifth configuration information sent by the network device, and the fifth configuration information is used to configure relevant parameters of the reference signal, and the relevant parameters of the reference signal include a first period parameter and / or third beam set information, and the first period parameter is used to indicate the sending period of the reference signal associated with the beam in the third beam set, and the third beam set is a set of beam compositions that the beam measurement results need to be predicted by the terminal device.

[0312] In some implementations, the first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

[0313] In some implementations, the beam measurement result includes beam measurement results for one or more cells, where the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

[0314] In some implementations, the sending unit is used to send first capability information to the network device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

[0315] In some implementations, the first capability information is indicated at one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

[0316] Figure 4 is a structural diagram of a network device provided by an embodiment of the present application. The network device 400 shown in Figure 4 may include a receiving unit, 410. The receiving unit 410 is used to receive first information sent by a terminal device, the first information including a performance monitoring result for a first model, the first model being used to predict a beam measurement result, wherein the first information includes any one of the following information: one or more first indication information, wherein one first indication information in the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, wherein the second indication information is used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including the proportion of the number of valid prediction results to the total number of predictions, or including the proportion of the number of invalid prediction results to the total number of predictions; information used to calculate the second proportion information, the second proportion information including the proportion of the number of valid prediction results to the total number of predictions, or including the proportion of the number of invalid prediction results to the total number of predictions.

[0317] In some implementations, the information used to calculate the second ratio information includes any one of the following information: the number of times the prediction results are valid and the number of times the prediction results are invalid; the number of times the prediction results are valid and the total number of predictions; the number of times the prediction results are invalid and the total number of predictions.

[0318] In some implementations, if the second indication information is used to indicate the proportion interval to which the first proportion information belongs, the network device 400 also includes: a determination unit, used to determine a first association relationship, the first association relationship including a correspondence between the value of the second indication information and the proportion interval; the network device determines the proportion interval to which the first proportion information belongs based on the first association relationship.

[0319] In some implementations, the network device 400 further includes: a sending unit, configured to send first configuration information to the terminal device, where the first configuration information includes threshold information for determining whether the prediction result is valid.

[0320] In some implementations, the sending unit is used to send a parameter K to the terminal device, where the parameter K is the number of beams included in the first beam set and / or the second beam set, wherein the first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results, and the first beam set and / or the second beam set are used to determine whether the prediction result is valid.

[0321] In some implementations, the sending unit is used to send second configuration information to the terminal device, the second configuration information includes parameter information for determining whether a first event is triggered, the parameter information including one or more of the following: the duration of a first timer, a fourth threshold, a first moment, a fifth threshold, and one or more of a sixth threshold, wherein when the first event is triggered, the first information is sent by the terminal device to the network device, and the first event includes one or more of the following: the first timer times out; the number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; the first moment arrives; the number of consecutive judgments that the prediction result is invalid reaches a fifth threshold; the number of times the first information is sent does not reach the sixth threshold.

[0322] In some implementations, the sending unit is used to send third configuration information to the terminal device, where the third configuration information includes a duration parameter for configuring the first timer.

[0323] In some implementations, the sending unit is used to send fourth configuration information to the terminal device, the fourth configuration information includes a seventh threshold and / or third indication information, the seventh threshold is used to determine whether the first timer needs to stop running during the operation of the first timer, the third indication information is used to update or delete the previously configured duration parameter of the first timer, and the seventh threshold and / or the third indication information are used to determine whether the first timer needs to stop running.

[0324] In some implementations, the sending unit is used to send fifth configuration information to the terminal device, and the fifth configuration information is used to configure relevant parameters of the reference signal, and the relevant parameters of the reference signal include a first period parameter and / or third beam set information, and the first period parameter is used to indicate the sending period of the reference signal associated with the beam in the third beam set, and the third beam set information is a set of beam compositions that the terminal device needs to predict based on the beam measurement results.

[0325] In some implementations, the first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

[0326] In some implementations, the beam measurement result includes beam measurement results for one or more cells, where the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

[0327] In some implementations, the receiving unit is used to receive first capability information sent by the terminal device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

[0328] In some implementations, the first capability information is indicated at one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

[0329] FIG5 is a schematic block diagram of an apparatus for downlink transmission according to an embodiment of the present application. The dashed lines in FIG5 indicate that the unit or module is optional. Apparatus 500 may be used to implement the method described in the above method embodiment. Apparatus 500 may be a chip, a terminal, or a network device.

[0330] The apparatus 500 may include one or more processors 510. The processor 510 may support the apparatus 500 in implementing the methods described in the above method embodiments. The processor 510 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 another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), 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, etc.

[0331] The apparatus 500 may further include one or more memories 520. The memories 520 store programs that can be executed by the processor 510, causing the processor 510 to perform the methods described in the above method embodiments. The memories 520 may be independent of the processor 510 or integrated into the processor 510.

[0332] The apparatus 500 may further include a transceiver 530. The processor 510 may communicate with other devices or chips via the transceiver 530. For example, the processor 510 may transmit and receive data with other devices or chips via the transceiver 530.

[0333] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0334] The present 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 the present application, and the program causes a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0335] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided in the embodiments of the present application, and the computer program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0336] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0337] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0338] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0339] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0340] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0341] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0342] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0343] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0344] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0345] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0346] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0347] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part 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, the process or function described in the embodiment of the present application is generated in whole or in part. 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 computer-readable storage medium. 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 a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0348] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The terminal device sends first information to the network device, where the first information includes a performance monitoring result for a first model, where the first model is used to predict a beam measurement result, wherein the first information includes any one of the following information: One or more first indication information, wherein one first indication information among the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, where the second indication information is used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including a proportion of the number of valid prediction results to the total number of predictions, or a proportion of the number of invalid prediction results to the total number of predictions; Information used to calculate second proportion information, where the second proportion information includes the proportion of the number of times the prediction results are valid to the total number of predictions, or the proportion of the number of times the prediction results are invalid to the total number of predictions.

2. The method according to claim 1, characterized in that The information used to calculate the second ratio information includes any one of the following information: The number of times the prediction results were valid and the number of times the prediction results were invalid; The number of times the prediction results are valid and the total number of predictions; The number of invalid prediction results and the total number of predictions.

3. The method according to claim 1 or 2, characterized in that If the second indication information is used to indicate a proportion interval to which the first proportion information belongs, the method further includes: The terminal device determines a first association relationship, where the first association relationship includes a correspondence between a value of the second indication information and a proportional interval; The terminal device determines the proportion interval to which the first proportion information belongs based on the first association relationship.

4. The method according to any one of claims 1 to 3, characterized in that The validity of the prediction result is related to one or more of the following information: Predicted beam measurements; Actual beam measurement results; a beam order determined based on predicted beam measurements; A beam set determined based on predicted beam measurement results; Beam order based on actual beam measurement results; The beam set is determined based on actual beam measurement results.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: When a first condition is met, the terminal device determines that the prediction result is valid, where the first condition includes one or more of the following: An absolute value of a difference between a predicted beam measurement result corresponding to a beam in the first beam set and an actual beam measurement result corresponding to the same beam is less than or equal to a first threshold; The number of beams for which the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to a second threshold; The beams included in the first beam set are the same as the beams included in the second beam set; The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results; The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; A ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is greater than or equal to a third threshold; The beam in the first beam set having the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set; The beams in the second beam set having the best beam measurement result determined based on the actual beam measurement result belong to the first beam set; The first beam set is a beam set determined based on a predicted beam measurement result, and the second beam set is a beam set determined based on an actual beam measurement result.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: When the second condition is met, the terminal device determines that the prediction result is invalid, and the second condition includes one of the following: One or more kinds: An absolute value of a difference between a predicted beam measurement result corresponding to at least one beam in the first beam set and an actual beam measurement result corresponding to the same beam is greater than a first threshold; The number of beams for which the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is less than a second threshold; The beams included in the first beam set are not completely identical to the beams included in the second beam set; A beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from a beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results; A beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from a beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; A ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is less than a third threshold; The beam in the first beam set having the best beam measurement result determined based on the predicted beam measurement result does not belong to the second beam set; The beam in the second beam set having the best beam measurement result determined based on the actual beam measurement result does not belong to the first beam set; The first beam set is a beam set determined based on a predicted beam result, and the second beam set is a beam set determined based on an actual beam measurement result.

7. The method according to claim 5 or 6, characterized in that The method further comprises: The terminal device receives first configuration information sent by the network device, where the first configuration information includes threshold information for determining whether the prediction result is valid, and the threshold information includes one or more of the following information: the first threshold, the second threshold, and the third threshold.

8. The method according to any one of claims 5 to 7, characterized in that The first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results, where K is an integer greater than or equal to 1.

9. The method according to claim 8, characterized in that The method further comprises: The terminal device receives the parameter K sent by the network device.

10. The method according to any one of claims 1 to 9, characterized in that The terminal device sends first information to the network device, including: When a first event is triggered, the terminal device sends the first information to the network device, where the first event is associated with one or more of the following information: First Timer; The number of times the validity of the predicted beam measurement results is judged; First moment; The number of invalid prediction results; Number of times the first message was sent.

11. The method according to any one of claims 1 to 10, characterized in that The terminal device sends first information to the network device, including: When a first event is triggered, the terminal device sends the first information to the network device, where the first event includes one or more of the following: The first timer times out; The number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; First moment arrived; The number of consecutive invalid prediction results reaches a fifth threshold; The number of times the first information is sent does not reach the sixth threshold.

12. The method according to claim 11, characterized in that The method further comprises: The terminal device receives second configuration information sent by the network device, and the second configuration information includes parameter information for determining whether the first event is triggered, and the parameter information includes one or more of the following: the duration of the first timer, the fourth threshold, the first moment, the fifth threshold and the sixth threshold.

13. The method according to claim 11 or 12, characterized in that The number of times the prediction result is continuously determined to be invalid reaches a fifth threshold includes: Within the first time window, the number of times the prediction result is continuously determined to be invalid reaches a fifth threshold.

14. The method according to any one of claims 10 to 13, characterized in that The start condition of the first timer includes one or more of the following: The terminal device receives third configuration information sent by the network device, where the third configuration information includes a duration parameter for configuring the first timer; The first timer times out; The terminal device sends the first information to the network device; The number of times the first information is sent does not exceed a sixth threshold; The number of times the prediction result is continuously determined to be invalid reaches a fifth threshold.

15. The method according to any one of claims 10 to 14, characterized in that The conditions for stopping the first timer include: During the operation of the first timer, the number of consecutive determinations that the prediction result is valid reaches a seventh threshold; or During the operation of the first timer, the terminal device receives third indication information sent by the network device, where the third indication information is used to update or delete the previously configured duration parameter of the first timer.

16. The method according to claim 15, characterized in that The method further comprises: The terminal device receives fourth configuration information sent by the network device, where the fourth configuration information includes the seventh threshold and / or the third indication information.

17. The method according to any one of claims 1 to 16, characterized in that The method further comprises: The terminal device receives the fifth configuration information sent by the network device, where the fifth configuration information is used to configure relevant parameters of the reference signal, where the relevant parameters of the reference signal include a first period parameter and / or third beam set information, where the first period parameter is used to indicate a transmission period of a reference signal associated with a beam in a third beam set, where the third beam set is a set of beam compositions that the terminal device needs to predict based on the beam measurement results.

18. The method according to claim 17, characterized in that The first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

19. The method according to any one of claims 1 to 18, characterized in that The beam measurement result includes beam measurement results for one or more cells, wherein the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

20. The method according to any one of claims 1 to 19, characterized in that The method further comprises: The terminal device sends first capability information to the network device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

21. The method according to claim 20, characterized in that The first capability information is indicated according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

22. A wireless communication method, characterized in that: include: The network device receives first information sent by the terminal device, where the first information includes a performance monitoring result for a first model, where the first model is used to predict a beam measurement result, wherein the first information includes any one of the following information: One or more first indication information, wherein one first indication information among the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, where the second indication information is used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including a proportion of the number of valid prediction results to the total number of predictions, or a proportion of the number of invalid prediction results to the total number of predictions; Information used to calculate second proportion information, where the second proportion information includes the proportion of the number of times the prediction results are valid to the total number of predictions, or the proportion of the number of times the prediction results are invalid to the total number of predictions.

23. The method according to claim 22, characterized in that The information used to calculate the second ratio information includes any one of the following information: The number of times the prediction results were valid and the number of times the prediction results were invalid; The number of times the prediction results are valid and the total number of predictions; The number of invalid prediction results and the total number of predictions.

24. The method according to claim 22 or 23, characterized in that If the second indication information is used to indicate a proportion interval to which the first proportion information belongs, the method further includes: The network device determines a first association relationship, where the first association relationship includes a correspondence between a value of the second indication information and a proportional interval; The network device determines, based on the first association relationship, a proportion interval to which the first proportion information belongs.

25. The method according to any one of claims 22 to 24, characterized in that The method further comprises: The network device sends first configuration information to the terminal device, where the first configuration information includes threshold information for determining whether the prediction result is valid.

26. The method according to any one of claims 22 to 25, characterized in that The method further comprises: The network device sends a parameter K to the terminal device, where the parameter K is the number of beams included in the first beam set and / or the second beam set, wherein the first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results. The first beam set and / or the second beam set are used to determine whether the prediction result is valid.

27. The method according to any one of claims 22 to 26, characterized in that The method further comprises: The network device sends second configuration information to the terminal device, where the second configuration information includes parameter information for determining whether a first event is triggered, where the parameter information includes one or more of the following: a duration of a first timer, a fourth threshold, a first time, a fifth threshold, and a sixth threshold; when the first event is triggered, the first information is sent by the terminal device to the network device, where the first event includes one or more of the following: The first timer times out; The number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; First moment arrived; The number of consecutive invalid prediction results reaches a fifth threshold; The number of times the first information is sent does not reach the sixth threshold.

28. The method according to claim 27, characterized in that The method further comprises: The network device sends third configuration information to the terminal device, where the third configuration information includes a duration parameter for configuring the first timer.

29. The method according to claim 27 or 28, characterized in that The method further comprises: The network device sends fourth configuration information to the terminal device, the fourth configuration information including a seventh threshold and / or third indication information, the seventh threshold being used to determine whether the first timer needs to stop running during the operation of the first timer, the third indication information being used to update or delete the previously configured duration parameter of the first timer, and the seventh threshold and / or the third indication information being used to determine whether the first timer needs to stop running.

30. The method according to any one of claims 22 to 29, characterized in that The method further comprises: The network device sends fifth configuration information to the terminal device, where the fifth configuration information is used to configure relevant parameters of the reference signal, where the relevant parameters of the reference signal include a first period parameter and / or third beam set information, where the first period parameter is used to indicate a sending period of a reference signal associated with a beam in a third beam set, and the third beam set information is a set of beam compositions that the terminal device needs to predict based on the beam measurement results.

31. The method according to claim 30, wherein The first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

32. The method according to any one of claims 22 to 31, characterized in that The beam measurement result includes beam measurement results for one or more cells, wherein the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

33. The method according to any one of claims 22 to 32, characterized in that The method further comprises: The network device receives first capability information sent by the terminal device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

34. The method according to claim 33, wherein The first capability information is indicated according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

35. A terminal device, characterized in that: include: A sending unit, configured to send first information to a network device, where the first information includes a performance monitoring result for a first model, where the first model is used to predict a beam measurement result, wherein the first information includes any one of the following information: One or more first indication information, wherein one first indication information among the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, where the second indication information is used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including a proportion of the number of valid prediction results to the total number of predictions, or a proportion of the number of invalid prediction results to the total number of predictions; Information used to calculate the second ratio information, the second ratio information including the ratio of the number of valid prediction results to the total number of predictions or the ratio of invalid prediction results to the total number of predictions.

36. The terminal device according to claim 35, characterized in that The information used to calculate the second ratio information includes any one of the following information: The number of times the prediction results were valid and the number of times the prediction results were invalid; The number of times the prediction results are valid and the total number of predictions; The number of invalid prediction results and the total number of predictions.

37. The terminal device according to claim 35 or 36, characterized in that: If the second indication information is used to indicate a proportion interval to which the first proportion information belongs, the terminal device further includes: a determining unit, configured to determine a first association relationship, where the first association relationship includes a correspondence between a value of the second indication information and a proportional interval; The determining unit is further configured to determine, based on the first association relationship, a proportion interval to which the first proportion information belongs.

38. The terminal device according to any one of claims 35 to 37, characterized in that: The validity of the prediction result is related to one or more of the following information: Predicted beam measurements; Actual beam measurement results; a beam order determined based on predicted beam measurements; A beam set determined based on predicted beam measurement results; Beam order based on actual beam measurement results; The beam set is determined based on actual beam measurement results.

39. The terminal device according to any one of claims 35 to 38, characterized in that: When the first condition is met, the terminal device further includes: A determination unit is configured to determine whether the prediction result is valid, wherein the first condition includes one or more of the following: An absolute value of a difference between a predicted beam measurement result corresponding to a beam in the first beam set and an actual beam measurement result corresponding to the same beam is less than or equal to a first threshold; The number of beams for which the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is greater than or equal to a second threshold; The beams included in the first beam set are the same as the beams included in the second beam set; The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results; The beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is the same as the beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; A ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is greater than or equal to a third threshold; The beam in the first beam set having the best beam measurement result determined based on the predicted beam measurement result belongs to the second beam set; The beams in the second beam set having the best beam measurement result determined based on the actual beam measurement result belong to the first beam set; The first beam set is a beam set determined based on a predicted beam measurement result, and the second beam set is a beam set determined based on an actual beam measurement result.

40. The terminal device according to any one of claims 35 to 39, characterized in that: When a second condition is met, the determining unit is configured to determine that the prediction result is invalid, where the second condition includes one or more of the following: An absolute value of a difference between a predicted beam measurement result corresponding to at least one beam in the first beam set and an actual beam measurement result corresponding to the same beam is greater than a first threshold; The number of beams for which the absolute value of the difference between the predicted beam measurement result corresponding to a beam in the first beam set and the actual beam measurement result corresponding to the same beam is less than or equal to a first threshold, and the ratio of the number of beams included in the first beam set or the second beam set is less than a second threshold; The beams included in the first beam set are not completely identical to the beams included in the second beam set; A beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from a beam arrangement order of the beams in the first beam set determined based on the actual beam measurement results; A beam arrangement order of the beams in the first beam set determined based on the predicted beam measurement results is different from a beam arrangement order of the beams in the second beam set determined based on the actual beam measurement results; A ratio of the number of beams included in the intersection of the first beam set and the second beam set to the number of beams included in the second beam set is less than a third threshold; The beam in the first beam set having the best beam measurement result determined based on the predicted beam measurement result does not belong to the second beam set; The beam in the second beam set having the best beam measurement result determined based on the actual beam measurement result does not belong to the first beam set; The first beam set is a beam set determined based on a predicted beam result, and the second beam set is a beam set determined based on an actual beam measurement result.

41. The terminal device according to claim 39 or 40, characterized in that: The terminal device further includes: A receiving unit is used to receive first configuration information sent by the network device, where the first configuration information includes threshold information for determining whether the prediction result is valid, and the threshold information includes one or more of the following information: the first threshold, the second threshold and the third threshold.

42. The terminal device according to any one of claims 39 to 41, characterized in that: The first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results, where K is an integer greater than or equal to 1.

43. The terminal device according to claim 42, characterized in that The receiving unit is used to receive the parameter K sent by the network device.

44. The terminal device according to any one of claims 35 to 43, characterized in that: The sending unit is configured to send first information to the network device, including: When a first event is triggered, the sending unit is configured to send the first information to the network device, where the first event is associated with one or more of the following information: First Timer; The number of times the validity of the predicted beam measurement results is judged; First moment; The number of invalid prediction results; Number of times the first message was sent.

45. The terminal device according to any one of claims 35 to 44, characterized in that: The sending unit is configured to send first information to the network device, including: When a first event is triggered, the sending unit is configured to send the first information to the network device, where the first event includes one or more of the following: The first timer times out; The number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; First moment arrived; The number of consecutive invalid prediction results reaches a fifth threshold; The number of times the first information is sent does not reach the sixth threshold.

46. The terminal device according to claim 45, characterized in that The receiving unit is used to receive second configuration information sent by the network device, the second configuration information including parameter information for determining whether the first event is triggered, the parameter information including one or more of the following: the duration of the first timer, the fourth threshold, the first moment, the fifth threshold and the sixth threshold.

47. The terminal device according to claim 45 or 46, characterized in that The number of times the prediction result is continuously determined to be invalid reaches a fifth threshold includes: Within the first time window, the number of times the prediction result is continuously determined to be invalid reaches a fifth threshold.

48. The terminal device according to any one of claims 44 to 47, characterized in that: The start condition of the first timer includes one or more of the following: The terminal device receives third configuration information sent by the network device, where the third configuration information includes a duration parameter for configuring the first timer; The first timer times out; The terminal device sends the first information to the network device; The number of times the first information is sent does not exceed a sixth threshold; The number of times the prediction result is continuously determined to be invalid reaches a fifth threshold.

49. The terminal device according to any one of claims 44 to 48, characterized in that: The conditions for stopping the first timer include: During the operation of the first timer, the number of consecutive determinations that the prediction result is valid reaches a seventh threshold; or During the operation of the first timer, the terminal device receives third indication information sent by the network device, where the third indication information is used to update or delete the previously configured duration parameter of the first timer.

50. The terminal device according to claim 49, characterized in that The receiving unit is configured to receive fourth configuration information sent by the network device, where the fourth configuration information includes the seventh threshold and / or the third indication information.

51. The terminal device according to any one of claims 35 to 50, characterized in that: The receiving unit is used to receive the fifth configuration information sent by the network device, and the fifth configuration information is used to configure relevant parameters of the reference signal. The relevant parameters of the reference signal include a first period parameter and / or third beam set information. The first period parameter is used to indicate the sending period of the reference signal associated with the beam in the third beam set. The third beam set is a set of beam compositions that the beam measurement results need to be predicted by the terminal device.

52. The terminal device according to claim 51, characterized in that The first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

53. The terminal device according to any one of claims 35 to 52, characterized in that: The beam measurement result includes beam measurement results for one or more cells, wherein the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

54. The terminal device according to any one of claims 35 to 53, characterized in that: The sending unit is used to send first capability information to the network device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

55. The terminal device according to claim 54, characterized in that The first capability information is indicated according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

56. A network device, characterized in that include: A receiving unit, configured to receive first information sent by a terminal device, where the first information includes a performance monitoring result for a first model, where the first model is used to predict a beam measurement result, wherein the first information includes any one of the following information: One or more first indication information, wherein one first indication information among the one or more first indication information is used to indicate whether a prediction result is valid; second indication information, where the second indication information is used to indicate first proportion information or to indicate a proportion interval to which the first proportion information belongs, the first proportion information including a proportion of the number of valid prediction results to the total number of predictions, or a proportion of the number of invalid prediction results to the total number of predictions; Information used to calculate second proportion information, where the second proportion information includes the proportion of the number of times the prediction results are valid to the total number of predictions, or the proportion of the number of times the prediction results are invalid to the total number of predictions.

57. The network device according to claim 56, wherein: The information used to calculate the second ratio information includes any one of the following information: The number of times the prediction results were valid and the number of times the prediction results were invalid; The number of times the prediction results are valid and the total number of predictions; The number of invalid prediction results and the total number of predictions.

58. The network device according to claim 56 or 57, characterized in that: If the second indication information is used to indicate a proportion interval to which the first proportion information belongs, the network device further includes: a determining unit, configured to determine a first association relationship, where the first association relationship includes a correspondence between a value of the second indication information and a proportional interval; The network device determines, based on the first association relationship, a proportion interval to which the first proportion information belongs.

59. The network device according to any one of claims 56 to 58, characterized in that: The network device further includes: A sending unit is used to send first configuration information to the terminal device, where the first configuration information includes threshold information for determining whether the prediction result is valid.

60. The network device according to any one of claims 56 to 59, characterized in that: The sending unit is used to send a parameter K to the terminal device, where the parameter K is the number of beams included in the first beam set and / or the second beam set, wherein the first beam set includes the top K beams with the best beam measurement results determined based on the predicted beam measurement results, and the second beam set includes the top K beams with the best beam measurement results determined based on the actual beam measurement results, and the first beam set and / or the second beam set are used to determine whether the prediction result is valid.

61. The network device according to any one of claims 56 to 60, characterized in that: The sending unit is configured to send second configuration information to the terminal device, where the second configuration information includes parameter information for determining whether a first event is triggered, where the parameter information includes one or more of the following: a duration of a first timer, a fourth threshold, a first moment, a fifth threshold, and a sixth threshold; wherein, when the first event is triggered, the first information is sent by the terminal device to the network device, where the first event includes one or more of the following: The first timer times out; The number of times the validity of the predicted beam measurement result is judged reaches a fourth threshold; First moment arrived; The number of consecutive invalid prediction results reaches a fifth threshold; The number of times the first information is sent does not reach the sixth threshold.

62. The network device according to claim 61, wherein: The sending unit is used to send third configuration information to the terminal device, where the third configuration information includes a duration parameter for configuring the first timer.

63. The network device according to claim 61 or 62, characterized in that: The sending unit is used to send fourth configuration information to the terminal device, the fourth configuration information includes a seventh threshold and / or third indication information, the seventh threshold is used to determine whether the first timer needs to stop running during the operation of the first timer, the third indication information is used to update or delete the previously configured duration parameter of the first timer, and the seventh threshold and / or the third indication information are used to determine whether the first timer needs to stop running.

64. The network device according to any one of claims 56 to 63, characterized in that: The sending unit is used to send fifth configuration information to the terminal device, and the fifth configuration information is used to configure relevant parameters of the reference signal. The relevant parameters of the reference signal include a first period parameter and / or third beam set information. The first period parameter is used to indicate the sending period of the reference signal associated with the beam in the third beam set. The third beam set information is a set of beam compositions that the terminal device needs to predict based on the beam measurement results.

65. The network device according to claim 64, characterized in that The first period parameter is different from the second period parameter, wherein the second period parameter is used to indicate the transmission period of the reference signal associated with the beam in the fourth beam set, and the fourth beam set is a set of beams whose beam measurement results need to be obtained through an actual measurement process.

66. The network device according to any one of claims 56 to 65, characterized in that: The beam measurement result includes beam measurement results for one or more cells, wherein the one or more cells include a serving cell and / or at least one neighboring cell of the terminal device.

67. The network device according to any one of claims 56 to 66, characterized in that: The receiving unit is used to receive first capability information sent by the terminal device, where the first capability information is used to indicate whether the terminal device supports performance monitoring of the first model.

68. The terminal device according to claim 67, characterized in that The first capability information is indicated according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

69. A terminal device, characterized in that: It includes a transceiver, a memory and a processor, the memory is used to store programs, the processor is used to call the programs in the memory and control the transceiver to receive or send signals, so that the terminal device executes the method as described in any one of claims 1 to 21.

70. A network device, characterized in that The network device comprises a transceiver, a memory and a processor, wherein the memory is used to store a program, and the processor is used to call the program in the memory and control the transceiver to receive or send a signal so that the network device executes the method as described in any one of claims 22 to 34.

71. A device, characterized in that The device comprises a processor configured to call a program from a memory so as to cause the device to execute the method according to any one of claims 1 to 21 or 22 to 34.

72. A chip, characterized in that The device comprises a processor configured to call a program from a memory so that a device equipped with the chip executes the method according to any one of claims 1 to 21 or 22 to 34.

73. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing a computer to execute the method according to any one of claims 1 to 21 or 22 to 34.

74. A computer program product, characterized in that A program is included, the program causing a computer to execute the method according to any one of claims 1 to 21 or 22 to 34.

75. A computer program, characterized in that The computer program causes a computer to execute the method of any one of claims 1 to 21 or 22 to 34.

Images