Communication method and related apparatus

Abstract

Provided in the present application are a communication method and a related apparatus, which can acquire measurement results of metrics at different prediction moments, thus facilitating more accurate monitoring of the performance of terminal-side models or functions. The method comprises: receiving first indication information, the first indication information being used for indicating a plurality of thresholds, the plurality of thresholds corresponding to a first metric, prediction moments corresponding to the plurality of thresholds being different, each of the plurality of thresholds corresponding to at least one prediction moment, and the first metric corresponding to the performance of a model or function; determining a measurement result corresponding to each of at least one threshold, wherein the measurement result corresponding to each threshold is a measurement result of the first metric at the at least one prediction moment corresponding to the threshold, and the plurality of thresholds comprise the at least one threshold; on the basis of the measurement result corresponding to each of the at least one threshold, generating a first measurement result; and sending second indication information, the second indication information being used for indicating the first measurement result.

Description

Communication method and related apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411098886.8, filed on August 9, 2024, and entitled “Communication method and related apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and in particular, to a communication method and related apparatus. BACKGROUND

[0003] The 3rd generation partnership project (3GPP) designs several application scenarios for the application of artificial intelligence (AI) on the radio access network (RAN) side, including channel state information reference signal (CSI-RS) feedback enhancement, beam management enhancement, and positioning enhancement. Taking the beam management enhancement as an example, the beam management enhancement includes two cases: case one, predicting the downlink beams of beam set A based on the measurement results of beam set B; case two, predicting the downlink beams of future beam set A based on the measurement results of beam set B. Among them, the mode of beam management enhancement is a one-sided model, that is, the AI model is deployed on the network device side (referred to as network side model), or the AI model is deployed on the terminal device side (referred to as terminal side model).

[0004] For the terminal side model, there are two types of model monitoring methods. Among them, the first type includes network side monitoring and terminal assisted monitoring. Specifically, the network side monitoring method is that the terminal device reports labels and inference outputs to the network device, the network device calculates performance indicators based on the reported information, and generates monitoring decisions; the terminal assisted monitoring method is that the terminal device reports performance indicators or events based on performance indicators to the network device, and then the network device generates monitoring decisions based on the reported information. The second type includes terminal side monitoring. Specifically, the terminal device reports monitoring decisions to the network device, and the monitoring decisions are, for example, model selection, activation / deactivation of the model, model switching, model fallback, and the like.

[0005] For the terminal assisted monitoring method of case two based on the terminal side model described above, the granularity of the performance indicators or events based on the performance indicators reported by the terminal device is large, and the performance monitoring of the performance indicators is not fine enough. SUMMARY

[0006] The application provides a communication method and related device, which is beneficial to more fine-grained performance monitoring of performance indicators.

[0007] In a first aspect, a communication method is provided. The method can be applied to a terminal side, such as a terminal device or a communication module in the terminal device, or a circuit or chip responsible for communication functions in the terminal device (such as a Modem chip, also known as a baseband chip, or a system on chip (SoC) chip or system in package (SIP) chip containing a modem core). Taking the case where the method is applied to a terminal device, in the method: the terminal device receives first indication information, which is used to indicate a plurality of thresholds. The plurality of thresholds are used to monitor a first indicator. The plurality of thresholds correspond to different predicted time points. Each threshold in the plurality of thresholds corresponds to at least one predicted time point. The first indicator corresponds to the performance of a model or function, or in other words, the first indication is an indicator used to monitor the performance of a model or function, or in other words, the first indicator is used for model monitoring. The terminal device determines a measurement result corresponding to each threshold in the at least one threshold. The measurement result corresponding to each threshold is a measurement result of the first indicator at the at least one predicted time point corresponding to each threshold. The plurality of thresholds includes the at least one threshold. The terminal device generates a first measurement result according to the measurement result corresponding to each threshold in the at least one threshold. The terminal device sends second indication information, which is used to indicate the first measurement result.

[0008] In this application, the indicator can be replaced by the performance indicator, and the measurement result can be replaced by the monitoring result.

[0009] The first indicator corresponds to the performance of a model or function or measurement task or reporting task.

[0010] In this application, the first indication information is used to indicate a plurality of thresholds, which can be understood as the first indication information indicating that the terminal device independently monitors the first indicator at the predicted time point corresponding to each threshold and indicates the measurement result of the first indicator at the predicted time point corresponding to each threshold to the network device, wherein the measurement result includes a triggering event or a non-triggering event. It can also be said that the measurement result is a triggering event or a non-triggering event.

[0011] If the value of the first indicator at the predicted time point corresponding to a threshold meets the threshold, it can be regarded as a non-triggering event. Accordingly, the measurement result of the first indicator at the predicted time point corresponding to the threshold includes a non-triggering event. If the value of the first indicator at the predicted time point corresponding to a threshold does not meet the threshold, it means that the event is not triggered, or a non-triggering event, and accordingly, the value of the first indicator at the predicted time point corresponding to the threshold includes a triggering event.

[0012] Based on the technical solutions of the present application, the terminal device independently monitors the first index at each prediction time based on the threshold corresponding to each prediction time based on the indication of the network device. This way of monitoring the index is more precise, and the measurement results of the index at different prediction times can be obtained, which is beneficial to more accurately monitor the performance of the terminal-side model / function / measure task / reporting task.

[0013] In some implementations of the first aspect, the at least one threshold includes a first threshold, a measurement result of the first threshold includes a trigger event or a non-trigger event; if the values of the first index at all prediction times corresponding to the first threshold satisfy the first threshold, the measurement result corresponding to the first threshold includes the non-trigger event; if the value of the first index at any prediction time corresponding to the first threshold does not satisfy the first threshold, the measurement result corresponding to the first threshold includes the trigger event.

[0014] In some implementations of the first aspect, the at least one threshold includes a first threshold, a measurement result of the first threshold includes a trigger event or a non-trigger event; if the values of the first index at all prediction times corresponding to the first threshold satisfy the first threshold, the measurement result corresponding to the first threshold includes the non-trigger event; if the value of the first index at any prediction time corresponding to the first threshold does not satisfy the first threshold, the measurement result corresponding to the first threshold includes the trigger event.

[0015] In some implementations of the first aspect, the second indication information includes any of the following: a plurality of bit positions, the plurality of bit positions correspond one-to-one to the plurality of thresholds; or, a first prediction time; or, a value of the first index at a second prediction time. The measurement result of the first index at the first prediction time and the prediction times after the first prediction time includes the trigger event, or the measurement result of the first index at the first prediction time and the prediction times before the first prediction time includes the non-trigger event. The measurement result of the first index at the second prediction time includes the trigger event.

[0016] In some implementations of the first aspect, the at least one threshold includes a first threshold, the first threshold corresponds to a plurality of prediction times, and a measurement result of the first threshold includes a trigger event and / or a non-trigger event; if the value of the first index at any prediction time corresponding to the first threshold satisfies the first threshold, the measurement result of the any prediction time includes the non-trigger event; if the value of the first index at any prediction time corresponding to the first threshold does not satisfy the first threshold, the measurement result of the any prediction time includes the trigger event.

[0017] It should be understood that the first threshold corresponds to at least one prediction time, each prediction time in the at least one prediction time corresponds to one measurement result, and therefore, the first threshold corresponds to at least one measurement result. Since each prediction time can include a trigger event or a non-trigger event, the measurement result of the first threshold includes a trigger event and / or a non-trigger event.

[0018] With reference to the first aspect, in some implementations of the first aspect, the second indication information includes any one of: a plurality of bits; or, the first prediction time; or, a value of the first indicator at the second prediction time. The plurality of bits correspond to the plurality of prediction times one by one, and the plurality of prediction times correspond to the plurality of threshold values. The measurement result of the first indicator at the first prediction time and prediction times after the first prediction time includes a triggering event, or the measurement result of the first indicator at the second prediction time and prediction times before the second prediction time includes a non-triggering event. The measurement result of the first indicator at the second prediction time includes a triggering event.

[0019] With reference to the first aspect, in some implementations of the first aspect, the first indicator is any one of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of predicted top K optimal beams, a probability that a predicted optimal beam is one of measured top K optimal beams, a difference between a measured reference signal received power (RSRP) of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0020] In any implementation of the first aspect described above, the measurement result of the first threshold value includes a triggering event or a non-triggering event, which can also be described as the measurement result of the first threshold value being a triggering event or a non-triggering event. The measurement result of the first threshold value includes a triggering event, which can also be described as the measurement result of the first threshold value being a triggering event. The measurement result of the first threshold value includes a non-triggering event, which can also be described as the measurement result of the first threshold value being a non-triggering event.

[0021] In a second aspect, a communication method is provided, which can be applied to a terminal side, for example, a terminal device or a communication module in the terminal device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a System on Chip (SoC) chip or a System in Package (SIP) chip containing a modem core) responsible for communication functions in the terminal device. Taking the case where the method is applied to a terminal device, in the method: the terminal device receives third indication information, the third indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one index, the index corresponding to a performance of a model or a function; the terminal device determines a measurement result of the index corresponding to each threshold in the at least one threshold at each prediction time in a plurality of prediction times; and the terminal device sends fourth indication information, the fourth indication information being used to indicate the measurement result. The measurement result includes a triggering event or a non-triggering event.

[0022] In this application, the third indication information is used to indicate a plurality of thresholds, which can be understood as the third indication information indicating that the terminal device independently monitors the index corresponding to each threshold. For each index, the threshold corresponding to the index is applicable to a plurality of prediction times. In this way, the monitoring of the index is more detailed, and since the terminal device reports the measurement result of the index to the network device, the measurement result of the index is for each prediction time, so the granularity of the reported measurement result of the index is smaller, which is beneficial to more accurately monitor the performance of the terminal side model / function / measure task / report task.

[0023] In this application, the index can be replaced by a performance index, and the measurement result can be replaced by a monitoring result.

[0024] In combination with the second aspect, in some implementations of the second aspect, the at least one threshold includes a second threshold, the second threshold corresponding to a second index; if the value of the second index corresponding to the second threshold at all prediction times satisfies the second threshold, the measurement result of the second index corresponding to the second threshold includes a non-triggering event; if the value of the second index corresponding to the second threshold at any prediction time in the plurality of prediction times does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold includes a triggering event. The second threshold is any one of the at least one threshold.

[0025] With reference to the second aspect, in some implementations of the second aspect, the fourth indication information comprises any one of: at least one bit; or, at least one third prediction time; or, a value or an identity of a target indicator at the at least one fourth prediction time. The at least one bit corresponds to the at least one threshold one by one. The measurement result of each indicator of the at least one indicator at the third prediction time comprises a triggering event. The measurement result of the target indicator of the at least one indicator at the fourth prediction time comprises a triggering event. The measurement result of an indicator other than the target indicator of the at least one indicator at the fourth prediction time comprises a non-triggering event.

[0026] With reference to the second aspect, in some implementations of the second aspect, the at least one threshold comprises a second threshold corresponding to a second indicator. If a value of the second indicator corresponding to the second threshold at any one of the plurality of prediction times satisfies the second threshold, a measurement result of the second indicator corresponding to the second threshold at the any one of the plurality of prediction times comprises a non-triggering event. If the value of the second indicator corresponding to the second threshold at the any one of the plurality of prediction times does not satisfy the second threshold, the measurement result of the second indicator corresponding to the second threshold at the any one of the plurality of prediction times comprises a triggering event.

[0027] With reference to the second aspect, in some implementations of the second aspect, the fourth indication information comprises any one of: at least one group of bits; at least one third prediction time; or, a value or an identity of a target indicator at the at least one fourth prediction time. The at least one group of bits corresponds to the at least one threshold one by one. Each group of bits of the at least one group of bits comprises a plurality of bits, and the plurality of bits correspond to the plurality of prediction times one by one. The measurement result of each indicator of the at least one indicator at the third prediction time comprises a triggering event. The measurement result of the target indicator of the at least one indicator at the fourth prediction time comprises a triggering event. The measurement result of an indicator other than the target indicator of the at least one indicator at the fourth prediction time comprises a non-triggering event.

[0028] In a second aspect, in some implementations of the second aspect, the at least one indicator includes one or more of: a probability that the measured optimal beam is the predicted optimal beam, a probability that the measured optimal beam is one of the predicted top K optimal beams, a probability that the predicted optimal beam is one of the measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0029] In any implementation of the second aspect described above, the measurement result of the first threshold includes a trigger event or a non-trigger event, which can also be described as the measurement result of the first threshold being a trigger event or a non-trigger event. The measurement result of the first threshold includes a trigger event, which can also be described as the measurement result of the first threshold being a trigger event. The measurement result of the first threshold includes a non-trigger event, which can also be described as the measurement result of the first threshold being a non-trigger event.

[0030] In a third aspect, a communication method is provided, which can be applied to a terminal side, such as a terminal device or a communication module in a terminal device, or a circuit or chip responsible for communication functions in a terminal device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core). Taking the case where the method is applied to a terminal device, in the method: the terminal device receives fifth indication information; the terminal device determines a plurality of measurement results according to the fifth indication information, the plurality of measurement results including a measurement result of a first indicator at each of a plurality of predicted time instants; and the terminal device sends sixth indication information, the sixth indication information being used to indicate the plurality of measurement results. The fifth indication information is used to indicate the reporting of the measurement result of the first indicator.

[0031] In this application, the measurement result of the first indicator at each predicted time instant includes a value of the first indicator at each predicted time instant, or in other words, the measurement result of the first indicator at each predicted time instant is a value of the first indicator at each predicted time instant.

[0032] Based on the technical method in the application, the terminal device independently monitors the first indicators at different prediction moments according to the fifth indication information, and obtains measurement results of the first indicators at different prediction moments. In this way, the monitoring manner of the first indicators is more fine-grained, and more fine-grained measurement results of the first indicators can be obtained, which is beneficial to more accurately monitoring the performance of the terminal-side model / function / measure task / report task.

[0033] In the application, the indicators can be replaced by performance indicators, and the measurement results can be replaced by monitoring results.

[0034] Optionally, after receiving the fifth indication information, the terminal device independently monitors the first indicators at different prediction moments according to a protocol definition.

[0035] In combination with the third aspect, in some implementation manners of the third aspect, before determining the plurality of monitoring results according to the fifth indication information, the method further includes: receiving seventh indication information, the seventh indication information being used to indicate that the performance of the first indicators at each of the plurality of prediction moments is monitored. In the application, the terminal device independently monitors the first indicators at different prediction moments based on the network-side indication, and reports the measurement results of the first indicators at different prediction moments.

[0036] In combination with the third aspect, in some implementation manners of the third aspect, the first indicator is any one of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of the first K predicted optimal beams, a probability that a predicted optimal beam is one of the first K measured optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the first K measured optimal beams and an average of predicted RSRPs of the first K measured optimal beams, or a difference between an average of predicted RSRPs of the first K predicted optimal beams and an average of measured RSRPs of the first K predicted optimal beams.

[0037] In a fourth aspect, a communication method is provided, which can be applied to a network side, for example, a network device or a communication module in the network device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) responsible for communication functions in the network device. Taking the case where the method is applied to the network device, in the method: the network device sends first indication information, the first indication information being used to indicate a plurality of threshold values, the plurality of threshold values corresponding to a first index, the plurality of threshold values corresponding to different prediction moments, each threshold value in the plurality of threshold values corresponding to at least one prediction moment, and the first index corresponding to a performance of a model or a function; and the network device receives second indication information, the second indication information being used to indicate a first measurement result, the first measurement result including a measurement result corresponding to each threshold value in the plurality of threshold values, and the measurement result corresponding to each threshold value being a measurement result of the first index at the at least one prediction moment corresponding to each threshold value.

[0038] In this application, the network device indicates a plurality of threshold values to the terminal device, which can be regarded as instructing the terminal device to monitor the first index at different prediction moments, and different threshold values correspond to different prediction moments. In this way, the monitoring method of the index is more detailed, which is beneficial to obtaining the measurement result of the index at different prediction moments, and further beneficial to more accurately monitoring the performance of the terminal side model / function / measure task / report task, so as to generate more accurate monitoring decisions.

[0039] In this application, the index can be replaced by a performance index, and the measurement result can be replaced by a monitoring result.

[0040] In combination with the fourth aspect, in some implementations of the fourth aspect, the plurality of threshold values include a first threshold value, and a measurement result of the first threshold value includes a trigger event or a non-trigger event. If the value of the first index at all prediction moments corresponding to the first threshold value meets the first threshold value, the measurement result corresponding to the first threshold value includes a non-trigger event; if the value of the first index at any prediction moment corresponding to the first threshold value does not meet the first threshold value, the measurement result corresponding to the first threshold value includes a trigger event.

[0041] In combination with the fourth aspect, in some implementations of the fourth aspect, the second indication information includes any of the following: a plurality of bit positions, the plurality of bit positions corresponding to the plurality of threshold values one by one; a first prediction moment, the measurement result of the first index at the first prediction moment and the prediction moments after the first prediction moment including a trigger event, or the measurement result of the first index at the first prediction moment and the prediction moments before the first prediction moment including a non-trigger event; or a value of the first index at a second prediction moment, the measurement result of the first index at the second prediction moment including a trigger event.

[0042] In some implementations of the fourth aspect, in combination with the fourth aspect, the plurality of thresholds comprises a first threshold, the first threshold corresponding to a plurality of predicted time instants, the measurement result of the first threshold comprising a triggering event and / or a non-triggering event. If a value of the first indicator at any predicted time instant corresponding to the first threshold satisfies the first threshold, the measurement result of the any predicted time instant comprises a non-triggering event; if the value of the first indicator at the any predicted time instant corresponding to the first threshold does not satisfy the first threshold, the measurement result of the any predicted time instant comprises a triggering event.

[0043] In some implementations of the fourth aspect, in combination with the fourth aspect, the second indication information comprises any one of: a plurality of bits corresponding to a plurality of predicted time instants, the plurality of predicted time instants corresponding to the plurality of thresholds; a first predicted time instant, the measurement result of the first indicator at the first predicted time instant and a predicted time instant after the first predicted time instant comprising a triggering event, or the measurement result of the first indicator at the first predicted time instant and a predicted time instant before the first predicted time instant comprising a non-triggering event; or a value of the first indicator at a second predicted time instant, the measurement result of the first indicator at the second predicted time instant comprising the triggering event.

[0044] In some implementations of the fourth aspect, in combination with the fourth aspect, the first indicator is any one of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of a predicted top K optimal beams, a probability that a predicted optimal beam is one of a measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of a measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of a predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0045] It should be understood that the fourth aspect of the present application corresponds to the technical solution of the first aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementations are similar, which will not be described again.

[0046] In a fifth aspect, a communication method is provided, which can be applied to a network side, e.g., a network device or a communication module in the network device, or a circuit or a chip (e.g., a Modem chip, also known as a baseband chip, or a SoC chip or a SIP chip containing a modem core) responsible for communication functions in the network device. Taking the case where the method is applied to the network device, in the method: the network device sends third indication information, the third indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one index corresponding to a performance of a model or a function; and the network device receives fourth indication information, the fourth indication information being used to indicate a measurement result, the measurement result including a measurement result of each index corresponding to the at least one threshold at each of a plurality of prediction time points.

[0047] In this application, the network device indicates the at least one threshold corresponding to the at least one index to the terminal device, which can be regarded as instructing the terminal device to independently monitor different indexes, and the threshold corresponding to each index is applicable to a plurality of prediction time points. In this way, the monitoring manner of the indexes is more refined, which is conducive to more accurately monitoring the performance of the terminal side model / function / measure task / report task, and further conducive to the network device generating more accurate monitoring decisions.

[0048] In this application, the index can be replaced by a performance index, and the measurement result can be replaced by a monitoring result.

[0049] In combination with the fifth aspect, in some implementation manners of the fifth aspect, the at least one threshold includes a second threshold, and the second threshold corresponds to a second index. If a value of the second index corresponding to the second threshold at all prediction time points satisfies the second threshold, the measurement result of the second index corresponding to the second threshold includes a non-triggering event. If the value of the second index corresponding to the second threshold at any prediction time point of the plurality of prediction time points does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold includes a triggering event.

[0050] In combination with the fifth aspect, in some implementation manners of the fifth aspect, the fourth indication information includes any one of the following: at least one bit, the at least one bit corresponding to the at least one threshold in a one-to-one manner; or, at least one third prediction time point; or, a value or an identifier of a target index at at least one fourth prediction time point. Wherein, the measurement result of each index of the at least one index at the third prediction time point includes a triggering event; the measurement result of a target index of the at least one index at the fourth prediction time point includes a triggering event, and the measurement result of an index other than the target index of the at least one index at the fourth prediction time point includes a non-triggering event.

[0051] In some implementations of the fifth aspect, in combination with the fifth aspect, the at least one threshold comprises a second threshold, the second threshold corresponding to a second index. If a value of the second index corresponding to the second threshold at any of the plurality of predicted time instants satisfies the second threshold, a measurement result of the second index corresponding to the second threshold at the any of the plurality of predicted time instants comprises a non-triggering event; if the value of the second index corresponding to the second threshold at the any of the plurality of predicted time instants does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold at the any of the plurality of predicted time instants comprises a triggering event.

[0052] In some implementations of the fifth aspect, in combination with the fifth aspect, the fourth indication information comprises any one of: at least one group of bits, the at least one group of bits corresponding to the at least one threshold in a one-to-one manner, each group of bits in the at least one group of bits comprising a plurality of bits, the plurality of bits corresponding to the plurality of predicted time instants in a one-to-one manner; or, at least one third predicted time instant; or, a value or an identifier of a target index at at least one fourth predicted time instant. Wherein a measurement result of each index in the at least one index at the third predicted time instant comprises a triggering event; a measurement result of a target index in the at least one index at the fourth predicted time instant comprises a triggering event, and a measurement result of an index other than the target index in the at least one index at the fourth predicted time instant comprises a non-triggering event.

[0053] In some implementations of the fifth aspect, in combination with the fifth aspect, the at least one index comprises one or more of:

[0054] The probability that the measured optimal beam is the predicted optimal beam, the probability that the measured optimal beam is one of the predicted top K optimal beams, the probability that the predicted optimal beam is one of the measured top K optimal beams, the difference between the measured RSRP of the measured kth optimal beam and the predicted RSRP of the measured kth optimal beam, the difference between the predicted RSRP of the predicted kth optimal beam and the measured RSRP of the predicted kth optimal beam, the difference between the average of the measured RSRP of the measured top K optimal beams and the average of the predicted RSRP of the predicted top K optimal beams, or the difference between the average of the predicted RSRP of the predicted top K optimal beams and the average of the measured RSRP of the measured top K optimal beams.

[0055] It should be understood that the fifth aspect of the present application corresponds to the technical solution of the second aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation manners are similar, and will not be repeated.

[0056] In a sixth aspect, a communication method is provided, which can be applied to a network side, for example, a network device or a communication module in the network device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) responsible for communication functions in the network device. Taking the case where the method is applied to the network device, in the method: the network device sends fifth indication information, the fifth indication information being used to indicate a measurement result of the first index; and the network device receives sixth indication information, the sixth indication information being used to indicate a plurality of measurement results, the plurality of measurement results including a measurement result of the first index at each of a plurality of predicted time instants.

[0057] In the present application, the network device receives the measurement results of the first index at different predicted time instants, which are more detailed and are conducive to more accurately monitoring the terminal-side model function / measurement task / reporting task and generating more accurate monitoring decisions.

[0058] In the present application, the index can be replaced by a performance index, and the measurement result can be replaced by a monitoring result.

[0059] In combination with the sixth aspect, in some implementations of the sixth aspect, the method further includes: sending seventh indication information, the seventh indication information being used to indicate performance monitoring of the first index at each of the plurality of predicted time instants.

[0060] In combination with the sixth aspect, in some implementations of the sixth aspect, the first index is any one of:

[0061] The probability that the measured optimal beam is the predicted optimal beam, the probability that the measured optimal beam is one of the predicted top K optimal beams, the probability that the predicted optimal beam is one of the measured top K optimal beams, the difference between the measured RSRP of the measured kth optimal beam and the predicted RSRP of the measured kth optimal beam, the difference between the predicted RSRP of the predicted kth optimal beam and the measured RSRP of the predicted kth optimal beam, the difference between the average of the measured RSRP of the measured top K optimal beams and the average of the predicted RSRP of the predicted top K optimal beams, or the difference between the average of the predicted RSRP of the predicted top K optimal beams and the average of the measured RSRP of the predicted top K optimal beams.

[0062] It should be understood that the sixth aspect of the present application corresponds to the technical solution of the third aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementations are similar, which will not be described again.

[0063] In a seventh aspect, a communication method is provided, which can be applied to a terminal side, for example, a terminal device or a communication module in the terminal device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) responsible for communication functions in the terminal device. Taking the case where the method is applied to a terminal device, in the method: the terminal device receives eighth indication information, the eighth indication information being used to indicate a plurality of thresholds, the plurality of thresholds being used to monitor the accuracy of first prediction information, the plurality of thresholds corresponding to different prediction moments, and each threshold in the plurality of thresholds corresponding to at least one prediction moment; and the terminal device receives ninth indication information, the ninth indication information being used to indicate the first prediction information at a target prediction moment in the at least one prediction moment, the accuracy of the first prediction information at the target prediction moment satisfying a threshold corresponding to the first prediction information at the target prediction moment.

[0064] In the present application, each threshold corresponds to at least one prediction moment, and each prediction moment corresponds to a threshold. Based on the eighth indication information, the terminal device monitors the accuracy of the first prediction information at each prediction moment in a plurality of prediction moments. For a prediction moment, when the accuracy of the first prediction information at the prediction moment satisfies the threshold corresponding to the prediction moment, the first prediction information at the prediction moment can be considered as reliable prediction information, and the prediction moment is a target prediction moment. The terminal device reports the first prediction information at the target prediction moment to a network device, which is beneficial to more finely monitor and report the accuracy of prediction information at different prediction moments, and is beneficial to save signaling overhead.

[0065] In an eighth aspect, a communication method is provided, which can be applied to a terminal side, for example, a terminal device or a communication module in the terminal device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) responsible for communication functions in the terminal device. Taking the case where the method is applied to a terminal device, in the method: the terminal device receives tenth indication information, the tenth indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one prediction information, and each threshold in the at least one threshold being used to monitor the accuracy of the corresponding prediction information; the terminal device determines the accuracy of the prediction information corresponding to each threshold in the at least one threshold at each prediction moment in a plurality of prediction moments; and the terminal device sends eleventh indication information, the eleventh indication information being used to indicate target prediction information at a target prediction moment, the accuracy of the target prediction information at the target prediction moment satisfying a threshold corresponding to the target prediction information.

[0066] In the present application, for a prediction information corresponding to a same threshold at multiple prediction moments, the terminal device monitors the accuracy of the prediction information at each of the multiple prediction moments based on the threshold corresponding to the prediction information. When the accuracy of the prediction information at a prediction moment meets the threshold corresponding to the measurement information, the prediction moment is a target prediction moment, the prediction information is a target prediction information, and the terminal device reports the target prediction information at the target prediction moment to the network device. This is beneficial for more fine-grained monitoring and reporting of the accuracy of prediction information at different prediction moments, and is beneficial for saving signaling overhead.

[0067] In a ninth aspect, a communication method is provided, which can be applied to the network side, such as a network device or a communication module in the network device, or a circuit or chip responsible for communication functions in the network device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core). Taking the case where the method is applied to the network device, in the method: the network device sends eighth indication information, the eighth indication information is used to indicate multiple thresholds, the multiple thresholds are used to monitor the accuracy of first prediction information, the multiple thresholds correspond to different prediction moments, and each threshold in the multiple thresholds corresponds to at least one prediction moment; and the network device receives ninth indication information, the ninth indication information is used to indicate the first prediction information at a target prediction moment in the at least one prediction moment, and the accuracy of the first prediction information at the target prediction moment meets the threshold of the first prediction information at the target prediction moment.

[0068] In the present application, the network device indicates the multiple thresholds, which is beneficial for more fine-grained monitoring of the accuracy of prediction information at different prediction moments, and can obtain prediction information meeting the accuracy requirement.

[0069] It should be understood that the ninth aspect of the present application corresponds to the technical solution of the seventh aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation manner are similar, and will not be repeated.

[0070] In a tenth aspect, a communication method is provided, which can be applied to a network side, e.g., a network device or a communication module in the network device, or a circuit or chip (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) responsible for communication functions in the network device. Taking the case where the method is applied to the network device, in the method: the network device sends tenth indication information, the tenth indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one prediction information, each threshold in the at least one threshold being used to monitor the accuracy of the corresponding prediction information; determines the accuracy of the prediction information corresponding to each threshold in the at least one threshold at each prediction time in the plurality of prediction times; and receives eleventh indication information, the eleventh indication information being used to indicate target prediction information at a target prediction time, the accuracy of the target prediction information at the target prediction time satisfying the threshold corresponding to the target prediction information.

[0071] In this application, the network device indicates at least one threshold corresponding to at least one prediction information, and the threshold corresponding to one prediction information is applicable to multiple prediction times, which is conducive to more fine-grained monitoring of different prediction information and can obtain prediction information meeting the accuracy requirement.

[0072] It should be understood that the tenth aspect of the present application corresponds to the technical solution of the eighth aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation manner are similar, and will not be repeated.

[0073] In an eleventh aspect, a communication apparatus is provided, which includes: means for performing the method in any possible implementation manner of any of the aspects above. Specifically, the apparatus includes means for performing the method in any possible implementation manner of any of the aspects above.

[0074] In one design, the apparatus can include a module corresponding to each of the methods / operations / steps / actions described in any of the aspects above, which can be a hardware circuit, or software, or a combination of hardware circuit and software.

[0075] In another design, the apparatus is a communication chip, which can include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

[0076] In another design, the apparatus is a terminal device, which can include a transmitter for sending information or data, and a receiver for receiving information or data.

[0077] In another design, the apparatus is configured to perform the method in any possible implementation manner of any of the aspects above, and the apparatus can be configured in a terminal device or a network device.

[0078] In a twelfth aspect, a communication apparatus is provided, comprising at least one processor configured to invoke and run a computer program from a memory, so that the apparatus performs the method in any possible implementation manner of any of the aspects above.

[0079] Optionally, the apparatus further comprises a memory configured to store instructions and data. The memory is coupled to the processor, and the processor implements the method described in the aspects above when executing the instructions stored in the memory.

[0080] Optionally, the apparatus further comprises a transmitter and a receiver, which can be separate or integrated together, referred to as a transceiver.

[0081] In a thirteenth aspect, a computer program product is provided, which comprises a computer program (also referred to as code or instructions), and when the computer program is run, the computer program causes a computer to perform the method in any possible implementation manner of any of the aspects above.

[0082] In a fourteenth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code or instructions), and when the computer program is run on a computer, the computer program causes the computer to perform the method in any possible implementation manner of any of the aspects above.

[0083] In a fifteenth aspect, a communication system is provided, comprising the terminal device of the first aspect above and the network device of the fourth aspect above; or, comprising the terminal device of the second aspect above and the network device of the fifth aspect above; or, comprising the terminal device of the third aspect above and the network device of the sixth aspect above.

[0084] In a sixteenth aspect, a communication system is provided, comprising the terminal device of the seventh aspect above and the network device of the ninth aspect above; or, comprising the terminal device of the eighth aspect above and the network device of the tenth aspect above.

[0085] In a seventeenth aspect, the present application provides a chip system, which comprises at least one processor configured to support the functions involved in any possible implementation manner of any of the aspects above, for example, receiving or processing the data involved in the methods above.

[0086] In a possible design, the chip system further comprises a memory configured to save program instructions and data, and the memory is located in or outside the processor.

[0087] Optionally, the chip system can be composed of a chip, or can contain a chip and other discrete devices. BRIEF DESCRIPTION OF DRAWINGS

[0088] FIG. 1 and FIG. 2 are schematic diagrams of a communication system suitable for embodiments of the present application;

[0089] FIG. 3 and FIG. 4 are schematic diagrams of possible application frameworks in a communication system;

[0090] FIG. 5, FIG. 7, FIG. 8, FIG. 9, and FIG. 10 are schematic diagrams of a communication method provided by embodiments of the present application;

[0091] FIG. 6 is a schematic diagram of reporting a value of a performance indicator provided by embodiments of the present application;

[0092] FIG. 11 and FIG. 12 are schematic block diagrams of a communication apparatus provided by embodiments of the present application. DETAILED DESCRIPTION

[0093] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0094] Before introducing the communication method and related apparatus provided by embodiments of the present application, the following points will be explained first.

[0095] First, in the embodiments shown below, each term and English abbreviation, such as RSRP, performance indicator, monitoring result, etc., are all exemplary examples given for convenience of description, and should not constitute any limitation on the present application. The present application does not exclude the possibility of defining other terms capable of achieving the same or similar functions in existing or future protocols.

[0096] For example, the indicator and the performance indicator in the present application can be used to replace each other, and the measurement result and the monitoring result can be used to replace each other.

[0097] Second, in the embodiments shown below, the first, second, and various numbers are only used to distinguish the same or similar items with basically the same functions and effects for convenience of description. For example, the first performance indicator and the second performance indicator are only used to distinguish different performance indicators, and do not limit the sequence, and do not limit the scope of the embodiments of the present application. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution sequence, and the words "first", "second", etc. also do not necessarily mean different.

[0098] Third, "at least one" means one or more, "multiple" means two or more. "And / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent: A exists alone, A and B exist together, B exists alone, where A, B can be singular or plural. The character " / " generally represents that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c, where a, b, c can be single or multiple.

[0099] Fourth, in this application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication, and can also include determination. The information indicated by a certain information (such as first indication information) is called to be indicated information, such as one or more contents indicated by the first indication information in the embodiments of the present application. In the implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship; the to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance, for example, the indication of a specific information can be realized by means of the arrangement order of each information agreed in advance (for example, protocol predefined), thereby reducing the indication overhead to a certain extent. The specific manner of indication is not limited in the present application. It can be understood that for the sender of the indication information, the indication information can be used to indicate the to-be-indicated information, and for the receiver of the indication information, the indication information can be used to determine the to-be-indicated information.

[0100] Fifth, the correspondence relationship shown in each table in the present application can be configured or predefined. The values of the information in each table are merely examples, and other values can be configured, and the present application does not limit. When configuring the correspondence relationship between the information and each parameter, it is not necessarily required to configure all the correspondence relationships shown in each table. For example, the correspondence relationship shown in some rows in the table in the present application can also not be configured. For another example, the above tables can be appropriately deformed, for example, split, merged, and the like. The names of the parameters shown in the titles of the above tables can also use other names understandable by the communication device, and the values or representation manners of the parameters can also use other values or representation manners understandable by the communication device. The above tables can also use other data structures when implemented, for example, can use arrays, queues, containers, stacks, linear tables, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or the like.

[0101] Sixth, in the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending first indication information to a terminal device" can be understood as that the destination of the first indication information is the terminal device, which can include direct transmission through the air interface, and also includes indirect transmission through the air interface by other units or modules. "Receiving first indication information from a network device" can be understood as that the source of the first indication information is the network device, which can include direct reception from the network device through the air interface, and also includes indirect reception from the network device through the air interface from other units or modules. "Sending" can also be understood as "output" of a chip interface, and "receiving" can also be understood as "input" of a chip interface.

[0102] In other words, sending and receiving can be between devices, for example, between a terminal and a base station; or can be within a device, for example, between components, between modules, between chips, between software modules or hardware modules in the device through a bus, a wire or an interface.

[0103] Seventh, in the present application, "when", "if" and "whether" all refer to the objective situation that the device will make corresponding processing, and are not limited in time, and also do not require the device to have a judgment action when implemented, and also do not mean that there are other limitations. Without special instructions, "if" and "whether" can be replaced, and "when" and "in the case of" can be replaced. "When" and "if" / "whether" can be replaced.

[0104] Eighth, in the present application, the words such as "exemplarily" or "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplarily" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. On the contrary, the words such as "exemplarily" or "for example" are intended to present the relevant concept in a specific manner.

[0105] Ninth, in the present application, the solutions in various embodiments can be reasonably combined, and the explanation or description of each term appearing in the embodiments, similar operations, or steps can be mutually referenced or explained in various embodiments, and this is not limited.

[0106] Tenth, in the present application, the monitoring result includes a triggering event or a non-triggering event, which can be alternatively described as the monitoring result being a triggering event or a non-triggering event. The monitoring result includes a triggering event, which can be alternatively described as the monitoring result being a triggering event. The monitoring result includes a non-triggering event, which can be alternatively described as the monitoring result being a non-triggering event.

[0107] FIG. 1 is a schematic diagram of a communication system applicable to embodiments of the present application. The communication system 100 shown in FIG. 1 includes a radio access network (RAN) 101 and a core network (CN) 102. Optionally, the communication system 100 also includes the Internet 103. The radio access network 101 can include at least one RAN node (such as 110a and 110b in FIG. 1), and can also include at least one terminal (such as 120a-120j in FIG. 1). The terminal is connected to the RAN node in a wireless manner, and the RAN node is connected to the core network 102 in a wireless or wired manner. The core network device and the RAN node can be independent and different physical devices, or can be a same physical device integrating the functions of the core network device and the logical functions of the RAN node, or can be a physical device integrating part of the functions of the core network device and part of the functions of the RAN node. The terminals and the terminals, and the RAN nodes and the RAN nodes can be connected to each other in a wired or wireless manner. FIG. 1 is only a schematic diagram, and the communication system can also include other RAN nodes, such as wireless relay devices and wireless backhaul devices, which are not shown in FIG. 1.

[0108] The radio access network 101 can be a third generation partnership project (3rd generation partnership project, 3GPP) related cellular system, for example, a fourth generation mobile communication technology (4th generation mobile communication technology, 4G) system (also known as a long term evolution (long term evolution, LTE) system), a fifth generation mobile communication technology (5th generation mobile communication technology, 5G) system (also known as a new radio (new radio, NR) system), or can also be applied to future communication systems, etc., which is not limited in the present application.

[0109] The radio access network 101 can also be an open RAN (open-RAN, O-RAN or ORAN), a cloud radio access network (CRAN). The radio access network 101 can also be a non-terrestrial network (NTN), a satellite communication network, a high altitude platform station (HAPS) communication network, an integrated access and backhaul (IAB) communication network, a reconfigurable intelligent surface (RIS) communication network, etc. The radio access network 101 can also be a communication system that integrates two or more of the above systems.

[0110] The RAN node can also be referred to as a RAN device or an access network device. The RAN node is configured to help terminals to access the network wirelessly. The RAN nodes in the communication system 100 can be of the same type or of different types.

[0111] In a possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), a transmitting and receiving point (TRP), a transmitting point (TP), a next generation NodeB (gNB), a base station in a future mobile communication system, an access point (AP) in a satellite, an IAB node, an access network device in an NTN communication system, i.e., can be deployed in a high altitude platform or a satellite, etc. The RAN node can be a macro base station (e.g., 110a in FIG. 1), a micro base station or an indoor station (e.g., 110b in FIG. 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. The RAN node can also be a device that plays a base station function in device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, unmanned aerial vehicle communication, machine communication, etc. Optionally, the access network device can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the V2X technology can be a road side unit (RSU).

[0112] In another possible scenario, a terminal device is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, in a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH). It can be understood that the RAN node can be a CU node, or a DU node, or a device including a CU node and a DU node. In addition, the CU can be divided into an access network device in the RAN, or can be divided into a core network device in the core network, which is not limited here.

[0113] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an O-RAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0114] The RAN node can support one or more types of fronthaul interfaces, each corresponding to a DU and RU having different functionalities. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions and the RU is configured to implement one or more of the radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, which, relative to the CPRI, moves one or more of the partial baseband functions for the downlink, such as precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / add cyclic prefix (CP), from the DU to the RU for implementation, or one or more of the partial baseband functions for the uplink, such as digital beamforming (BF), or fast Fourier transform (FFT) / remove CP, from the DU to the RU for implementation. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the split between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0115] Taking eCPRI Cat A as an example, for downlink transmission, the split is at layer mapping, the DU is configured to implement one or more of the functions before layer mapping (i.e., one or more of encoding, rate matching, scrambling, modulation, and layer mapping), and the other functions after layer mapping (e.g., one or more of resource element (RE) mapping, BF, or IFFT / add CP) are moved to the RU for implementation. For uplink transmission, the split is at de-RE mapping, the DU is configured to implement one or more of the functions before de-mapping (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), and the other functions after de-mapping (e.g., one or more of digital BF or fast FFT / remove CP) are moved to the RU for implementation. It can be appreciated that the descriptions of the functionalities of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described herein.

[0116] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0117] A terminal device is a device with wireless transceiving functions, which can send signals to a RAN node or receive signals from a RAN node. The terminal device can also be referred to as a terminal apparatus, a terminal, a user equipment (UE), a mobile station, a mobile terminal, etc. The terminal device can be widely applied in various scenarios, for example, at least one of the following scenarios, including but not limited to: enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), D2D, V2X communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, automatic driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal device can specifically be a mobile phone, a tablet computer, a computer with wireless transceiving functions, a wearable device, a vehicle, an airplane, a ship, a robot, a mechanical arm, a smart home device, etc. Embodiments of the present application do not limit the specific technologies and specific device forms adopted by the terminal device.

[0118] The RAN node and the terminal can be fixed in position or movable. The RAN node and the terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water surface; can also be deployed on an airplane, a balloon, and a man-made satellite. Embodiments of the present application do not limit the application scenarios of the RAN node and the terminal.

[0119] The roles of the RAN nodes and the terminals can be relative. For example, the helicopter or the drone 120i in FIG. 1 can be configured to be a mobile RAN node, and for those terminals 120j that access to the wireless access network 101 through 120i, the terminal 120i is a RAN node; but for the RAN node 110a, 120i is a terminal, that is, 110a communicates with 120i through a wireless air interface protocol. Of course, 110a and 120i can also communicate through an interface protocol between RAN nodes and RAN nodes, and in this case, 120i is also a RAN node relative to 110a. Therefore, the RAN nodes and the terminals can be collectively referred to as communication apparatuses, 110a and 110b in FIG. 1 can be referred to as communication apparatuses with RAN node functions, and 120a-120j in FIG. 1 can be referred to as communication apparatuses with terminal functions.

[0120] The RAN nodes and the terminals, the RAN nodes and the RAN nodes, and the terminals and the terminals can communicate through licensed spectrum, can communicate through unlicensed spectrum, and can communicate through both licensed spectrum and unlicensed spectrum; can communicate through spectrum below 6 gigahertz (GHz), can communicate through spectrum above 6 GHz, and can communicate through both spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0121] In the embodiments of the present application, the functions of the RAN nodes can also be performed by modules (such as chips) in the RAN nodes, or can be performed by control subsystems containing RAN node functions. The control subsystems containing RAN node functions herein can be control centers in the above-mentioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. The functions of the terminals can also be performed by modules (such as chips or modems) in the terminals, or can be performed by devices containing terminal functions.

[0122] The core network device refers to a device in the core network that provides service support for the terminal. Currently, some examples of core network devices are: access and mobility management function (AMF) network elements, session management function (SMF) network elements, user plane function (UPF) network elements, and the like, which are not listed one by one here.

[0123] The RAN nodes and the core network devices can be collectively referred to as network devices, and the network devices in the present application can refer to access network devices and / or core network devices.

[0124] It should be understood that the network element in this application can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc.

[0125] In a wireless communication network, e.g., in a mobile communication network, the services supported by the network are increasingly diverse, and thus the requirements to be met are increasingly diverse. For example, the network needs to be able to support ultra-high rates, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as the functions of the network become increasingly powerful, such as supporting increasingly high frequency spectrums, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new requirements, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. In order to meet this challenge, AI technology can be introduced into the wireless communication network, thereby realizing network intelligence. In order to support AI technology in the wireless network, an AI model or AI function can also be introduced into the network.

[0126] FIG. 2 is a schematic diagram of another communication system 200 suitable for embodiments of the present application. As shown in FIG. 2, the communication system 200 includes a network device 201, an AI module 202, a terminal device 203, and a terminal device 204. The network device 201 is, for example, the RAN node 110a in FIG. 1 described above. For the functions and possible forms of the terminal device and the network device, refer to the description of FIG. 1 above, which will not be repeated here. The AI network element 202 is used to perform AI-related operations, such as constructing a training data set or training an AI model, etc.

[0127] In a possible implementation, the network device 201 can send data related to training an AI model to the AI module 202, and the AI module 202 can construct a training data set and train an AI model. For example, the data related to training an AI model can include data reported by a terminal device. The AI module 202 can send the result of the AI model-related operation to the network device 201 and forward it to the terminal device through the network device 201. For example, the result of the AI model-related operation can include at least one of the following: a trained AI model, an evaluation result or a test result of the model, etc. Illustratively, part of the trained AI model can be deployed on the network device 201, and the other part can be deployed on the terminal device. Alternatively, the trained AI model can be deployed on the network device 201, or the trained AI model can be deployed on the terminal device.

[0128] It should be understood that FIG. 2 only illustrates an example in which the AI module 202 is directly connected with the network device 201, and in other scenarios, the AI module 202 can also be connected with a terminal device. Alternatively, the AI module 202 can be connected with both the network device 201 and the terminal device. Alternatively, the AI module 202 can also be connected with the network device 201 through a third-party network element. The embodiments of the present application do not limit the connection relationship between the AI module and other network elements.

[0129] It should also be understood that the AI module shown in FIG. 2 is independent of the network device 201, for example, the AI module 202 is arranged in a host or a cloud server of an over the top (OTT) system.

[0130] It should also be understood that the AI module 202 can also be arranged as a module in the network device and / or the terminal device, for example, arranged in the RAN node or the terminal device shown in FIG. 1, and can also be arranged in the core network device.

[0131] It should also be understood that the present application does not limit the number of AI modules. For example, when there are multiple AI modules, the multiple AI modules can be divided based on functions, such as different AI modules responsible for different functions.

[0132] It should also be understood that the AI module can be a separate device, can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (such as a cloud platform), and the present application does not limit the specific form of the AI module.

[0133] In the present application, the AI module can also be described as an AI network element, an AI node, an AI device, an AI apparatus, etc., and the present application does not limit this.

[0134] It should be noted that FIGS. 1 and 2 are only simplified schematic diagrams for ease of understanding, for example, the communication system can include more or fewer devices than those shown in FIGS. 1 or 2, for example, can also include a wireless relay device and / or a wireless backhaul device, etc., which are not shown in FIGS. 1 and 2. In actual applications, the communication system can include multiple network devices, or can include multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0135] FIG. 3 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 3, network elements in the communication system are connected through interfaces (e.g., NG interface, Xn interface), or air interfaces. One or more AI modules are deployed in one or more of the network elements, such as a core network device, a RAN node, a terminal device, or one or more devices in operation administration and maintenance (OAM) (for clarity, only one AI module is shown in each network element in FIG. 3). The CU and / or the DU can also be provided with one or more AI modules. Optionally, the CU can also be split into a CU-CP and a CU-UP. One or more AI modules are deployed in the CU-CP and / or the CU-UP.

[0136] The AI module is used to implement a corresponding AI function. The AI modules deployed in different network elements can be the same or different. The model of the AI module can implement different functions according to different parameter configurations. The model of the AI module can be configured based on one or more of the following parameters: a structural parameter (e.g., at least one of a number of neural network layers, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in the activation function), an input parameter (e.g., a type of input parameter and / or a dimension of the input parameter), or an output parameter (e.g., a type of output parameter and / or a dimension of the output parameter). The bias in the activation function can also be referred to as a bias of the neural network.

[0137] One AI module can have one or more models. One model can infer an output including one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0138] FIG. 4 is a schematic diagram of another possible application framework in a communication system. As shown in FIG. 4, a RAN intelligent controller (RIC) is included in the communication system. The RIC can be an AI module shown in FIG. 3, for example, to implement AI-related functions. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The Non-RT RIC mainly processes non-real-time information, such as data that is not sensitive to latency, which can be in the order of seconds. The near-RT RIC mainly processes near-real-time information, such as data that is relatively sensitive to latency, which can be in the order of tens of milliseconds.

[0139] Near real-time RIC is used for model or function training and inference. For example, for training an AI model or function, inference is performed using the AI model or function. The near real-time RIC can obtain network side and / or terminal side information from the RAN node (for example, CU, CU-CP, CU-UP, DU and / or RU) and / or terminal device, which can be used as training data or inference data. Optionally, the near real-time RIC can submit the inference result to the RAN node and / or terminal device. Optionally, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU, for example, the near real-time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0140] Non-real-time RIC can also be used for model or function training and inference. For example, for training an AI model or function, inference is performed using the model or function. The non-real-time RIC can obtain network side and / or terminal side information from the RAN node (for example, CU, CU-CP, CU-UP, DU and / or RU) and / or terminal device. The information can be used as training data or inference data, and the inference result can be submitted to the RAN node and / or terminal device. Optionally, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU, for example, the non-real-time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0141] Exemplarily, the near real-time RIC and the non-real-time RIC can be respectively set as a network element alone. Alternatively, the near real-time RIC and the non-real-time RIC can be part of other devices, for example, the near real-time RIC is set in the RAN node (for example, in the CU, DU), and the non-real-time RIC is set in the OAM, in the cloud server, in the core network device, or in other network devices.

[0142] The related technologies and concepts involved in the present application are introduced below.

[0143] 3GPP currently proposes to apply AI to NR, to improve network performance and user experience by intelligently collecting and analyzing data. 3GPP designs several application scenarios for AI application on the RAN side, including CSI-RS feedback enhancement, positioning enhancement, and beam management enhancement. Each of the above scenarios can be further subdivided into different sub-scenarios. The main processes of each application scenario are briefly introduced below.

[0144] (1) CSI-RS feedback enhancement (CSI-RS feedback enhancement)

[0145] CSI is a channel attribute of a communication link, and is downlink channel quality information reported by a terminal device to a network device. The terminal device reports the downlink channel quality information to the network device, so that the network device selects a more appropriate modulation and coding scheme (MCS) for the terminal device, so as to better adapt to the changing wireless channel. The CSI reported by the terminal device includes at least one of the following information: rank indicator (RI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), layer indicator (LI), chanel quality indicator (CQI), and layer 1 reference signal received power (L1-RSRP).

[0146] CSI-RS feedback enhancement can include scenarios such as CSI compression, CSI prediction, and CSI configuration signaling reduction. Among them, CSI compression can include compression in at least one of the spatial domain, the time domain, and the frequency domain.

[0147] Taking CSI compression as an example, a possible implementation process includes: the network device and the terminal device interact with a dictionary, which can be regarded as a model trained in advance by the network device according to the UE capability and its own needs; the network device sends an encoder and a quantizer to the terminal device; the terminal device compresses and quantizes the measured channel matrix according to the existing dictionary, the encoder, and the quantizer, and sends the result to the network device; and the network device reversely recovers the original channel matrix according to the dictionary and the result reported by the terminal device.

[0148] (2) Positioning Accuracy Enhancements

[0149] AI-based positioning enhancement, mainly considering improving the positioning accuracy. A possible flow to enhance the positioning accuracy includes: the terminal device collects raw data and sends the raw data to the network side; the location management function (LMF) network element and the access network device train models based on the raw data, respectively. The model trained by the LMF network element can be used to infer the final positioning (latitude and longitude, etc.), and the model trained by the access network device can be used to infer the line of sight (LOS) or non-LOS (NLOS) judgment result.

[0150] (3) Beam management enhancement

[0151] AI-based beam management enhancement can include beam scanning matrix prediction, optimal beam prediction, and other sub-scenarios. AI-based sparse beam prediction mainly considers improving the prediction accuracy. A possible flow to enhance the prediction accuracy includes: the network device trains a sparse scanning matrix based on the reporting results of a certain number of terminal devices on SSB full beam scanning, which becomes a sparse model. The sparse model is usually unique for each cell; the network device sends the sparse model to the terminal device (for example, by sending a system information block (SIB) message), and the terminal device performs P1 stage beam scanning according to the sparse model and sends the P1 stage beam scanning result to the network device; the network device infers the optimal CSI-RS beam based on the P1 stage beam scanning result, and starts P2 stage beam scanning for the terminal device; the terminal device performs P2 stage beam scanning and sends the identification of the optimal CSI-RS to the network device.

[0152] In the current research, beam management enhancement includes two cases: case one, predicting the downlink beam under the beam set A at the current time based on the measurement result of the beam set B; case two, predicting the downlink beam under the beam set A in the future based on the measurement result of the beam set B. Among them, the mode of beam management enhancement is a one-sided model, that is, the AI model is deployed on the network device side (referred to as network side model), or the AI model is deployed on the terminal device side (referred to as terminal side model).

[0153] A possible flow of the above case one includes: the network device scans the beam set B, and the network device (or terminal device) obtains the measurement result of the beam set B; the network device (or terminal device) inputs the measurement result of the beam set B into the AI model to predict the top K optimal beams on the beam set A at the current time.

[0154] A possible procedure of the above case two includes: the network device scans the beam set B, the network device (or the terminal device) obtains the measurement result of the beam set B; the network device (or the terminal device) inputs the measurement result of the beam set B into the AI model to predict the Top K optimal beams on the beam set A at the future time.

[0155] For the terminal side model, there are two types of model monitoring methods. The first type includes network side monitoring and UE-assisted monitoring. Specifically, in the network side monitoring method, the terminal device reports labels and inference outputs to the network device, the network device calculates performance indicators based on the reported information, and generates monitoring decisions. In the UE-assisted monitoring method, the terminal device reports performance indicators or events based on performance indicators to the network device, and then the network device generates monitoring decisions based on the reported information. The second type includes UE side monitoring. Specifically, the terminal device reports monitoring decisions to the network device, and the monitoring decisions are, for example, model selection, model activation / deactivation, model switching, model fallback, and the like.

[0156] The performance indicators currently discussed include one or more of the following: beam prediction accuracy related key performance indicators (KPIs), link quality related KPIs, performance metrics based on AI input / output data distribution, and the difference between measured RSRP and predicted RSRP (which can be referred to as the difference of L1-RSRP).

[0157] Exemplarily, the beam prediction accuracy related KPIs include one or more of the following: the probability that the measured optimal beam is the predicted optimal beam (Top 1 (%)), the probability that the measured optimal beam is one of the predicted Top K optimal beams (Top K / 1 (%)), and the probability that the predicted optimal beam is one of the measured Top K optimal beams (Top 1 / K (%)).

[0158] Exemplarily, the link quality related KPIs include one or more of the following: throughput, L1-RSRP, layer 1 signal to interference plus noise ratio (L1-SINR), and hypothetical block error rate (BLER).

[0159] For the terminal-assisted monitoring manner in the case two based on the terminal-side model, in the existing scheme, the monitoring result reported by the terminal device is in the granularity of a period or a sample, the granularity is large, and the monitoring result is not fine enough. Taking a performance indicator as an example, the monitoring result of the performance indicator reported by the terminal device is the average value of the performance indicator at a plurality of predicted moments in a period, or the value of the performance indicator at the last predicted moment in a period. Since the prediction performance of the terminal device at different predicted moments is inconsistent, it is necessary to perform more fine performance monitoring on the performance indicator at different predicted moments.

[0160] Therefore, embodiments of the present application provide a communication method, in which the terminal device can independently perform performance monitoring on the performance indicator at different predicted moments in a more fine granularity to obtain the monitoring result of the performance indicator at different predicted moments, which is beneficial to more accurately monitoring the terminal-side model function / measurement task / reporting task, and thus is beneficial to the network device to generate a more accurate monitoring decision.

[0161] FIG. 5 is a schematic flowchart of a communication method 500 provided by embodiments of the present application. The steps of the method 500 can be performed by the terminal side and the network side interaction, wherein the terminal side is, for example, a terminal device or a communication module in the terminal device, or a circuit or chip responsible for communication function in the terminal device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and hereinafter the terminal device is taken as an example for description. The network side is, for example, a network device or a communication module in the network device, or a circuit or chip responsible for communication function in the network device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and hereinafter the network device is taken as an example for description.

[0162] The method 500 includes S501 to S504, and each step is described in detail below.

[0163] S501, the network device sends first indication information to the terminal device, the first indication information is used to indicate a plurality of threshold values, the plurality of threshold values correspond to a first indicator, the plurality of threshold values correspond to different predicted moments, and each threshold value in the plurality of threshold values corresponds to at least one predicted moment. The first indicator is used for model monitoring, or in other words, the first indicator corresponds to the performance of a model or function, which can also be referred to as a performance indicator, and hereinafter the performance indicator is taken as an example for description. Accordingly, the terminal device receives the first indication information.

[0164] The prediction time is a future time, and for the terminal side model or function, the terminal device can predict information of the future time based on the measurement resource. The predicted information of the future time is referred to as prediction information. For example, the prediction information is the top K beams (referred to as Top K beams) at the future time.

[0165] The prediction time can be replaced by a prediction time period, a future time, a future time period, a time, or a time period. The prediction times corresponding to the plurality of thresholds are different. The difference can be not completely the same, that is, there is a partial intersection. For example, the two prediction time periods have an intersection. Or, the difference can be completely different, that is, there is no intersection. For example, the two prediction time periods have no intersection.

[0166] The first index can also be described as a first performance index. Hereinafter, the first performance index is taken as an example for description.

[0167] The first performance index is any one of at least one performance index corresponding to the model or function, and the value of the first performance index can reflect the performance of the model or function.

[0168] The at least one performance index includes one or more of the following: a probability that the actually measured optimal beam is the predicted optimal beam (i.e., Top 1 (%)), a probability that the actually measured optimal beam is one of the predicted top K optimal beams (i.e., Top K / 1 (%)), a probability that the predicted optimal beam is one of the actually measured top K optimal beams (i.e., Top 1 / K (%)), a difference between an actually measured RSRP of the actually measured k-th optimal beam and a predicted RSRP of the actually measured k-th optimal beam (referred to as a difference of actually measured Top K L1-RSRP), a difference between a predicted RSRP of the predicted k-th optimal beam and an actually measured RSRP of the predicted k-th optimal beam (referred to as a difference of predicted Top K L1-RSRP), a difference between an average of actually measured RSRPs of the actually measured top K optimal beams and an average of predicted RSRPs of the actually measured top K optimal beams (referred to as a difference of an average of actually measured Top K L1-RSRP), or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of actually measured RSRPs of the predicted top K optimal beams (referred to as a difference of an average of predicted Top K L1-RSRP).

[0169] For example, when k is 1, the difference between the measured RSRP of the kth best beam and the predicted RSRP of the kth best beam includes the difference between the measured RSRP of the best beam and the predicted RSRP of the best beam (referred to as the difference between the measured Top 1 L1-RSRP). The difference between the predicted RSRP of the kth best beam and the measured RSRP of the kth best beam includes the difference between the predicted RSRP of the best beam and the measured RSRP of the best beam (referred to as the difference between the predicted Top 1 L1-RSRP).

[0170] For example, when k is 2, the difference between the measured RSRP of the kth best beam and the predicted RSRP of the kth best beam includes the difference between the measured RSRP of the second best beam and the predicted RSRP of the second best beam (referred to as the difference between the measured Top 2 L1-RSRP). The difference between the predicted RSRP of the kth best beam and the measured RSRP of the kth best beam includes the difference between the predicted RSRP of the second best beam and the measured RSRP of the second best beam (referred to as the difference between the predicted Top 2 L1-RSRP).

[0171] In a possible design, the difference can be represented by a difference value (in dB), the difference value of the measured Top K L1-RSRP = the measured RSRP of the best beam - the predicted RSRP of the best beam, or the difference value of the measured Top K L1-RSRP = the predicted RSRP of the best beam - the measured RSRP of the best beam. The difference value of the predicted Top K L1-RSRP = the predicted RSRP of the best beam - the measured RSRP of the best beam, or the difference value of the predicted Top K L1-RSRP = the measured RSRP of the best beam - the predicted RSRP of the best beam.

[0172] In another possible design, the above difference can be represented by an absolute value of the difference (in dB), an absolute value of the difference of the measured Top K L1-RSRP = |measured RSRP of the measured optimal beam - predicted RSRP of the measured optimal beam|, or an absolute value of the difference of the measured Top K L1-RSRP = |predicted RSRP of the measured optimal beam - measured RSRP of the measured optimal beam|. An absolute value of the difference of the predicted Top K L1-RSRP = |predicted RSRP of the predicted optimal beam - measured RSRP of the predicted optimal beam|, or an absolute value of the difference of the predicted Top K L1-RSRP = |measured RSRP of the predicted optimal beam - predicted RSRP of the predicted optimal beam|.

[0173] In another possible design, the above difference can be represented by an accuracy (in percentage (%)), an accuracy of the measured Top K L1-RSRP = difference of the measured Top K L1-RSRP / difference of the predicted Top K L1-RSRP, or an absolute value of the difference of the measured Top K L1-RSRP / absolute value of the difference of the predicted Top K L1-RSRP. An accuracy of the predicted Top K L1-RSRP = difference of the predicted Top K L1-RSRP / difference of the measured Top K L1-RSRP, or an absolute value of the difference of the predicted Top K L1-RSRP / absolute value of the difference of the measured Top K L1-RSRP.

[0174] For the terminal-side model or function, the terminal device can perform performance monitoring on at least one performance indicator at at least one predicted time based on an indication of the network device, where the at least one predicted time refers to at least one future time. For example, the at least one predicted time includes t1, t2, and t3, where t1 is closest to the current time, t2 is second closest to the current time, and t3 is third closest to the current time. The at least one performance indicator includes Top1 (%), Top K / 1 (%), and Top 1 / K (%), that is, the terminal device needs to monitor Top1 (%), Top K / 1 (%), and Top 1 / K (%) at t1, monitor Top1 (%), Top K / 1 (%), and Top 1 / K (%) at t2, and monitor Top1 (%), Top K / 1 (%), and Top 1 / K (%) at t3.

[0175] The multiple thresholds of this step are described in detail below.

[0176] Taking any one of the performance indicators (denoted as a first performance indicator) as an example, in order to enable the terminal device to more accurately monitor the first performance indicator at different moments, and to report more effective monitoring results, the network device can indicate a plurality of threshold values of the first performance indicator through the first indication information, and the plurality of threshold values are used to monitor the first performance indicator. The plurality of threshold values correspond to different prediction moments, each threshold value corresponds to at least one prediction moment, and the threshold values corresponding to different prediction moments can be used to determine the monitoring result of the first performance indicator at the prediction moment.

[0177] In one example, the plurality of threshold values include threshold value 1, threshold value 2, and threshold value 3, wherein threshold value 1 corresponds to t1 moment, threshold value 2 corresponds to t2 moment, and threshold value 3 corresponds to t3 moment.

[0178] In another example, the plurality of threshold values include threshold value 1 and threshold value 2, wherein threshold value 1 corresponds to t1 moment, and threshold value 2 corresponds to t2 moment and t3 moment.

[0179] In another example, the plurality of threshold values include threshold value 1 and threshold value 2, wherein threshold value 1 corresponds to t1 moment and t2 moment, and threshold value 2 corresponds to t3 moment.

[0180] The network device can indicate the plurality of threshold values through various implementation manners, and the following introduces several possible implementation manners.

[0181] In one possible implementation manner, the network device indicates that t1 moment corresponds to threshold value 1, and indicates that other prediction moments after t1 moment correspond to threshold value 2.

[0182] In another possible implementation manner, the network device indicates the threshold value corresponding to each prediction moment, for example, indicates that t1 moment, t2 moment, and t3 moment correspond to threshold value 1, threshold value 2, and threshold value 3 respectively.

[0183] In another possible implementation manner, the network device indicates that t1 moment corresponds to threshold value 1, and indicates the offset of the threshold value of other prediction moments after t1 moment relative to threshold value 1, for example, indicates △th2 and △th3, wherein △th2 is the offset of threshold value 2 of t2 moment relative to threshold value 1 of t1 moment, and △th3 is the offset of threshold value 3 of t3 moment relative to threshold value 1 of t1 moment. The terminal device can determine the threshold value corresponding to other prediction moments according to threshold value 1 corresponding to t1 moment and the offset corresponding to other prediction moments.

[0184] In another possible implementation, the network device indicates a threshold 1 corresponding to the t1 moment, and indicates a threshold decay factor m, that is, implicitly indicates the threshold corresponding to other prediction moments after the t1 moment as: threshold 1+n×m, where n represents the n th prediction moment after the t1 moment. For example, the t2 moment is the first prediction moment after the t1 moment, and the threshold 2 corresponding to the t2 moment is threshold 1+m, the t3 moment is the second prediction moment after the t1 moment, and the threshold 3 corresponding to the t3 moment is threshold 1+2×m.

[0185] In another possible implementation, the network device indicates that the same threshold is shared by part of the prediction moments, for example, the t1 moment and the t2 moment correspond to the threshold 1, and the t3 moment and the t4 moment correspond to the threshold 2. In this way, the number of thresholds is less than the number of prediction moments.

[0186] For at least one performance indicator, the network device can indicate different thresholds corresponding to different performance indicators at different prediction moments. The correspondence between the threshold and the performance indicator and the prediction moment can be presented in the form of a table, such as Table 1 and Table 2.

[0187] Table 1

[0188] Table 2

[0189] The above Table 1 shows the thresholds corresponding to the performance indicators related to the RSRP of the beam at different prediction moments. The performance indicators related to the RSRP of the beam include the difference of the measured Top K L1-RSRP, the difference of the predicted Top K L1-RSRP, the difference of the average value of the measured Top K L1-RSRP, and the difference of the average value of the predicted Top K L1-RSRP. Wherein, k takes the value of 1, 2…K.

[0190] The above Table 2 shows the thresholds corresponding to the performance indicators related to the beam prediction accuracy at different prediction moments. The performance indicators related to the beam prediction accuracy include Top k (%), k takes the value of 1, 2…K.

[0191] It should be understood that the thresholds of different performance indicators at different prediction moments shown in the above Table 1 and Table 1 are only examples and do not constitute a limitation on the protection scope of the embodiments of the present application.

[0192] It should also be understood that the above Table 1 and Table 2 can also be combined into one table. The network device can indicate the thresholds of part or all of the performance indicators at different prediction moments in one table.

[0193] S502, the terminal device determines a measurement result corresponding to each threshold value in the at least one threshold value, the measurement result corresponding to each threshold value being a measurement result of the first performance indicator at each prediction time corresponding to each threshold value, the at least one threshold value being at least one threshold value in the plurality of threshold values indicated by the network device in S501, in other words, the plurality of threshold values including the at least one threshold value.

[0194] The measurement result can be replaced by a monitoring result. The following description takes the monitoring result as an example.

[0195] Optionally, before S502, the method 500 further includes: the network device sends a prediction resource to the terminal device, and then the network device sends a downlink control information (DCI) to the terminal device, for triggering the terminal device to perform a prediction task. After receiving the DCI, the terminal device performs measurement and / or prediction based on a terminal-side model or function, to obtain prediction information at a plurality of prediction times. Then, the terminal device sends the prediction information to the network device. Optionally, the network device can send a monitoring resource to the terminal device, and trigger the terminal device to monitor the first performance indicator through the DCI. The terminal device determines the value of the first performance indicator at each prediction time in the at least one prediction time based on the monitoring resource.

[0196] It should be noted that, if the network device does not send the monitoring resource to the terminal device, the terminal device can reuse other prediction resources to monitor the first performance indicator.

[0197] After the terminal device determines the value of the first performance indicator at each prediction time and the threshold value of the first performance indicator at each prediction time, the terminal device further determines whether the value of the first performance indicator at each prediction time meets the threshold value corresponding to the prediction time, and then determines the monitoring result of the first performance indicator at each prediction time, and determines the monitoring result corresponding to each threshold value.

[0198] When the value of the first performance indicator at a prediction time meets the threshold value corresponding to the prediction time, the monitoring result of the first performance indicator at the prediction time includes a non-triggering event, and when the value of the first performance indicator at a prediction time does not meet the threshold value corresponding to the prediction time, the value of the first performance indicator at the prediction time includes a triggering event.

[0199] It should be noted that, the value of the first performance indicator meeting the threshold value in the embodiments of the present application can include: the value of the first performance indicator being greater than or equal to the threshold value, or the value of the first performance indicator being less than or equal to the threshold value.

[0200] For example, the first performance indicator is Top 1 (%), and the value of the first performance indicator satisfying the threshold value means that the value of the first performance indicator is greater than or equal to the threshold value.

[0201] For another example, the first performance indicator is the difference of the measured Top 1 L1-RSRP, and the value of the first performance indicator satisfying the threshold value means that the value of the first performance indicator is less than or equal to the threshold value.

[0202] It should be noted that the at least one threshold value in this step can be the multiple threshold values indicated by the network device in S501, or the at least one threshold value in this step is part of the multiple threshold values indicated by the network device in S501, that is, the number of the at least one threshold value is less than the number of the multiple threshold values.

[0203] First, the case where the at least one threshold value is the multiple threshold values will be described.

[0204] It should be understood that each threshold value in the at least one threshold value corresponds to at least one prediction time, including: each threshold value in the at least one threshold value corresponds to one prediction time (hereinafter referred to as case one), and each threshold value in the at least one threshold value corresponds to multiple prediction times (hereinafter referred to as case two). For these two cases, the terminal device can determine the monitoring result corresponding to each threshold value based on the determination rule one, which includes: if the value of the first performance indicator at all prediction times corresponding to the first threshold value in the at least one threshold value satisfies the first threshold value, the monitoring result corresponding to the first threshold value includes a non-triggering event, or the monitoring result corresponding to the first threshold value is a non-triggering event; if the value of the first performance indicator at any prediction time corresponding to the first threshold value does not satisfy the first threshold value, the monitoring result corresponding to the first threshold value includes a triggering event, or the monitoring result corresponding to the first threshold value is a triggering event. Wherein the first threshold value is any one of the at least one threshold value.

[0205] In combination with the above determination rule one, the monitoring result corresponding to each threshold value in the above case one will be exemplarily described first. Here, a first assumption is made: the multiple threshold values include threshold value 1, threshold value 2, and threshold value 3, wherein threshold value 1 corresponds to t1 time, threshold value 2 corresponds to t2 time, and threshold value 3 corresponds to t3 time.

[0206] Based on the above first assumption, in one possible case (hereinafter referred to as case one in the first assumption), if the value of the first performance indicator at t1 time satisfies threshold value 1, the monitoring result corresponding to threshold value 1 includes a non-triggering event. If the value of the first performance indicator at t2 time satisfies threshold value 2, the monitoring result corresponding to threshold value 2 includes a non-triggering event. If the value of the first performance indicator at t3 time does not satisfy threshold value 3, the monitoring result corresponding to threshold value 3 includes a triggering event.

[0207] In this case, the terminal device determines the monitoring result of the first performance indicator on the threshold 1, the threshold 2 and the threshold 3, that is, the at least one threshold is the plurality of thresholds. The monitoring result corresponding to the threshold 1 is the monitoring result of the first performance indicator at the time t1, that is, no event is triggered, the monitoring result corresponding to the threshold 2 is the monitoring result of the first performance indicator at the time t2, that is, no event is triggered, and the monitoring result corresponding to the threshold 3 is the monitoring result of the first performance indicator at the time t3, that is, an event is triggered.

[0208] In this case, each threshold corresponds to a prediction time, and the first performance indicator at a prediction time corresponds to a monitoring result. Therefore, each threshold corresponds to a monitoring result.

[0209] In combination with the above determination rule one, the monitoring result corresponding to each threshold in the above case two is exemplified as follows. Here, a second assumption is made: the plurality of thresholds include the threshold 1 and the threshold 2, wherein the threshold 1 corresponds to the time t1 and the time t2, and the threshold 2 corresponds to the time t3 and the time t4.

[0210] Based on the above second assumption, in a possible case (hereinafter referred to as case one in the second assumption), the monitoring result of each threshold is determined according to the monitoring result of each prediction time corresponding to each threshold. Specifically, if the monitoring result of the first performance indicator at all prediction times corresponding to a threshold includes no event, the monitoring result corresponding to the threshold includes no event; if the monitoring result of the first performance indicator at any prediction time corresponding to a threshold includes an event, the monitoring result corresponding to the threshold includes an event.

[0211] For example, the value of the first performance indicator at the time t1 satisfies the threshold 1, and the value of the first performance indicator at the time t2 satisfies the threshold 1, the monitoring result of the first performance indicator at the time t1 includes no event, the monitoring result of the first performance indicator at the time t2 includes no event, and the monitoring result corresponding to the threshold 1 includes no event. For another example, the value of the first performance indicator at the time t1 does not satisfy the threshold 1, and / or the value of the first performance indicator at the time t2 does not satisfy the threshold 1, the monitoring result of the first performance indicator at the time t1 includes an event, and / or the monitoring result of the first performance indicator at the time t2 includes an event, and the monitoring result corresponding to the threshold 1 includes an event.

[0212] Similarly, if the value of the first performance indicator at the time t3 satisfies the threshold 2, and the value of the first performance indicator at the time t4 satisfies the threshold 2, the monitoring result corresponding to the threshold 2 includes no trigger event, if the monitoring result of the first performance indicator at the time t3 includes no trigger event, and the monitoring result of the first performance indicator at the time t4 includes no trigger event. If the value of the first performance indicator at the time t3 does not satisfy the threshold 2, and / or the value of the first performance indicator at the time t4 does not satisfy the threshold 2, the monitoring result corresponding to the threshold 2 includes trigger event, if the monitoring result of the first performance indicator at the time t3 includes trigger event, and / or the monitoring result of the first performance indicator at the time t4 includes trigger event.

[0213] In this case, each threshold corresponds to a plurality of predicted times, and each threshold corresponds to a monitoring result.

[0214] In the above assumption one, each threshold in the plurality of thresholds corresponds to a predicted time, and in the above assumption two, each threshold in the plurality of thresholds corresponds to a plurality of predicted times. Of course, the plurality of thresholds can also include thresholds corresponding to one predicted time and thresholds corresponding to a plurality of predicted times at the same time, for example, the plurality of thresholds includes the threshold 1 and the threshold 2, wherein the threshold 1 corresponds to the time t1, the threshold 2 corresponds to the time t2 and the time t3.

[0215] For the above case two, the terminal device can also determine the monitoring result corresponding to each threshold based on the determination rule two, the determination rule two includes: if the value of the first performance indicator at any predicted time corresponding to the first threshold in the at least one threshold satisfies the first threshold, the monitoring result of the any predicted time includes no trigger event; if the value of the first performance indicator at any predicted time corresponding to the first threshold does not satisfy the first threshold, the monitoring result of the any predicted time includes trigger event.

[0216] In combination with the above determination rule two, the monitoring result corresponding to each threshold in the above case two is exemplified as follows.

[0217] Based on the above assumption two, in a possible case (hereinafter referred to as case two in assumption two), if the value of the first performance indicator at the time t1 satisfies the threshold 1, the monitoring result at the time t1 includes no trigger event, if the value of the first performance indicator at the time t2 satisfies the threshold 1, the monitoring result at the time t2 includes no trigger event, for the threshold 1, the monitoring result corresponding thereto includes two no trigger events. If the value of the first performance indicator at the time t3 satisfies the threshold 2, the monitoring result at the time t3 includes no trigger event, if the value of the first performance indicator at the time t4 satisfies the threshold 2, the monitoring result at the time t4 includes trigger event, for the threshold 2, the monitoring result corresponding thereto includes one trigger event and one no trigger event.

[0218] In this case, the monitoring result of each threshold is determined according to the monitoring result of each prediction moment corresponding to each threshold. Each threshold corresponds to multiple prediction moments, and each prediction moment corresponds to a monitoring result. Therefore, each threshold corresponds to multiple monitoring results.

[0219] The following describes a case where the at least one threshold is part of the multiple thresholds.

[0220] For example, the multiple thresholds include threshold 1, threshold 2, and threshold 3, where threshold 1 corresponds to time t1, threshold 2 corresponds to time t2, and threshold 3 corresponds to time t3. When time t1 arrives, the terminal device monitors the first performance indicator at time t1. If the value of the first performance indicator at time t1 meets threshold 1, the monitoring result of the first performance indicator at time t1 includes no triggering event. Then, when time t2 arrives, the terminal device monitors the first performance indicator at time t2. If the value of the first performance indicator at time t2 does not meet threshold 2, the monitoring result of the first performance indicator at time t2 includes a triggering event, and the terminal device no longer monitors the first performance indicator at time t3, but instead informs the network device that threshold 2 is not met, or in other words, that there is a threshold in the multiple thresholds indicated by the network device that cannot be met.

[0221] In this case, the terminal device determines the monitoring result corresponding to threshold 1 and the monitoring result corresponding to threshold 2, and does not determine the monitoring result corresponding to threshold 3. That is, the at least one threshold includes threshold 1 and threshold 2, the multiple thresholds include threshold 1, threshold 2, and threshold 3, and the at least one threshold is part of the multiple thresholds.

[0222] S503, the terminal device generates a first measurement result according to the monitoring result corresponding to each threshold in the at least one threshold.

[0223] The measurement result can be replaced by the monitoring result. The following describes the monitoring result as an example.

[0224] The first monitoring result includes the monitoring result of the first performance indicator at the at least one prediction moment corresponding to each threshold in the multiple thresholds. For example, “0” represents no triggering event and “1” represents a triggering event. Of course, “0” can also represent a triggering event, and “1” can represent no triggering event. The embodiments of the present application do not limit this.

[0225] The first monitoring result is described in detail below in combination with the description in S502.

[0226] For the case one in hypothesis one, the first monitoring result can include a combination of triggering events and no triggering events, which is described below as an example:

[0227] In one example, the first monitoring result includes three non-trigger events, denoted as [0, 0, 0], indicating that the monitoring result of the first performance indicator at t1 corresponding to threshold 1 includes a non-trigger event, the monitoring result of the first performance indicator at t2 corresponding to threshold 2 includes a non-trigger event, and the monitoring result of the first performance indicator at t3 corresponding to threshold 3 includes a non-trigger event.

[0228] In another example, the first monitoring result includes two non-trigger events and one trigger event, denoted as [0, 0, 1], indicating that the monitoring result of the first performance indicator at t1 corresponding to threshold 1 includes a non-trigger event, the monitoring result of the first performance indicator at t2 corresponding to threshold 2 includes a non-trigger event, and the monitoring result of the first performance indicator at t3 corresponding to threshold 3 includes a trigger event.

[0229] In another example, the first monitoring result includes one non-trigger event and two trigger events, denoted as [0, 1, 1], indicating that the monitoring result of the first performance indicator at t1 corresponding to threshold 1 includes a non-trigger event, the monitoring result of the first performance indicator at t2 corresponding to threshold 2 includes a trigger event, and the monitoring result of the first performance indicator at t3 corresponding to threshold 3 includes a trigger event.

[0230] In another example, the first monitoring result includes three trigger events, denoted as [1, 1, 1], indicating that the monitoring result of the first performance indicator at t1 corresponding to threshold 1 includes a trigger event, the monitoring result of the first performance indicator at t2 corresponding to threshold 2 includes a trigger event, and the monitoring result of the first performance indicator at t3 corresponding to threshold 3 includes a trigger event.

[0231] For the case one in hypothesis two, the first monitoring result can include a combination of trigger events and non-trigger events, which are illustrated as follows:

[0232] In one example, the first monitoring result includes two non-trigger events, denoted as [0, 0], indicating that the monitoring result corresponding to threshold 1 includes a non-trigger event and the monitoring result corresponding to threshold 2 includes a non-trigger event.

[0233] In another example, the first monitoring result includes one trigger event and one non-trigger event, denoted as [0, 1] or [1, 0]. Wherein, [0, 1] indicates that the monitoring result corresponding to threshold 1 includes a non-trigger event and the monitoring result corresponding to threshold 2 includes a trigger event; [1, 0] indicates that the monitoring result corresponding to threshold 1 includes a trigger event and the monitoring result corresponding to threshold 2 includes a non-trigger event.

[0234] In another example, the first monitoring result includes two trigger events, denoted as [1,1,], which means the monitoring result corresponding to threshold 1 includes a trigger event, and the monitoring result corresponding to threshold 2 includes a trigger event.

[0235] For case two in hypothesis two, the first monitoring result can include a combination of trigger events and non-trigger events, which is illustrated as follows:

[0236] In one example, the first monitoring result includes four non-trigger events, denoted as [(0,0);(0,0)], where the first group (0,0) means the monitoring result corresponding to threshold 1 includes two non-trigger events (corresponding to time t1 and time t2), and the second group (0,0) means the monitoring result corresponding to threshold 2 includes two non-trigger events (corresponding to time t3 and time t4).

[0237] In another example, the first monitoring result includes one trigger event and three non-trigger events, denoted as [(0,0);(0,1)], or, [(0,0);(1,0)], or, [(0,1);(0,0)], or, [(1,0);(0,0)]. Wherein, the first group (0,0) in [(0,0);(0,1)] means the monitoring result corresponding to threshold 1 includes two non-trigger events (corresponding to time t1 and time t2), and the second group (0,1) means the monitoring result corresponding to threshold 2 includes one non-trigger event (corresponding to time t3) and one trigger event (corresponding to time t4). The first group (0,0) in [(0,0);(1,0)] means the monitoring result corresponding to threshold 1 includes two non-trigger events (corresponding to time t1 and time t2), and the second group (1,0) means the monitoring result corresponding to threshold 2 includes one trigger event (corresponding to time t3) and one non-trigger event (corresponding to time t4). The first group (0,1) in [(0,1);(0,0)] means the monitoring result corresponding to threshold 1 includes one non-trigger event (corresponding to time t2) and one trigger event (corresponding to time t2), and the second group (0,0) means the monitoring result corresponding to threshold 2 includes two non-trigger events (corresponding to time t3 and time t4). The first group (1,0) in [(1,0);(0,0)] means the monitoring result corresponding to threshold 1 includes one trigger event (corresponding to time t1) and one non-trigger event (corresponding to time t2), and the second group (0,0) means the monitoring result corresponding to threshold 2 includes two non-trigger events (corresponding to time t3 and time t4).

[0238] In another example, the first monitoring result includes two trigger events and two non-trigger events, denoted as [(0, 0); (1, 1)], or [(1, 1); (0, 0)], or, [(0, 1); (0, 1)], or, [(1, 0); (1, 0)], or, [(0, 1); (1, 0)], or, [(1, 0); (0, 1)].

[0239] In the first group (0, 0) in [(0, 0); (1, 1)], the monitoring result corresponding to threshold 1 includes two non-trigger events (corresponding to t1 moment and t2 moment), and the second group (1, 1) indicates that the monitoring result corresponding to threshold 2 includes two trigger events (corresponding to t3 moment and t4 moment).

[0240] The first group (1, 1) in [(1, 1); (0, 0)] indicates that the monitoring result corresponding to threshold 1 includes two trigger events (corresponding to t1 moment and t2 moment), and the second group (0, 0) indicates that the monitoring result corresponding to threshold 2 includes two non-trigger events (corresponding to t3 moment and t4 moment).

[0241] The first group (0, 1) in [(0, 1); (0, 1)] indicates that the monitoring result corresponding to threshold 1 includes one non-trigger event (corresponding to t1 moment) and one trigger event (corresponding to t2 moment), and the second group (0, 1) indicates that the monitoring result corresponding to threshold 2 includes one non-trigger event (corresponding to t3 moment) and one trigger event (corresponding to t4 moment).

[0242] The first group (1, 0) in [(1, 0); (1, 0)] indicates that the monitoring result corresponding to threshold 1 includes one trigger event (corresponding to t1 moment) and one non-trigger event (corresponding to t2 moment), and the second group (1, 0) indicates that the monitoring result corresponding to threshold 2 includes one trigger event (corresponding to t3 moment) and one non-trigger event (corresponding to t4 moment).

[0243] The first group (0, 1) in [(0, 1); (1, 0)] indicates that the monitoring result corresponding to threshold 1 includes one non-trigger event (corresponding to t1 moment) and one trigger event (corresponding to t2 moment), and the second group (1, 0) indicates that the monitoring result corresponding to threshold 2 includes one trigger event (corresponding to t3 moment) and one non-trigger event (corresponding to t4 moment).

[0244] The first group (1, 0) in [(1, 0); (0, 1)] indicates that the monitoring result corresponding to threshold 1 includes one trigger event (corresponding to t1 moment) and one non-trigger event (corresponding to t2 moment), and the second group (0, 1) indicates that the monitoring result corresponding to threshold 2 includes one non-trigger event (corresponding to t3 moment) and one trigger event (corresponding to t4 moment).

[0245] In another example, the first monitoring result includes three trigger events and one non-trigger event, denoted as [(0, 1); (1, 1)], or, [(1, 0); (1, 1)], or, [(1, 1); (0, 1)], or, [(1, 1); (1, 0)].

[0246] In the [(0, 1); (1, 1)], the first group (0, 1) indicates that the monitoring result corresponding to the threshold 1 includes one non-trigger event (corresponding to the t1 moment) and one trigger event (corresponding to the t2 moment), and the second group (1, 1) indicates that the monitoring result corresponding to the threshold 2 includes two trigger events (corresponding to the t3 moment and the t4 moment).

[0247] In the [(1, 0); (1, 1)], the first group (1, 0) indicates that the monitoring result corresponding to the threshold 1 includes one trigger event (corresponding to the t1 moment) and one non-trigger event (corresponding to the t2 moment), and the second group (1, 1) indicates that the monitoring result corresponding to the threshold 2 includes two trigger events (corresponding to the t3 moment and the t4 moment).

[0248] In the [(1, 1); (0, 1)], the first group (1, 1) indicates that the monitoring result corresponding to the threshold 1 includes two trigger events (corresponding to the t1 moment and the t2 moment), and the second group (0, 1) indicates that the monitoring result corresponding to the threshold 2 includes one non-trigger event (corresponding to the t3 moment) and one trigger event (corresponding to the t4 moment).

[0249] In the [(1, 1); (1, 0)], the first group (1, 1) indicates that the monitoring result corresponding to the threshold 1 includes two trigger events (corresponding to the t1 moment and the t2 moment), and the second group (1, 0) indicates that the monitoring result corresponding to the threshold 2 includes one trigger event (corresponding to the t3 moment) and one non-trigger event (corresponding to the t4 moment).

[0250] In another example, the first monitoring result includes four trigger events, denoted as [(1, 1); (1, 1)], wherein the first group (1, 1) indicates that the monitoring result corresponding to the threshold 1 includes two trigger events (corresponding to the t1 moment and the t2 moment), and the second group (1, 1) indicates that the monitoring result corresponding to the threshold 2 includes two trigger events (corresponding to the t3 moment and the t4 moment).

[0251] It should be understood that, for the case that the at least one threshold is part of the plurality of thresholds, the first monitoring result can include the first threshold that is not satisfied, or include one threshold in the plurality of thresholds that cannot be satisfied.

[0252] S504, the terminal device sends second indication information to the network device, and the second indication information is used to indicate the first measurement result. Correspondingly, the network device receives the second indication information.

[0253] The measurement result can be replaced by the monitoring result. The following description takes the monitoring result as an example.

[0254] Referring to the description of S503, for the case one or case two in the assumption one, or the case one or case two in the assumption two, optionally, the second indication information comprises one or more of the following: a plurality of bits; or, the first prediction moment; or, the value of the first performance indicator at the second prediction moment.

[0255] It should be noted that for the case one or case two in the assumption one, or the case one in the assumption two, the plurality of bits correspond to the plurality of thresholds one by one; for the case two in the assumption two, the plurality of bits correspond to the plurality of prediction moments one by one, and the plurality of prediction moments are the plurality of threshold moments corresponding to the plurality of thresholds. It should be understood that since each threshold corresponds to at least one prediction moment, the plurality of thresholds correspond to the plurality of prediction moments.

[0256] The following illustrates that the second indication information comprises a plurality of bits, and the plurality of bits correspond to the plurality of thresholds one by one.

[0257] Based on the case one or case two in the above assumption one, exemplarily, the second indication information comprises three bits, and the bit state is [0, 0, 1]. The first bit corresponds to the monitoring result of the threshold 1, or in other words, the monitoring result of the first performance indicator at the moment t1. The second bit corresponds to the monitoring result of the threshold 2, or in other words, the monitoring result of the first performance indicator at the moment t2. The third bit corresponds to the threshold 3, or in other words, the monitoring result of the first performance indicator at the moment t3.

[0258] The terminal device can report the monitoring results corresponding to different thresholds in the form of a table, see Table 3.

[0259] Table 3

[0260] Based on the case one in the above assumption two, exemplarily, the second indication information comprises two bits, and the bit state is [0, 1]. The first bit corresponds to the monitoring result of the threshold 1, and the second bit corresponds to the monitoring result of the threshold 2.

[0261] The following illustrates that the second indication information comprises a plurality of bits, and the plurality of bits correspond to the plurality of prediction moments one by one.

[0262] Based on the case two in the second assumption, exemplarily, the second indication information includes four bits, the bit states are [(0, 0); (0, 1)], the first bit state corresponds to the t1 moment, indicating the monitoring result of the first performance index at the t1 moment corresponding to the threshold 1, the second bit t2 moment, indicating the monitoring result of the first performance index at the t2 moment corresponding to the threshold 1, the third bit corresponds to the t3 moment, indicating the monitoring result of the first performance index at the t3 moment corresponding to the threshold 2, and the fourth bit corresponds to the t4 moment, indicating the monitoring result of the first performance index at the t4 moment corresponding to the threshold 4.

[0263] The case that the second indication information includes the first predicted moment is described below.

[0264] The monitoring result of the first performance index at the first predicted moment and the predicted moment after the first predicted moment includes a trigger event, or the monitoring result of the first performance index at the first predicted moment and the predicted moment before the first predicted moment includes a non-trigger event.

[0265] For example, the monitoring result of the first performance index at the t1 moment includes a non-trigger event, the monitoring result of the first performance index at the t2 moment includes a non-trigger event, and the monitoring result of the first performance index at the t3 moment includes a trigger event. It can be considered that the monitoring result of the first performance index at the predicted moment after the t3 moment includes a trigger event. The terminal device can carry the t3 moment in the second indication information, that is, the first predicted moment is the t3 moment. After the network device receives the second indication information, it can be determined that the monitoring result of the first performance index at the t3 moment and the predicted moment after the t3 moment includes a trigger event, and the monitoring result of the first performance index at the t1 moment and the t2 moment before the t3 moment includes a non-trigger event. Or, the terminal device can carry the t2 moment in the second indication information, that is, the first predicted moment is the t2 moment. Then, after the network device receives the second indication information, it can be determined that the value of the first performance index at the t2 moment and the predicted moment before the t2 moment includes a non-trigger event, and the monitoring result of the first performance index at the predicted moment after the t2 moment includes a trigger event.

[0266] The value of the first performance index at the second predicted moment included in the second indication information is exemplified below. The monitoring result of the first performance index at the second predicted moment includes a trigger event.

[0267] FIG. 6 is a schematic diagram of reporting a value of a performance indicator according to an embodiment of the present application. As shown in FIG. 6, the terminal device monitors the first performance indicator at t1, the first performance indicator at t2, and the first performance indicator at t3 according to the monitoring resource configured by the network device. If the value of the first performance indicator at t1 satisfies the threshold corresponding to t1, the monitoring result of the first performance indicator at t1 includes no triggering event. If the value of the first performance indicator at t2 satisfies the threshold corresponding to t2, the monitoring result of the first performance indicator at t2 includes no triggering event. If the value of the first performance indicator at t3 does not satisfy the threshold corresponding to t3, the monitoring result of the first performance indicator at t3 includes a triggering event. Then, the second prediction time is t3, and the terminal device can carry the value of the first performance indicator at t3 in the second indication information.

[0268] It should be understood that the terminal device can send the monitoring result of the first performance indicator at t2 to the network device after t1, send the monitoring result of the first performance indicator at t2 to the network device after t2, and send the monitoring result of the first performance indicator at t3 to the network device after t3. Alternatively, the network device can send the monitoring results of the first performance indicators at t1, t2, and t3 to the terminal device after t3. The specific sending manner depends on the configuration of the network device.

[0269] Optionally, the terminal device can label the value of the first performance indicator with t3, for example, report the combination of t3 and the value of t3, to indicate that the reported value of the first performance indicator is the value of the first performance indicator at t3. In this way, after receiving the second indication information, the network device can determine that the monitoring result of the first performance indicator at t3 includes a triggering event, and the monitoring result of the first performance indicator at other prediction times includes no triggering event.

[0270] It should be understood that the present application considers the case of a single performance indicator. For the case of multiple performance indicators, if the values of other performance indicators at t3 do not satisfy the threshold, the terminal device can report the values of the multiple performance indicators at t3. In this case, it is further necessary to divide different performance indicators, for example, using different identifiers to distinguish different performance indicators.

[0271] After receiving the second indication information, the network device can generate a monitoring decision according to the content indicated by the second indication information. The monitoring decision is, for example, modifying the number of prediction times, model / function fallback, model / function switching, etc.

[0272] In one example, the predicted time instants indicated by the network device include the t1 time instant, the t2 time instant, and the t3 time instant. If the second indication information includes the t3 time instant, the network device can determine that the performance of the model or function at the t3 time instant is likely to be poor, and the network device can indicate that the monitoring results of the prediction information and the performance indicators of the next two time instants are reported, that is, the number of prediction time instants is modified from three to two.

[0273] It should be understood that, for the case that the at least one threshold is part of the plurality of thresholds, the first monitoring result can include the first unsatisfied threshold, or include that one threshold in the plurality of thresholds cannot be satisfied. That is, the terminal device can indicate, through the second indication information, the first unsatisfied threshold, or indicate that one threshold in the plurality of thresholds cannot be satisfied, or indicate that the plurality of thresholds cannot be satisfied, or use 1 bit to indicate that there is a monitoring condition that does not satisfy the threshold. In this way, after receiving the second indication information, the network device can indicate a monitoring decision to the terminal device, for example, instruct the terminal device to retrain the model or function, or reissue the model or function to the terminal device, or instruct the terminal device to exit the AI function, or instruct the terminal device to switch the AI model or function.

[0274] In the method 500 described above, the network device indicates the plurality of thresholds to the terminal device, which can be understood as that the network device instructs the terminal device to independently monitor the first performance indicators at different prediction time instants based on the plurality of thresholds. Such a monitoring manner is more detailed, and a more fine-grained monitoring result can be obtained. Then, the terminal device indicates the monitoring results of the first performance indicators at different prediction time instants to the network device through the second indication information. In this way, after receiving the second indication information, the network device can generate a more accurate monitoring decision based on the more fine-grained monitoring result.

[0275] The threshold in the embodiments of the present application can be replaced by a monitoring threshold, a monitoring threshold, or a reporting threshold. The reported monitoring result can be replaced by a monitoring parameter, a reporting parameter, or a reporting result.

[0276] In the above description, the network device indicates a plurality of thresholds for one performance indicator. In another embodiment, the network device can indicate one threshold for one performance indicator, and the plurality of prediction time instants corresponding to the one performance indicator share the one threshold. For details, see the description of the method 700 below.

[0277] FIG. 7 is a schematic diagram of another communication method 700 provided by the embodiments of the present application. The steps of the method 700 can be performed by the terminal side and the network side interacting with each other, where the terminal side is, for example, a terminal device or a communication module in the terminal device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) in the terminal device responsible for communication functions, and hereinafter the terminal device is taken as an example for description. The network side is, for example, a network device or a communication module in the network device, or a circuit or chip (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) in the network device responsible for communication functions, and hereinafter the network device is taken as an example for description.

[0278] The method 700 includes S701 to S703, and each step is described in detail below.

[0279] S701, the network device sends third indication information to the terminal device, where the third indication information is used to indicate at least one threshold, and the at least one threshold corresponds to at least one index, the index is used for monitoring of a model or a function, or the index corresponds to performance of the model or the function, and the index can also be referred to as a performance index, and hereinafter the performance index is taken as an example for description.

[0280] Herein, the measurement result can be replaced by a monitoring result. Hereinafter the monitoring result is taken as an example for description.

[0281] The performance index is introduced, and the description is the same as that in the foregoing description, and details are not described herein.

[0282] The at least one threshold and the at least one performance index are in a one-to-one correspondence, that is, one threshold corresponds to one performance index, or each performance index has a corresponding threshold. Each threshold in the at least one threshold corresponds to a plurality of prediction moments, and different thresholds correspond to the same prediction moment.

[0283] For example, the at least one performance index includes a performance index 1 and a performance index 2, and the plurality of prediction moments includes a t1 moment, a t2 moment, and a t3 moment, where a threshold 1 corresponds to the performance index 1 at the t1 moment, the t2 moment, and the t3 moment, and a threshold 2 corresponds to the performance index 2 at the t1 moment, the t2 moment, and the t3 moment. The correspondence between the threshold and the performance index can be embodied in the form of a table, for example, as shown in Table Four.

[0284] Table Four

[0285] It should be understood that the network device can indicate the threshold of all performance indexes in the at least one performance index through a table, or can individually indicate the threshold corresponding to each performance index, and the embodiments of the present application do not limit this.

[0286] S702, the terminal device determines a measurement result of each performance indicator corresponding to each threshold value in the at least one threshold value at each prediction time in the plurality of prediction times.

[0287] The measurement result can be replaced by a monitoring result. Hereinafter, the monitoring result is taken as an example for description.

[0288] As described above, the monitoring result of each performance indicator corresponding to each threshold value includes a triggering event or a non-triggering event.

[0289] In a possible implementation (hereinafter referred to as implementation one), the terminal device can determine the monitoring result of a second performance indicator corresponding to a second threshold value based on a third determination rule, the second performance indicator being one of the at least one performance indicator. The second threshold value is one of the at least one threshold value, and the third determination rule includes: if the value of the second performance indicator corresponding to the second threshold value at all prediction times meets the second threshold value, the monitoring result of the second performance indicator corresponding to the second threshold value includes a non-triggering event; if the value of the second performance indicator corresponding to the second threshold value at any prediction time in the plurality of prediction times does not meet the second threshold value, the monitoring result of the second performance indicator corresponding to the second threshold value includes a triggering event. The second threshold value is any one of the at least one threshold value.

[0290] For example, the at least one threshold value includes threshold value 1 and threshold value 2, the threshold value 1 corresponds to a performance indicator 1, the threshold value 2 corresponds to a performance indicator 2, and the plurality of prediction times includes a t1 time, a t2 time, and a t3 time, i.e., the terminal device needs to monitor the performance indicator 1 and the performance indicator 2 at each prediction time in the t1 time, the t2 time, and the t3 time. If the performance indicator 1 at the t1 time meets the threshold value 1, the performance indicator 1 at the t2 time meets the threshold value 1, and the performance indicator 1 at the t3 time meets the threshold value 1, the monitoring result of the performance indicator 1 corresponding to the threshold value 1 includes a non-triggering event. If the performance indicator 2 at at least one prediction time in the t1 time, the t2 time, and the t3 time does not meet the threshold value 2, the monitoring result of the performance indicator 2 corresponding to the threshold value 2 includes a triggering event. Based on the third determination rule, each threshold value corresponds to a monitoring result.

[0291] In another possible implementation (hereinafter referred to as implementation two), the terminal device can determine the monitoring result of the second performance indicator corresponding to the second threshold based on a fourth determination rule. The fourth determination rule includes: if the value of the second performance indicator corresponding to the second threshold at any one of the plurality of prediction moments satisfies the second threshold, the monitoring result of the second performance indicator corresponding to the second threshold at the any one of the plurality of prediction moments includes no triggering event; if the value of the second performance indicator corresponding to the second threshold at any one of the plurality of prediction moments does not satisfy the second threshold, the monitoring result of the second performance indicator corresponding to the second threshold at the any one of the plurality of prediction moments includes triggering event. Based on the fourth determination rule, each threshold corresponds to a plurality of monitoring results, and the plurality of monitoring results correspond to the plurality of prediction moments one by one.

[0292] For example, the at least one threshold includes threshold 1 and threshold 2, threshold 1 corresponds to performance indicator 1, threshold 2 corresponds to performance indicator 2, and the plurality of prediction moments includes t1 moment, t2 moment, and t3 moment. If the value of the performance indicator 1 corresponding to the threshold 1 at the t1 moment satisfies the threshold 1, the monitoring result of the performance indicator 1 corresponding to the threshold 1 at the t1 moment includes no triggering event, if the value of the performance indicator 1 corresponding to the threshold 1 at the t2 moment satisfies the threshold 1, the monitoring result of the performance indicator 1 corresponding to the threshold 1 at the t2 moment includes no triggering event, and if the value of the performance indicator 1 corresponding to the threshold 1 at the t3 moment satisfies the threshold 1, the monitoring result of the performance indicator 1 corresponding to the threshold 1 at the t3 moment includes triggering event. Thus, the monitoring result of the performance indicator 1 corresponding to the threshold 1 includes no triggering event (corresponding to t1), no triggering event (corresponding to t2), and triggering event (corresponding to t3).

[0293] Similarly, if the value of the performance indicator 2 corresponding to the threshold 2 at the t1 moment satisfies the threshold 2, the monitoring result of the performance indicator 2 corresponding to the threshold 2 at the t1 moment includes no triggering event, if the value of the performance indicator 2 corresponding to the threshold 2 at the t2 moment does not satisfy the threshold 2, the monitoring result of the performance indicator 2 corresponding to the threshold 2 at the t2 moment includes triggering event, and if the value of the performance indicator 2 corresponding to the threshold 2 at the t3 moment satisfies the threshold 2, the monitoring result of the performance indicator 2 corresponding to the threshold 2 at the t3 moment includes triggering event. Thus, the monitoring result of the performance indicator 2 corresponding to the threshold 2 includes no triggering event (corresponding to t1), triggering event (corresponding to t2), and triggering event (corresponding to t3).

[0294] It should be noted that, since the performance of the prediction accuracy or the model or function is probably reduced over time, for a threshold corresponding to multiple prediction time points, or multiple prediction time points sharing a threshold, in a possible implementation, the terminal device can determine the monitoring result of different prediction time point pairs in the order of prediction time points. If the value of the first performance indicator at a prediction time point meets the threshold corresponding to the prediction time point, the terminal device continues to monitor whether the value of the first performance indicator at the next prediction time point meets the threshold corresponding to the next prediction time point. When it is first determined that the value of the first performance indicator at a prediction time point does not meet the threshold corresponding to the prediction time point, the terminal device can stop monitoring the first performance indicator at the prediction time point after the prediction time point, that is, the terminal device considers that the monitoring result of the first performance indicator at all prediction time points after the prediction time point includes a trigger event.

[0295] For example, threshold 1 corresponds to performance indicator 1, and the multiple prediction time points include t1 time point, t2 time point and t3 time point, wherein the t2 time point is a prediction time point after the t1 time point, and the t3 time point is a prediction time point after the t2 time point. If the value of the performance indicator 1 at the t1 time point meets the threshold 1, the monitoring result of the performance indicator 1 at the t1 time point includes a non-trigger event, and if the value of the performance indicator 1 at the t2 time point does not meet the threshold 1, the monitoring result of the performance indicator 1 at the t2 time point includes a trigger event. Since the monitoring result of the performance indicator 1 at the t2 time point includes a trigger event, the terminal device can consider that the value of the performance indicator 1 at the prediction time point after the t2 time point does not meet the threshold 1, that is, the monitoring result of the performance indicator 1 at the prediction time point (for example, t3 time point) after the t2 time point includes a trigger event. Therefore, the terminal device can stop monitoring the performance indicator 1 at the prediction time point (for example, t3 time point) after the t2 time point, that is, the terminal device determines that the monitoring result of the performance indicator 1 at the prediction time point (for example, t3 time point) after the t2 time point includes a trigger event without monitoring the performance indicator 1 at the prediction time point (for example, t3 time point) after the t2 time point.

[0296] S703, the terminal device sends fourth indication information to the network device, and the fourth indication information is used to indicate the measurement result. Correspondingly, the network device receives the fourth indication information.

[0297] The measurement result can be replaced by the monitoring result. Hereinafter, the monitoring result is taken as an example for description.

[0298] The monitoring result in this step includes the monitoring result of the performance indicator corresponding to each threshold at each predicted moment. The terminal device sends the monitoring result of each threshold at each predicted moment to the network device, so that the obtained monitoring result is more detailed, and then the network device can generate more accurate monitoring decisions based on the monitoring result reported by the terminal device.

[0299] Optionally, for the first implementation manner described in S702, the fourth indication information includes any of the following: at least one bit, or, at least one third predicted moment, or, a value or an identifier of the target performance indicator at at least one fourth predicted moment. The at least one bit corresponds to the at least one threshold in a one-to-one manner, and each bit can indicate the monitoring result of the performance indicator corresponding to the bit. For example, the bit state of a bit is 0, indicating that the monitoring result of the threshold corresponding to the bit includes no triggering event, and the bit state of a bit is 1, indicating that the monitoring result of the threshold corresponding to the bit includes triggering event.

[0300] For example, the monitoring result of the performance indicator corresponding to threshold 1 includes no triggering event, and the monitoring result of the performance indicator corresponding to threshold 2 includes triggering event, and the at least one bit includes two bits with values [0, 1], wherein the first bit corresponds to threshold 1, and the second bit corresponds to threshold 2.

[0301] Optionally, for the second implementation manner described in S702, the fourth indication information includes any of the following: at least one group of bits, or, at least one third predicted moment, or, a value or an identifier of the target performance indicator at at least one fourth predicted moment. The at least one group of bits corresponds to the at least one threshold in a one-to-one manner, in other words, one threshold corresponds to one group of bits. Each group of bits in the at least one group of bits includes a plurality of bits, and the plurality of bits correspond to the plurality of predicted moments in a one-to-one manner, in other words, one bit corresponds to one predicted moment. Each bit can indicate the monitoring result of the performance indicator at a predicted moment, for example, the bit state of a bit is 0, indicating that the monitoring result of the performance indicator at the predicted moment corresponding to the bit includes no triggering event, and the bit state of a bit is 1, indicating that the monitoring result of the performance indicator at the predicted moment corresponding to the bit includes triggering event. Since one group of bits corresponds to one threshold, and each bit in each group of bits corresponds to one predicted moment, one group of bits can be regarded as corresponding to a plurality of predicted moments.

[0302] For example, the monitoring result of the performance indicator 1 at the t1 moment corresponding to the threshold 1 includes no triggering event, the monitoring result of the performance indicator 1 at the t2 moment corresponding to the threshold 1 includes no triggering event, and the monitoring result of the performance indicator 1 at the t3 moment corresponding to the threshold 1 includes triggering event. A set of bit positions can be used to represent the monitoring result of the performance indicator 1 of the threshold 1 at the t1 moment, the t2 moment and the t3 moment, for example, the set of bit positions corresponding to the threshold 1 is [0, 0, 1], wherein the first bit position corresponds to the t1 moment, the second bit position corresponds to the t2 moment, and the third bit position corresponds to the t3 moment.

[0303] The following describes the case that the fourth indication information includes at least one third prediction moment.

[0304] If the monitoring result of each performance indicator in the at least one performance indicator at a certain prediction moment in the plurality of prediction moments includes triggering event, that is, the monitoring result of all performance indicators at the prediction moment includes triggering event, the prediction moment is the third prediction moment, and if there is at least one such prediction moment, there is at least one third prediction moment. After receiving the fourth indication information, the network device can determine that the monitoring result of all performance indicators at each prediction moment in the at least one third prediction moment includes triggering event, and then the network device can generate a monitoring decision, for example, no longer monitoring the performance indicators at the at least one third prediction moment.

[0305] For example, the at least one performance indicator includes a performance indicator 1 and a performance indicator 2, the performance indicator 1 corresponds to a threshold 1, the performance indicator 2 corresponds to a threshold 2, and the plurality of prediction moments includes a t1 moment and a t2 moment. If the value of the performance indicator 1 at the t1 moment satisfies the threshold 1 (that is, the monitoring result of the performance indicator of the performance indicator 1 at the t1 moment corresponding to the threshold 1 includes no triggering event), the value of the performance indicator 2 at the t1 moment satisfies the threshold 2 (that is, the monitoring result of the performance indicator of the performance indicator 2 at the t1 moment corresponding to the threshold 2 includes no triggering event), the value of the performance indicator 1 at the t2 moment does not satisfy the threshold 1 (that is, the monitoring result of the performance indicator of the performance indicator 1 at the t2 moment corresponding to the threshold 1 includes triggering event), and the value of the performance indicator 2 at the t2 moment does not satisfy the threshold 2 (that is, the monitoring result of the performance indicator of the performance indicator 2 at the t2 moment corresponding to the threshold 2 includes triggering event), the at least one third prediction moment includes the t2 moment.

[0306] For example, the at least one performance indicator includes performance indicator 1 and performance indicator 2, performance indicator 1 corresponds to threshold 1, performance indicator 2 corresponds to threshold 2, and the plurality of prediction time instants includes t1, t2 and t3. If the value of performance indicator 1 at t1 satisfies threshold 1, the value of performance indicator 2 at t1 satisfies threshold 2, the value of performance indicator 1 at t2 does not satisfy threshold 1, the value of performance indicator 2 at t2 does not satisfy threshold 2, the value of performance indicator 1 at t3 does not satisfy threshold 1, and the value of performance indicator 2 at t3 does not satisfy threshold 2, then the at least one third prediction time instant includes t2 and t3.

[0307] The following describes a case where the fourth indication information includes the value of the target performance indicator at the at least one fourth prediction time instant.

[0308] If the monitoring result of the target performance indicator in the at least one performance indicator at a certain prediction time instant in the plurality of prediction time instants includes a triggering event, and the monitoring result of the performance indicator other than the target performance indicator in the at least one performance indicator at the prediction time instant includes a non-triggering event, then the prediction time instant is the fourth prediction time instant, and if there is at least one such prediction time instant, there is at least one fourth prediction time instant. The target performance indicator is part of the at least one performance indicator at the fourth prediction time instant.

[0309] For example, the at least one performance indicator includes performance indicator 1 and performance indicator 2, performance indicator 1 corresponds to threshold 1, performance indicator 2 corresponds to threshold 2, and the plurality of prediction time instants includes t1 and t2. If the value of performance indicator 1 at t1 satisfies threshold 1 (i.e., the monitoring result of performance indicator 1 at t1 corresponding to threshold 1 includes a non-triggering event), the value of performance indicator 2 at t1 does not satisfy threshold 2 (i.e., the monitoring result of performance indicator 2 at t1 corresponding to threshold 2 includes a triggering event), the value of performance indicator 1 at t2 satisfies threshold 1 (i.e., the monitoring result of performance indicator 1 at t2 corresponding to threshold 1 includes a non-triggering event), and the value of performance indicator 2 at t2 does not satisfy threshold 2 (i.e., the monitoring result of performance indicator 2 at t2 corresponding to threshold 2 includes a triggering event), then the value of the target performance indicator at the at least one fourth prediction time instant includes the value of performance indicator 2 at t1 and the value of performance indicator 2 at t2.

[0310] In the method 700, the network device sends third indication information to the terminal device, indicating at least one threshold. It can be understood that the network device instructs the terminal device to monitor different performance indicators at different prediction moments independently based on the at least one threshold, and independently sets events for different prediction moments. The terminal device indicates the monitoring results of different performance indicators at different prediction moments to the network device based on the at least one threshold. Such a monitoring manner is more detailed, and the granularity of the reported monitoring results is smaller, which is beneficial to the network device to generate more accurate monitoring decisions.

[0311] In another embodiment, the network device can instruct the terminal device to independently monitor different performance indicators at different prediction moments, and report the values of different performance indicators at different prediction moments. See the description of method 800 below.

[0312] FIG. 8 is a schematic flowchart of another communication method 800 provided by the embodiments of the present application. The steps of the method 800 can be executed by the terminal side and the network side interaction, wherein the terminal side is, for example, a terminal device or a communication module in the terminal device, or a circuit or chip responsible for communication function in the terminal device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and hereinafter the terminal device is taken as an example for description. The network side is, for example, a network device or a communication module in the network device, or a circuit or chip responsible for communication function in the network device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and hereinafter the network device is taken as an example for description.

[0313] The method 800 includes S801-S803, and optionally, the method 800 further includes S804. Each step is described in detail below.

[0314] S801, the network device sends fifth indication information to the terminal device. Correspondingly, the terminal device receives the fifth indication information.

[0315] The fifth indication information is used to indicate the monitoring result of the first indicator. The first indicator is one of the plurality of indicators, which is used for monitoring of a model or a function, or said to correspond to the performance of the model or the function, which can also be called a performance indicator, and hereinafter the performance indicator is taken as an example for description.

[0316] Exemplarily, the fifth indication information is an identifier or an index of the first performance indicator, and after receiving the fifth indication information, the terminal device can determine that the first performance indicator needs to be monitored.

[0317] It should be understood that the network device can instruct the terminal device to report the monitoring result of at least one performance indicator. For ease of description, the network device instructs the first performance indicator in the at least one performance indicator as an example for description.

[0318] The performance indicator can refer to the description in the foregoing description, and will not be described here.

[0319] S802, the terminal device determines a plurality of measurement results according to the fifth indication information, and the plurality of measurement results include a measurement result of the first indicator at each of the plurality of predicted time points.

[0320] The measurement result can be replaced by the monitoring result, and the first performance indicator is described as an example in the following description. The first indicator can be replaced by the first performance indicator, and the first performance indicator is described as an example in the following description.

[0321] The terminal device determines that the first performance indicator needs to be monitored according to the fifth indication information.

[0322] Optionally, if the protocol stipulates that the performance indicator is independently monitored based on the predicted time point, or in other words, each predicted time point is independently monitored, the terminal device determines that the first performance indicator at each of the plurality of predicted time points needs to be monitored according to the fifth indication information and the protocol stipulation.

[0323] Optionally, monitoring the first performance indicator at each predicted time point includes generating a value of the first performance indicator at each predicted time point.

[0324] S803, the terminal device sends a plurality of monitoring results to the network device. The network device receives the plurality of monitoring results.

[0325] As described in S802, the plurality of monitoring results include a monitoring result of the first performance indicator at each of the plurality of predicted time points, that is, the plurality of monitoring results are one-to-one corresponding to the plurality of predicted time points, and one predicted time point corresponds to one monitoring result.

[0326] For example, the first performance indicator is Top 1 (%), the plurality of predicted time points include t1 time point, t2 time point and t3 time point, and the terminal device reports Top 1 (%) at t1 time point, Top 1 (%) at t2 time point and Top 1 (%) at t3 time point, for example, as shown in Table 5.

[0327] Table 5

[0328] For example, the first performance indicator is the difference of Top 1 L1-RSRP, the plurality of prediction moments include t1 moment, t2 moment and t3 moment, and the terminal device reports the difference of Top 1 L1-RSRP at t1 moment, the difference of Top 1 L1-RSRP at t2 moment and the difference of Top 1 L1-RSRP at t3 moment, as shown in Table 6.

[0329] Table 6

[0330] After the network device receives the plurality of monitoring results, the network device identifies the problems of the terminal-side model or function according to the plurality of monitoring results, and further generates a monitoring decision. The monitoring decision is, for example, modifying the number of prediction moments, model or function fallback, model or function switching, etc.

[0331] For example, the value of Top 1 (%) at t3 moment is small, and the network device can modify the number of prediction moments, for example, from 3 prediction moments to 2 prediction moments.

[0332] It should be noted that the above describes the terminal device reporting a plurality of monitoring results of the first performance indicator at a plurality of prediction moments. For a plurality of performance indicators, the terminal device can report a plurality of monitoring results of the plurality of performance indicators at a plurality of prediction moments, and the network device generates a monitoring decision according to the plurality of monitoring results of the plurality of performance indicators at a plurality of prediction moments.

[0333] For example, more than a certain number of performance indicators in the plurality of performance indicators have an undesirable value at t3 moment, and the network device can modify the number of prediction moments, for example, from 3 prediction moments to 2 prediction moments. In this way, the terminal device subsequently monitors the performance indicators at two future moments.

[0334] Optionally, the undesirable value of the performance indicator at t3 moment can include that the value of the performance indicator at t3 moment does not meet the threshold value corresponding to t3 moment, and the threshold value is stored internally by the network device. In combination with the method 500 or the method 700 described above, the network device determines the monitoring results of the performance indicators at different moments, and if the value of the performance indicator at one prediction moment does not meet the threshold value, the monitoring result of the performance indicator at the prediction moment includes a trigger event.

[0335] In the method 800, the terminal device independently monitors different prediction moments, and reports the monitoring results of the performance indicators at different prediction moments to the network device. Further, the network device can more accurately monitor the performance of the terminal-side model or function based on the monitoring results of the performance indicators at different prediction moments, and generate a more accurate monitoring decision.

[0336] In a possible implementation, the terminal device monitors the first performance indicator at each of the plurality of predicted time instants based on protocol predefinition or protocol specification, and reports the value of the first performance indicator at each of the plurality of predicted time instants. If the protocol does not specify independent monitoring of the performance indicators at different predicted time instants, the terminal device can monitor the first performance indicator in a period according to an existing scheme, to obtain a monitoring result of the first performance indicator in the period, or monitor the first performance indicator at a sample, to obtain a monitoring result of the first performance indicator at the sample.

[0337] In another possible implementation, the method 800 further includes that the network device sends seventh indication information to the terminal device, in S804. Accordingly, the terminal device receives the seventh indication information. The seventh indication information is used to indicate that the performance of the first performance indicator at each of the plurality of predicted time instants is monitored. After receiving the seventh indication information, the terminal device determines that the network device indicates that independent monitoring is required for different predicted time instants, and thus determines the monitoring result of the first performance indicator at each of the plurality of predicted time instants according to the fifth indication information and the seventh indication information, and reports the value of the first performance indicator at each of the plurality of predicted time instants.

[0338] For example, the length of the seventh indication information is 1 bit, and the network device can indicate the performance monitoring of the first performance indicator at each of the plurality of predicted time instants by 1 bit. For example, "0" indicates that the performance monitoring of the first performance indicator at each of the plurality of predicted time instants is performed, and "1" indicates that the performance monitoring of the first performance indicator at each of the plurality of predicted time instants is not required. Alternatively, "1" indicates that the performance monitoring of the first performance indicator at each of the plurality of predicted time instants is performed, and "0" indicates that the performance monitoring of the first performance indicator at each of the plurality of predicted time instants is not required.

[0339] In summary, for the performance monitoring scenario, the terminal device can perform independent monitoring for different predicted time instants, and the terminal device can indicate the value of different performance indicators at different predicted time instants to the network device, or indicate the monitoring result of different performance indicators at different predicted time instants to the network device, thereby facilitating the network device to generate more accurate monitoring decisions.

[0340] In addition to being applied to the above performance monitoring scenario, the technical solution of the present application can also be applied to a model inference scenario. In the model inference scenario, for a terminal-side model / function / measurement task / reporting task, the network device can generally send predicted resources to the terminal device, and the terminal device can perform model inference or execute terminal-side functions / measurement tasks / reporting tasks based on the predicted resources to obtain predicted information at a plurality of predicted time instants.

[0341] A communication method for a terminal device to report prediction information will be provided below, see the description below for FIG. 9.

[0342] FIG. 9 is a schematic flowchart of another communication method 900 provided by an embodiment of the application. The steps of method 900 can be performed by interaction between a terminal side and a network side, where the terminal side is, for example, a terminal device or a communication module in the terminal device, or a circuit or chip responsible for communication functions in the terminal device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and the following description takes the terminal device as an example. The network side is, for example, a network device or a communication module in the network device, or a circuit or chip responsible for communication functions in the network device (such as a Modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), and the following description takes the network device as an example.

[0343] Method 900 includes S901 and S902, which are described in detail below.

[0344] S901, the network device sends eighth indication information to the terminal device, the eighth indication information being used to indicate a plurality of thresholds, the plurality of thresholds being used to monitor the accuracy of the first prediction information, the plurality of thresholds corresponding to different prediction moments, and each threshold in the plurality of thresholds corresponding to at least one prediction moment. Correspondingly, the terminal device receives the eighth indication information.

[0345] Wherein, the prediction moment is a future moment, for the terminal side model or function, the terminal device can predict information of the future moment based on the measurement resource, the predicted information of the future moment being referred to as prediction information, or prediction result, which is not limited by the present application.

[0346] The prediction moment can be replaced by a prediction period. The plurality of thresholds correspond to different prediction moments, where different can mean not exactly the same, that is, there is a partial intersection, for example, two prediction periods have an intersection. Or, different can mean completely different, that is, there is no intersection, for example, two prediction periods have no intersection.

[0347] Exemplarily, the accuracy of the first prediction information can be embodied by the value of the monitoring parameter of the first prediction information, which can be generated together with the generation of the first prediction information by the terminal side model or function, or the terminal device generates the monitoring parameter of the first prediction information based on other models or functions after generating the first prediction information.

[0348] The prediction information or the performance index corresponding prediction information can be: beam prediction (including Top K beam prediction and RSRP thereof), RSRP prediction, CSI prediction, radio link failure (RLF) prediction, or hand over failure (HOF) prediction.

[0349] The RSRP prediction can be RSRP prediction of each / specified beam / synchronization signal block (SSB).

[0350] The CSI prediction can be CSI prediction of each / specified beam / SSB, and can be one or a combination of the following: index of beam / SSB, RI, PMI, CRI, LI, CQI, and L1-RSRP.

[0351] The RLF prediction can be the number / probability of radio link failures of the terminal device in a specified time period / specified area.

[0352] The HOF prediction can be the number / probability of handover failures of the terminal device in a specified time period / specified area.

[0353] For the monitoring scenario, the corresponding monitoring index can be: accuracy of beam prediction, accuracy of RSRP prediction, accuracy of CSI prediction, accuracy of RLF prediction, and accuracy of HOF prediction.

[0354] The accuracy or precision of the above beam prediction can be: probability that the actually measured optimal beam is the predicted optimal beam (Top 1 (%)), probability that the actually measured optimal beam is one of the predicted top K optimal beams (Top K / 1 (%)), and probability that the predicted optimal beam is one of the actually measured top K optimal beams (Top 1 / K (%)).

[0355] The accuracy of the RSRP can be: a difference between a measured RSRP of a kth best beam and a predicted RSRP of the kth best beam (referred to as a difference of Top K L1-RSRP), a difference between a predicted RSRP of a kth best beam and a measured RSRP of the kth best beam (referred to as a difference of predicted Top K L1-RSRP), a difference between an average of measured RSRPs of the first K best beams and an average of predicted RSRPs of the first K best beams (referred to as a difference of an average of Top K L1-RSRP), or a difference between an average of predicted RSRPs of the first K best beams and an average of measured RSRPs of the first K best beams (referred to as a difference of an average of predicted Top K L1-RSRP). The difference can refer to a difference value, an absolute value of the difference value, or an accuracy, etc.

[0356] For the inference scenario, the corresponding monitoring parameters can be: a prediction probability / prediction accuracy / prediction accuracy of the different prediction information, a predicted RSRP value, a predicted CSI value (which can be specific to each sub-information prediction value), a number / probability of RLF prediction occurrence, a number / probability of HOF prediction occurrence. The sub-information can be one or more of: RI, PMI, CRI, LI, CQI, L1-RSRP.

[0357] If the value of the monitoring parameter of the first prediction information of the terminal device at a prediction time satisfies the threshold corresponding to the prediction time, it means that the accuracy of the first prediction information at the prediction time satisfies the threshold corresponding to the prediction time.

[0358] The multiple thresholds of this step are described in detail below.

[0359] Taking any one of the at least one prediction information (denoted as first prediction information) as an example, in order for the terminal device to more accurately monitor the first prediction information at different times, the network device can indicate multiple thresholds of the first prediction information through the eighth indication information, and the multiple thresholds are used to monitor the accuracy of the first prediction information. The multiple thresholds correspond to different prediction times, and each threshold corresponds to at least one prediction time. The threshold corresponding to different prediction times can be used to determine whether the first prediction information at the prediction time satisfies the reporting condition.

[0360] In one example, the multiple thresholds include threshold 1, threshold 2, and threshold 3, wherein threshold 1 corresponds to time t1, threshold 2 corresponds to time t2, and threshold 3 corresponds to time t3.

[0361] In another example, the plurality of thresholds comprises threshold 1 and threshold 2, wherein threshold 1 corresponds to time t1, and threshold 2 corresponds to time t2 and time t3.

[0362] In another example, the plurality of thresholds comprises threshold 1 and threshold 2, wherein threshold 1 corresponds to time t1 and time t2, and threshold 2 corresponds to time t3.

[0363] The network device can indicate the plurality of thresholds in various ways. For details, refer to the ways of indicating the plurality of thresholds described above with respect to S501, which will not be described herein again. For example, the threshold corresponding to each prediction time is directly indicated, or the threshold corresponding to time t1 is indicated, and the same threshold corresponding to other prediction times is indicated, or the threshold corresponding to time t1 is indicated, and the offset of the threshold corresponding to other prediction times relative to the threshold corresponding to time t2 is indicated.

[0364] After the terminal device receives the plurality of thresholds corresponding to the first prediction information, the terminal device determines whether the accuracy of the first prediction information at each prediction time meets the threshold corresponding to the prediction time. If the accuracy of the first prediction information at a prediction time meets the threshold corresponding to the prediction time, the terminal device can report the first prediction information at the prediction time, otherwise, the terminal device can not report the first prediction information at the prediction time.

[0365] S902, the terminal device sends ninth indication information to the network device, and the ninth indication information is used to indicate the first prediction information at the target prediction time in the at least one prediction time. Correspondingly, the network device receives the ninth indication information.

[0366] The accuracy of the first prediction information at the target prediction time meets the threshold of the first prediction information at the target prediction time. That is, if the accuracy of the first prediction information at a prediction time meets the threshold corresponding to the prediction time, the prediction time is the target prediction time, and the terminal device reports the first prediction information at the prediction time to the network device.

[0367] It should be understood that the accuracy of the first prediction information at a prediction time meeting the threshold corresponding to the prediction time can include that the accuracy of the first prediction information at the prediction time is greater than or equal to the threshold corresponding to the prediction time.

[0368] The following describes a monitoring parameter as an example of prediction accuracy.

[0369] The first prediction information is Top K beam prediction, the monitoring parameter is prediction accuracy, the multiple thresholds include threshold 1 and threshold 2, threshold 1 is 98%, threshold 2 is 95%, threshold 1 corresponds to time t1, and threshold 2 corresponds to time t2. That is, threshold 1 is used to monitor the prediction accuracy of the kth best beam in the Top K beam prediction at time t1, and threshold 2 is used to monitor the prediction accuracy of the kth best beam in the Top K beam prediction at time t2, where k=1,2,…,K.

[0370] If the prediction accuracy of the kth best beam in the Top K beam prediction at time t1 is 99%, and the prediction accuracy of the kth best beam in the Top K beam prediction at time t2 is 93%, since the prediction accuracy of the kth best beam in the Top K beam prediction at time t1 is 99%, which is greater than the threshold 1 corresponding to time t1, and the prediction accuracy of the kth best beam in the Top K beam prediction at time t2 is 93%, which is less than the threshold 2 corresponding to time t2, therefore, the prediction accuracy of the kth best beam in the Top K beam prediction at time t1 satisfies the threshold 1 corresponding to time t1, and the prediction accuracy of the kth best beam in the Top K beam prediction at time t2 does not satisfy the threshold 2 corresponding to time t2. Further, the terminal device can report the kth best beam at time t1 as one of the Top K beams at time t1 to the network device, and when reporting the Top K beams at time t2, the terminal device can not report the kth best beam, that is, the Top K beams reported do not include the kth best beam. Wherein k=1,2,…,K.

[0371] For example, K=5 in the above Top K, if the prediction accuracy of all beams in the Top 5 beams at time t1 is greater than the threshold corresponding to time t1, the terminal device can report all beams in the Top 5 beams to the network device, that is, the reported Top 5 beams at time t1 include the 1st best beam, the 2nd best beam, the 3rd best beam, the 4th best beam and the 5th best beam. If the prediction accuracy of the 5th best beam in the Top 5 beams at time t2 is less than the threshold corresponding to time t2, the terminal device can report the beams in the Top 5 beams except the 5th best beam to the network device, that is, the reported Top 5 beams at time t2 include the 1st best beam, the 2nd best beam, the 3rd best beam and the 4th best beam.

[0372] The following takes the monitoring parameter as the predicted RSRP value (also referred to as the predicted value of RSRP) as an example for description.

[0373] Suppose the first prediction information is Top K beam prediction, the monitoring parameter is the predicted RSRP value, and the multiple thresholds include threshold 1 and threshold 2, where threshold 1 is 10 dB and threshold 2 is 8 dB, threshold 1 corresponds to time t, and threshold 2 corresponds to time t2. That is, threshold 1 is used to monitor the predicted RSRP value of the kth beam in the Top K beam prediction at time t1, and threshold 2 is used to monitor the predicted RSRP value of the kth beam in the Top K beam prediction at time t2, where k = 1, 2, …, K.

[0374] If the predicted RSRP value of the kth best beam in the Top K beam prediction at time t1 is 12 dB, and the predicted RSRP value of the kth best beam in the Top K beam prediction at time t2 is 7 dB, since the predicted RSRP value of the kth best beam in the Top K beam prediction at time t1 is greater than the threshold corresponding to time t1, and the predicted RSRP value of the kth best beam in the Top K beam prediction at time t2 is less than the threshold corresponding to time t2, the predicted RSRP value of the kth best beam in the Top K beam prediction at time t1 satisfies the threshold corresponding to time t1, and the predicted RSRP value of the kth best beam in the Top K beam prediction at time t2 does not satisfy the threshold corresponding to time t2. Furthermore, the terminal device can report the kth best beam at time t1 as one of the Top K beams at time t1 to the network device, and when reporting the Top K beams at time t2, the terminal device can not report the kth best beam, that is, the reported Top K beams do not include the kth best beam. Where k = 1, 2, …, K.

[0375] For example, K = 5 in the above Top K, if the predicted RSRP values of all beams in the Top 5 beams at time t1 are greater than the threshold corresponding to time t1, the terminal device can report all beams in the Top 5 beams to the network device, that is, the reported Top 5 beams at time t1 include the first best beam, the second best beam, the third best beam, the fourth best beam, and the fifth best beam. If the predicted RSRP value of the fifth best beam in the Top 5 beams at time t2 is less than the threshold corresponding to time t2, the terminal device can report the beams in the Top 5 beams at time t2 to the network device, that is, the reported Top 5 beams at time t2 include the first best beam, the second best beam, the third best beam, and the fourth best beam.

[0376] In the method 900, the network device sets a threshold for monitoring the first prediction information for each prediction moment independently, the terminal device can monitor the first prediction information at each prediction moment based on the threshold corresponding to the prediction moment, and then the terminal device determines whether to report the first prediction information at the prediction moment, so that the first prediction information can be monitored more finely, and the network device can be provided with more accurate and more effective prediction information.

[0377] In the embodiment described above with reference to FIG. 9, the network device indicates a plurality of thresholds, and the plurality of thresholds correspond to different prediction moments. In another embodiment, the network device indicates at least one threshold, and the at least one threshold corresponds to at least one prediction information. Different thresholds correspond to the same prediction moment, which will be described below with reference to FIG. 10.

[0378] FIG. 10 is a schematic flowchart of another communication method 1000 according to an embodiment of the present application. The steps of the method 1000 can be executed by the terminal side and the network side, for example, a terminal device or a communication module in the terminal device, or a circuit or a chip responsible for communication functions in the terminal device (such as a Modem chip, also known as a baseband chip, or a SoC chip or a SIP chip containing a modem core), which will be described below with reference to a terminal device. The network side, for example, a network device or a communication module in the network device, or a circuit or a chip responsible for communication functions in the network device (such as a Modem chip, also known as a baseband chip, or a SoC chip or a SIP chip containing a modem core), which will be described below with reference to a network device.

[0379] The method 1000 includes S1001 and S1002, which will be described in detail below.

[0380] S1001, the network device sends tenth indication information to the terminal device, and the tenth indication information is used to indicate at least one threshold, the at least one threshold corresponds to at least one prediction information, and each threshold in the at least one threshold is used to monitor the accuracy of the corresponding prediction information.

[0381] The at least one threshold and the at least one prediction information are in a one-to-one correspondence, that is, one threshold corresponds to one prediction information, or each prediction information has a corresponding threshold. Each threshold in the at least one threshold corresponds to a plurality of prediction moments, and different thresholds correspond to the same prediction moment.

[0382] For example, the at least one threshold value includes threshold value 1 and threshold value 2, the threshold value 1 corresponds to the prediction information 1, and the threshold value 2 corresponds to the prediction information 2. The threshold value 1 corresponds to the time t1, the time t2, and the time t3, and the threshold value 2 corresponds to the time t1, the time t2, and the time t3. The prediction time corresponding to the threshold value 1 and the threshold value 2 is the same.

[0383] It should be understood that the threshold value 1 corresponds to the time t1, the time t2, and the time t3. It can be understood that the threshold value 1 is used to monitor the accuracy of the prediction information 1 at the time t1, the time t2, and the time t3. The threshold value 2 corresponds to the time t1, the time t2, and the time t3. It can be understood that the threshold value 2 is used to monitor the accuracy of the prediction information 2 at the time t1, the time t2, and the time t3.

[0384] The introduction of the prediction information can refer to the description in the above, which will not be described here.

[0385] The network device can indicate the at least one threshold value in various ways. The specific implementation method can refer to the way of indicating multiple threshold values described above for S701. For example, the correspondence between the threshold value and the prediction information can be embodied in the form of a table, which will not be described here.

[0386] S1002, the terminal device sends the eleventh indication information to the network device, and the eleventh indication information is used to indicate the target prediction information at the target prediction time.

[0387] The accuracy of the target prediction information at the target prediction time satisfies the threshold value corresponding to the target prediction information. For example, the accuracy of the first prediction information at the first prediction time in the plurality of prediction times satisfies the first threshold value corresponding to the first prediction information. The first prediction time is a target prediction time, the first prediction information is a target prediction information, and the terminal device reports the first prediction information at the first prediction time to the network device.

[0388] It should be understood that the accuracy of the first prediction information at the first prediction time satisfies the threshold value corresponding to the first prediction information, which can include that the accuracy of the first prediction information at the first prediction time is greater than or equal to the threshold value corresponding to the first prediction information.

[0389] The following describes an example in which the monitoring parameter is the prediction accuracy, and the plurality of prediction times include the time t1, the time t2, and the time t3.

[0390] Suppose threshold 1 is 95%, the corresponding prediction information is Top K beam prediction, and the monitoring parameter is prediction accuracy, that is, threshold 1 is used to monitor the prediction accuracy of the kth best beam in Top K beam prediction, k = 1, 2, …, K. The prediction accuracy of the kth best beam in Top K beam prediction at t1 is 98%, the prediction accuracy of the kth best beam in Top K beam prediction at t2 is 97%, and the prediction accuracy of the kth best beam in Top K beam prediction at t3 is 94%.

[0391] Since the prediction accuracy of the kth best beam in Top K beam prediction at t1 is greater than threshold 1, the prediction accuracy of the kth best beam in Top K beam prediction at t2 is greater than threshold 1, and the prediction accuracy of the kth best beam in Top K beam prediction at t3 is less than threshold 1, the prediction accuracy of the kth best beam in Top K beam prediction at t1 meets threshold 1, the prediction accuracy of the kth best beam in Top K beam prediction at t2 meets threshold 1, and the prediction accuracy of the kth best beam in Top K beam prediction at t3 does not meet threshold 1. Further, the terminal device can report the kth best beam at t1 to the network device as one of Top K beams at t1, and report the kth best beam at t2 to the network device as one of Top K beams at t1. When reporting Top K beams at t3, the terminal device can not report the kth best beam, that is, the kth best beam is not included in the reported Top K beams. Wherein, k = 1, 2, …, K.

[0392] For example, K = 5 in the above Top K, if the prediction accuracy of all beams in Top 5 beams at t1 is greater than the threshold corresponding to t1, the terminal device can report all beams in Top 5 beams to the network device, that is, the reported Top 5 beams at t1 include the 1st best beam, the 2nd best beam, the 3rd best beam, the 4th best beam and the 5th best beam. If the prediction accuracy of all beams in Top 5 beams at t2 is greater than the threshold corresponding to t2, the terminal device can report all beams in Top 5 beams to the network device, that is, the reported Top 5 beams at t2 include the 1st best beam, the 2nd best beam, the 3rd best beam, the 4th best beam and the 5th best beam. If the prediction accuracy of the 5th best beam in Top 5 beams at t3 is less than the threshold corresponding to t3, the terminal device can report the beams in Top 5 beams except the 5th best beam to the network device, that is, the reported Top 5 beams at t3 include the 1st best beam, the 2nd best beam, the 3rd best beam and the 4th best beam. Wherein, t1, t2 and t3 correspond to the same threshold, which is the threshold corresponding to Top K beam prediction.

[0393] The following describes an example in which the monitoring parameter is a predicted RSRP value, the multiple prediction moments include a t1 moment, a t2 moment, and a t3 moment.

[0394] Suppose that the threshold 1 is 10 dB, the corresponding prediction information is Top K beam prediction, and the monitoring parameter is a predicted RSRP value, that is, the threshold 1 is used to monitor a predicted RSRP value of a kth best beam in Top K beam prediction. The predicted RSRP value of the kth best beam in Top K beam prediction at the t1 moment is 12 dB, the predicted RSRP value of the kth best beam in Top K beam prediction at the t2 moment is 11 dB, and the predicted RSRP value of the kth best beam in Top K beam prediction at the t3 moment is 8 dB.

[0395] Since the predicted RSRP value of the kth best beam in Top K beam prediction at the t1 moment is greater than the threshold 1, the predicted RSRP value of the kth best beam in Top K beam prediction at the t2 moment is greater than the threshold 1, and the predicted RSRP value of the kth best beam in Top K beam prediction at the t3 moment is greater than the threshold 1 corresponding to the t3 moment, the predicted RSRP value of the kth best beam in Top K beam prediction at the t1 moment satisfies the threshold 1, the predicted RSRP value of the kth best beam in Top K beam prediction at the t2 moment satisfies the threshold 1, and the predicted RSRP value of the kth best beam in Top K beam prediction at the t3 moment does not satisfy the threshold 1. Further, the terminal device can report the kth best beam at the t1 moment to the network device as one of Top K beams at the t1 moment, and report the kth best beam at the t2 moment to the network device as one of Top K beams at the t1 moment. When reporting Top K beams at the t3 moment, the terminal device can not report the kth best beam, that is, the kth best beam is not included in the reported Top K beams. Wherein, k = 1, 2, …, K.

[0396] For example, K=5 in the above Top K, if the predicted RSRP values of all beams in the Top 5 beams at t1 are greater than the threshold corresponding to t1, the terminal device can report all beams in the Top 5 beams to the network device, that is, the reported Top 5 beams at t1 include the 1st optimal beam, the 2nd optimal beam, the 3rd optimal beam, the 4th optimal beam, and the 5th optimal beam. If the predicted RSRP values of all beams in the Top 5 beams at t2 are greater than or equal to the threshold corresponding to t1, the terminal device can report all beams in the Top 5 beams to the network device, that is, the reported Top 5 beams at t2 include the 1st optimal beam, the 2nd optimal beam, the 3rd optimal beam, the 4th optimal beam, and the 5th optimal beam. If the predicted RSRP value of the 5th optimal beam in the Top 5 beams at t3 is less than the threshold corresponding to t3, the terminal device can report other beams except the 5th optimal beam to the network device, that is, the reported Top 5 beams at t3 include the 1st optimal beam, the 2nd optimal beam, the 3rd optimal beam, and the 4th optimal beam. The t1, t2, and t3 correspond to the same threshold, which is the threshold corresponding to the Top K beam prediction.

[0397] In the above method 1000, one threshold corresponds to one prediction information, and the threshold corresponding to the prediction information is used to monitor the accuracy of the prediction information at multiple prediction times. The terminal device can report the prediction information whose accuracy meets the threshold to the network device, which is beneficial to more finely monitor and report the accuracy of the prediction information at different prediction times, and is beneficial to save signaling overhead.

[0398] It should be understood that the scheme of the embodiments of the present application is not limited to the prediction information related to the beam management use case, but can also be extended to other scenarios or use cases for AI time domain prediction, for example, CSI time domain prediction, future (measurement) information prediction for mobility. Among them, the future (measurement) information prediction for mobility is, for example, time domain RSRP prediction, RLF prediction, HOF prediction.

[0399] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for differentiation for convenience of description, and do not limit the scope of the embodiments of the present application. The size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic.

[0400] The method provided in the embodiments of the present application is introduced by taking the terminal device and the network device as an example. In the present application, each embodiment can be implemented independently or in combination based on certain internal relationship. In each embodiment, different implementation manners can be implemented in combination or independently. In order to implement the functions in the method provided in the embodiments of the present application, the steps performed by the terminal device can be implemented by the terminal device itself, or by different functional entities constituting the terminal device. The steps performed by the network device can be implemented by the network device itself, or by different functional entities constituting the network device. For example, the network device is an access network device, which can be a CU-DU architecture. The CU can generate the indication information, and the DU can send the indication information. In order to implement the functions in the method provided in the embodiments of the present application, the terminal device and the network device can include hardware structures and / or software modules, and the above functions are implemented in the form of hardware structure, software module, or hardware structure plus software module. Whether a certain function in the above functions is implemented in the form of hardware structure, software module, or hardware structure plus software module depends on the specific application and design constraints of the technical solution.

[0401] The communication method according to the embodiments of the present application is described in detail above in combination with FIG. 5, FIG. 7, and FIG. 8. The communication apparatus according to the embodiments of the present application will be described in detail below in combination with FIG. 11 and FIG. 12.

[0402] FIG. 11 and FIG. 12 are schematic block diagrams of the communication apparatus provided in the embodiments of the present application. These communication apparatuses can be used to implement the functions of the terminal device or the network device in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments.

[0403] As shown in FIG. 11, the communication apparatus 1100 includes a processing module 1120. Optionally, the communication apparatus 1100 further includes a transceiver module 1110. The transceiver module 1110 can also be referred to as a communication interface or a communication module.

[0404] The apparatus 1100 can be used to perform the actions performed by the terminal device or the network device in the above method embodiments. Alternatively, the apparatus 1100 is a component (for example, a chip) configured in the terminal device or the network device. The processing module 1120 is used to perform processing-related operations of the terminal device or the network device in the above method embodiments. The transceiver module 1110 is used to perform receiving and sending-related operations of the terminal device or the network device in the above method embodiments.

[0405] Optionally, the transceiver module 1110 can include a sending module and a receiving module. The sending module is used to perform the sending operations in the above method embodiments. The receiving module is used to perform the receiving operations in the above method embodiments.

[0406] It should be noted that the apparatus 1100 can include a sending module but not a receiving module. Alternatively, the apparatus 1100 can include a receiving module but not a sending module. Whether the apparatus 1100 includes a sending module or a receiving module can depend on whether the apparatus 1100 performs the sending action and the receiving action in the above-described solutions.

[0407] Optionally, the apparatus 1100 is configured to perform the actions performed by the terminal device or the network device in the above-described embodiments shown in FIG. 5, FIG. 7, and FIG. 8. For details, refer to the related description in the above-described embodiments shown in FIG. 7 or FIG. 11, which will not be repeated here.

[0408] Optionally, the apparatus 1100 can further include a storage module, which can be configured to store data, and / or store a computer program or instructions, and the processing module 1120 can read the computer program / instructions and / or data in the storage module, so that the apparatus 1100 implements the above-described method embodiments.

[0409] In one embodiment, when the apparatus 1100 is configured to implement the functions of the terminal device in the method embodiment shown in FIG. 5, the transceiver module 1110 is configured to: receive first indication information, the first indication information being used to indicate a plurality of threshold values, the plurality of threshold values corresponding to a first index, the plurality of threshold values corresponding to different prediction moments, each threshold value in the plurality of threshold values corresponding to at least one prediction moment, the first index corresponding to a performance of a model or a function. The processing module 1120 is configured to: determine a measurement result corresponding to each threshold value in the at least one threshold value, the measurement result corresponding to each threshold value being a measurement result of the first index at the at least one prediction moment corresponding to each threshold value, the plurality of threshold values including the at least one threshold value; and generate a first monitoring result according to the measurement result corresponding to each threshold value in the at least one threshold value. The transceiver module 1110 is further configured to: send second indication information, the second indication information being used to indicate the first measurement result.

[0410] Optionally, the at least one threshold value includes a first threshold value, the measurement result of the first threshold value including a trigger event or a non-trigger event; if values of the first index at all prediction moments corresponding to the first threshold value satisfy the first threshold value, the measurement result corresponding to the first threshold value includes the non-trigger event; if the value of the first index at any prediction moment corresponding to the first threshold value does not satisfy the first threshold value, the measurement result corresponding to the first threshold value includes the trigger event.

[0411] Optionally, the second indication information comprises any one of the following: a plurality of bit positions corresponding to the plurality of thresholds one by one; or, the first prediction moment; or, a value of the first indicator at the second prediction moment. Wherein, a measurement result of the first indicator at the first prediction moment and a prediction moment after the first prediction moment comprises the trigger event, or a measurement result of the first indicator at a prediction moment before the first prediction moment and the second prediction moment comprises the non-trigger event. The measurement result of the first indicator at the second prediction moment comprises the trigger event.

[0412] Optionally, the at least one threshold comprises a first threshold, the first threshold corresponds to a plurality of prediction moments, and a measurement result of the first threshold comprises the trigger event and / or the non-trigger event; if a value of the first indicator at any prediction moment corresponding to the first threshold satisfies the first threshold, the measurement result of the any prediction moment comprises the non-trigger event; if the value of the first indicator at the any prediction moment corresponding to the first threshold does not satisfy the first threshold, the measurement result of the any prediction moment comprises the trigger event.

[0413] Optionally, the second indication information comprises any one of the following: a plurality of bit positions; or, the first prediction moment; or, a value of the first indicator at the second prediction moment. Wherein, the plurality of bit positions correspond to a plurality of prediction moments one by one, and the plurality of prediction moments correspond to the plurality of thresholds. A measurement result of the first indicator at the first prediction moment and a prediction moment after the first prediction moment comprises the trigger event, or a measurement result of the first indicator at a prediction moment before the first prediction moment and the second prediction moment comprises the non-trigger event. The measurement result of the first indicator at the second prediction moment comprises the trigger event.

[0414] Optionally, the first indicator is any one of the following: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of a predicted top K optimal beams, a probability that a predicted optimal beam is one of a measured top K optimal beams, a difference between a measured reference signal received power (RSRP) of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of a measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of a predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0415] In another embodiment, when the apparatus 1100 is configured to implement the function of a terminal device in the method embodiment as shown in FIG. 7, the transceiver module 1110 is configured to: receive third indication information, the third indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one index corresponding to performance of a model or a function. The processing module 1120 is configured to: determine a measurement result of the index corresponding to each threshold in the at least one threshold at each prediction time in a plurality of prediction times. The transceiver module 1110 is further configured to: send fourth indication information, the fourth indication information being used to indicate the measurement result. The measurement result includes a triggering event or a non-triggering event.

[0416] Optionally, the at least one threshold includes a second threshold, the second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all prediction times satisfies the second threshold, the measurement result of the second index corresponding to the second threshold includes a non-triggering event; if the value of the second index corresponding to the second threshold at any prediction time in the plurality of prediction times does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold includes a triggering event.

[0417] Optionally, the fourth indication information includes any one of: at least one bit; or, at least one third prediction time; or, a value or an identifier of a target index at at least one fourth prediction time. The at least one bit corresponds to the at least one threshold one by one, the measurement result of each index in the at least one index at the third prediction time includes a triggering event. The measurement result of a target index in the at least one index at the fourth prediction time includes a triggering event, and the measurement result of an index other than the target index in the at least one index at the fourth prediction time includes a non-triggering event.

[0418] Optionally, the at least one threshold includes a second threshold, the second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all prediction times satisfies the second threshold, the measurement result of the second index corresponding to the second threshold includes a non-triggering event; if the value of the second index corresponding to the second threshold at any prediction time in the plurality of prediction times does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold includes a triggering event.

[0419] Optionally, the fourth indication information comprises any one of: at least one group of bits; at least one third prediction time; or, a value or an identity of a target indicator at the at least one fourth prediction time. The at least one group of bits corresponds to the at least one threshold value one by one, each group of bits in the at least one group of bits comprises a plurality of bits, and the plurality of bits correspond to the plurality of prediction times one by one. The measurement result of each indicator in the at least one indicator at the third prediction time comprises a trigger event, the measurement result of the target indicator in the at least one indicator at the fourth prediction time comprises a trigger event, and the measurement result of an indicator other than the target indicator in the at least one indicator at the fourth prediction time comprises a non-trigger event.

[0420] Optionally, the at least one indicator comprises one or more of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of the predicted top K optimal beams, a probability that a predicted optimal beam is one of the measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0421] In another embodiment, when the apparatus 1100 is configured to implement the functions of a terminal device in the method embodiment as shown in FIG. 8, the transceiver module 1110 is configured to: receive fifth indication information. The processing module 1120 is configured to: determine, according to the fifth indication information, a plurality of measurement results, the plurality of measurement results comprising a measurement result of a first indicator at each prediction time in a plurality of prediction times. The transceiver module 1110 is further configured to: send sixth indication information, the sixth indication information being used to indicate the plurality of measurement results. The fifth indication information is used to indicate reporting of the measurement result of the first indicator.

[0422] Optionally, the transceiver module 1110 is configured to: receive seventh indication information, the seventh indication information being used to indicate performance monitoring on the first indicator at each prediction time in the plurality of prediction times.

[0423] Optionally, the first index is any one of: a probability that the measured optimal beam is the predicted optimal beam, a probability that the measured optimal beam is one of the predicted top K optimal beams, a probability that the predicted optimal beam is one of the measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0424] In another embodiment, when the apparatus 1100 is configured to implement the function of the network device in the method embodiment as shown in FIG. 5, the transceiver module 1110 is configured to: send first indication information, the first indication information being used to indicate a plurality of thresholds, the plurality of thresholds corresponding to a first index, the plurality of thresholds corresponding to different predicted time instants, each threshold in the plurality of thresholds corresponding to at least one predicted time instant, the first index corresponding to a performance of a model or a function; and receive second indication information, the second indication information being used to indicate a first measurement result, the first measurement result including a measurement result corresponding to each threshold in the plurality of thresholds, the measurement result corresponding to each threshold being a measurement result of the first index at the at least one predicted time instant corresponding to each threshold.

[0425] Optionally, the at least one threshold includes a first threshold, a measurement result corresponding to the first threshold including a trigger event or a non-trigger event; if values of the first index at all predicted time instants corresponding to the first threshold satisfy the first threshold, the measurement result corresponding to the first threshold including the non-trigger event; if values of the first index at any predicted time instant corresponding to the first threshold do not satisfy the first threshold, the measurement result corresponding to the first threshold including the trigger event.

[0426] Optionally, the second indication information includes any one of: a plurality of bit positions, the plurality of bit positions one-to-one corresponding to the plurality of thresholds; or, a value of the first index at a first predicted time instant; or, a value of the first index at a second predicted time instant. Wherein the measurement result of the first index at the first predicted time instant and after the first predicted time instant includes the trigger event, or the measurement result of the first index at the first predicted time instant and before the first predicted time instant includes the non-trigger event. The measurement result of the first index at the second predicted time instant includes the trigger event.

[0427] Optionally, the at least one threshold comprises a first threshold, the first threshold corresponds to a plurality of prediction time points, and a measurement result of the first threshold comprises a triggering event and / or a non-triggering event; if a value of the first index at any prediction time point corresponding to the first threshold satisfies the first threshold, the measurement result of the any prediction time point comprises a non-triggering event; if the value of the first index at the any prediction time point corresponding to the first threshold does not satisfy the first threshold, the measurement result of the any prediction time point comprises a triggering event.

[0428] Optionally, the second indication information comprises any one of: a plurality of bit positions; or, a first prediction time point; or, a value of the first index at a second prediction time point. The plurality of bit positions correspond to the plurality of prediction time points one by one, and the plurality of prediction time points correspond to the plurality of thresholds. The measurement result of the first index at the first prediction time point and the prediction time points after the first prediction time point comprises a triggering event, or the measurement result of the first index at the second prediction time point and the prediction time points before the second prediction time point comprises a non-triggering event. The measurement result of the first index at the second prediction time point comprises a triggering event.

[0429] Optionally, the first index is any one of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of the predicted top K optimal beams, a probability that a predicted optimal beam is one of the measured top K optimal beams, a difference between a measured reference signal received power (RSRP) of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0430] In another embodiment, when the apparatus 1100 is configured to implement the functions of the network device in the method embodiment as shown in FIG. 7: the transceiver module 1110 is configured to: send third indication information, the third indication information being used to indicate at least one threshold, the at least one threshold corresponding to at least one index, the index corresponding to a performance of a model or a function; and receive fourth indication information, the fourth indication information being used to indicate the measurement result. The measurement result comprises a triggering event or a non-triggering event.

[0431] Optionally, the at least one threshold comprises a second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all predicted time instants satisfies the second threshold, a measurement result of the second index corresponding to the second threshold comprises a non-triggering event; if the value of the second index corresponding to the second threshold at any predicted time instant of the plurality of predicted time instants does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold comprises a triggering event.

[0432] Optionally, the fourth indication information comprises any one of: at least one bit; or, at least one third predicted time instant; or, a value or an identifier of a target index at at least one fourth predicted time instant. The at least one bit corresponds to the at least one threshold one by one, and a measurement result of each index of the at least one index at the third predicted time instant comprises a triggering event. A measurement result of a target index of the at least one index at the fourth predicted time instant comprises a triggering event, and a measurement result of an index other than the target index of the at least one index at the fourth predicted time instant comprises a non-triggering event.

[0433] Optionally, the at least one threshold comprises a second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all predicted time instants satisfies the second threshold, a measurement result of the second index corresponding to the second threshold comprises a non-triggering event; if the value of the second index corresponding to the second threshold at any predicted time instant of the plurality of predicted time instants does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold comprises a triggering event.

[0434] Optionally, the fourth indication information comprises any one of: at least one group of bits; at least one third predicted time instant; or, a value or an identifier of a target index at at least one fourth predicted time instant. The at least one group of bits corresponds to the at least one threshold one by one, each group of bits of the at least one group of bits comprises a plurality of bits, and the plurality of bits correspond to the plurality of predicted time instants one by one. A measurement result of each index of the at least one index at the third predicted time instant comprises a triggering event. A measurement result of a target index of the at least one index at the fourth predicted time instant comprises a triggering event, and a measurement result of an index other than the target index of the at least one index at the fourth predicted time instant comprises a non-triggering event.

[0435] Optionally, the at least one indicator comprises one or more of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of the predicted top K optimal beams, a probability that a predicted optimal beam is one of the measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0436] In another embodiment, when the apparatus 1100 is configured to implement the function of the network device in the method embodiment as shown in FIG. 8, the transceiver module 1110 is configured to: send fifth indication information, the fifth indication information being used to indicate a measurement result of the first indicator; and receive sixth indication information, the sixth indication information being used to indicate a plurality of measurement results, the plurality of measurement results comprising a measurement result of the first indicator at each of the plurality of predicted time instants.

[0437] Optionally, the transceiver module 1110 is configured to: send seventh indication information, the seventh indication information being used to indicate performance monitoring on the first indicator at each of the plurality of predicted time instants.

[0438] Optionally, the first indicator is any one of: a probability that a measured optimal beam is a predicted optimal beam, a probability that a measured optimal beam is one of the predicted top K optimal beams, a probability that a predicted optimal beam is one of the measured top K optimal beams, a difference between a measured RSRP of a measured k-th optimal beam and a predicted RSRP of the measured k-th optimal beam, a difference between a predicted RSRP of a predicted k-th optimal beam and a measured RSRP of the predicted k-th optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

[0439] More detailed descriptions of the steps can be found in the descriptions of the method embodiments above, which will not be repeated here.

[0440] Figure 12 is a schematic block diagram of another communication apparatus 1200 provided by the embodiments of the present application. As shown in Figure 12, the apparatus 1200 includes one or more processors 1210 and interface circuitry 1220. The one or more processors 1210 and the interface circuitry 1220 are coupled to each other. It can be understood that the interface circuitry 1220 can be a transceiver or an input / output interface. Optionally, the apparatus 1200 can further include a memory 1230 for storing instructions executed by the processor 1210, or for storing input data required by the processor 1210 to execute the instructions, or for storing data generated by the processor 1210 after executing the instructions. Sometimes, the interface circuitry 1220 can also be understood as a part of the one or more processors 1210, and in this case, the apparatus 1200 includes the one or more processors 1210.

[0441] The one or more processors 1210 and the memory 1230 can be separately arranged or integrally arranged, which is not limited in the present application.

[0442] When the apparatus 1200 is used to implement the methods shown in Figures 5, 7 and 8, the one or more processors 1210 are configured to implement the functions of the processing module 1120, and the interface circuitry 1220 is configured to implement the functions of the transceiver module 1110.

[0443] When the apparatus 1200 is a chip for a terminal device, the chip for the terminal device implements the functions of the terminal device in the above method embodiments. The chip for the terminal device receives information from a network device, which can be understood as that the information is first received by other modules (such as a radio frequency module or an antenna) in the terminal device, and then transmitted to the chip for the terminal device by the other modules. The chip for the terminal device transmits information to the network device, which can be understood as that the information is first transmitted to other modules (such as a radio frequency module or an antenna) in the terminal device, and then transmitted to the network device by the other modules.

[0444] When the apparatus 1200 is a chip for a network device, the chip for the network device implements the functions of the network device in the above method embodiments. The chip for the network device receives information from a terminal device, which can be understood as that the information is first received by other modules (such as a radio frequency module or an antenna) in the network device, and then transmitted to the chip for the terminal device by the other modules. The chip for the network device transmits information to the terminal device, which can be understood as that the information is first transmitted to other modules (such as a radio frequency module or an antenna) in the network device, and then transmitted to the terminal device by the other modules.

[0445] The embodiment of the present application further provides a computer readable storage medium for storing a computer program, which can enable a computer to execute the method in the above embodiment when the computer program runs on the computer. Alternatively, the computer program comprises instructions for implementing the method in the above embodiment.

[0446] The embodiment of the present application further provides a computer program product comprising a computer program or instructions, which can enable a computer to execute the method in the above embodiment when the computer program or instructions runs on the computer.

[0447] The embodiment of the present application further provides a chip comprising at least one processor, which can support implementation of the method in the above embodiment, for example, receiving or processing data involved in the method in the above embodiment.

[0448] It should be understood that, in the embodiment of the present application, the processor can be a CPU, and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0449] In the implementation process, each step of the above method can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The steps of the method disclosed in the embodiment of the present application can be directly embodied as hardware processor execution completion, or executed by combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor executes the instructions in the memory, and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0450] Those skilled in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or combination of computer software and electronic hardware. Whether the functions are executed in hardware or software mode depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0451] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and module can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0452] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0453] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical modules, i.e., can be located in one place or distributed to a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0454] In addition, the functional modules in each embodiment of the present application can be integrated into one processing module, or each module can exist physically, or two or more modules can be integrated into one module.

[0455] If the functions are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various program code storage media.

[0456] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: Comprising: receiving first indication information, the first indication information being used for indicating a plurality of thresholds, the plurality of thresholds corresponding to a first index, the plurality of thresholds corresponding to different prediction moments, each threshold in the plurality of thresholds corresponding to at least one prediction moment, the first index corresponding to performance of a model or a function; determining a measurement result corresponding to each threshold in at least one threshold, the measurement result corresponding to each threshold being a measurement result of the first index at the at least one prediction moment corresponding to each threshold, the plurality of thresholds including the at least one threshold; generating a first measurement result according to the measurement result corresponding to each threshold in the at least one threshold; sending second indication information, the second indication information being used for indicating the first measurement result.

2. The method of claim 1, wherein, The at least one threshold includes a first threshold, the measurement result of the first threshold including a trigger event or a non-trigger event; If values of the first index at all prediction moments corresponding to the first threshold satisfy the first threshold, the measurement result corresponding to the first threshold includes the non-trigger event; If values of the first index at any prediction moment corresponding to the first threshold do not satisfy the first threshold, the measurement result corresponding to the first threshold includes the trigger event.

3. The method of claim 2, wherein, The second indication information includes any of the following: a plurality of bit positions, the plurality of bit positions corresponding to the plurality of thresholds one by one; a first prediction moment, the measurement result of the first index at the first prediction moment and prediction moments after the first prediction moment including the trigger event, or the measurement result of the first index at the first prediction moment and prediction moments before the first prediction moment including the non-trigger event; or a value of the first index at a second prediction moment, the measurement result of the first index at the second prediction moment including the trigger event.

4. The method of claim 1, wherein, The at least one threshold includes a first threshold, the first threshold corresponding to a plurality of prediction moments, the measurement result of the first threshold including a trigger event and / or a non-trigger event; If values of the first index at any prediction moment corresponding to the first threshold satisfy the first threshold, the measurement result of the any prediction moment includes the non-trigger event; If values of the first index at the any prediction moment corresponding to the first threshold do not satisfy the first threshold, the measurement result of the any prediction moment includes the trigger event.

5. The method of claim 4, wherein, The second indication information includes any of the following: a plurality of bit positions, the plurality of bit positions corresponding to a plurality of prediction moments, the plurality of prediction moments corresponding to the plurality of thresholds; a first prediction moment, the measurement result of the first index at the first prediction moment and prediction moments after the first prediction moment including the trigger event, or the measurement result of the first index at the first prediction moment and prediction moments before the first prediction moment including the non-trigger event; or a value of the first index at a second prediction moment, the measurement result of the first index at the second prediction moment including the trigger event.

6. The method according to any one of claims 1 to 5, characterized in that, The first index is any of the following: The measured optimal beam is a probability of the measured optimal beam being the predicted optimal beam, a probability of the measured optimal beam being one of the predicted top K optimal beams, a probability of the predicted optimal beam being one of the measured top K optimal beams, a difference between a measured RSRP of a measured kth optimal beam and a predicted RSRP of the measured kth optimal beam, a difference between a predicted RSRP of a predicted kth optimal beam and a measured RSRP of the predicted kth optimal beam, a difference between an average of measured RSRPs of the measured top K optimal beams and an average of predicted RSRPs of the measured top K optimal beams, or a difference between an average of predicted RSRPs of the predicted top K optimal beams and an average of measured RSRPs of the predicted top K optimal beams.

7. A communication method characterized by comprising: Comprise: receiving third indication information, the third indication information being used for indicating at least one threshold, the at least one threshold corresponding to at least one index, the index corresponding to performance of a model or a function; determining a measurement result of the index corresponding to each threshold in the at least one threshold at each of a plurality of predicted time instants; sending fourth indication information, the fourth indication information being used for indicating the measurement result.

8. The method of claim 7, wherein, The at least one threshold comprises a second threshold, the second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all predicted time instants satisfies the second threshold, the measurement result of the second index corresponding to the second threshold comprises a non-triggering event; if the value of the second index corresponding to the second threshold at any predicted time instant in the plurality of predicted time instants does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold comprises the triggering event.

9. The method of claim 8, wherein, The fourth indication information comprises any of: at least one bit, the at least one bit corresponding to the at least one threshold in a one-to-one manner; at least one third predicted time instant; or a value or an identifier of a target index at at least one fourth predicted time instant; wherein the measurement result of each index in the at least one index at the third predicted time instant comprises the triggering event; the measurement result of the target index in the at least one index at the fourth predicted time instant comprises the triggering event, and the measurement result of an index other than the target index in the at least one index at the fourth predicted time instant comprises the non-triggering event.

10. The method of claim 7, wherein, The at least one threshold comprises a second threshold, the second threshold corresponding to a second index; if a value of the second index corresponding to the second threshold at all predicted time instants satisfies the second threshold, the measurement result of the second index corresponding to the second threshold comprises a non-triggering event; if the value of the second index corresponding to the second threshold at any predicted time instant in the plurality of predicted time instants does not satisfy the second threshold, the measurement result of the second index corresponding to the second threshold at the any predicted time instant comprises the triggering event.

11. The method of claim 10, wherein, The fourth indication information comprises any of: at least one set of bits corresponding to the at least one threshold value, each set of bits including a plurality of bits corresponding to the plurality of prediction instants; at least one third prediction instant; or a value or an identity of a target indicator at at least one fourth prediction instant; wherein the measurement of each of the at least one indicator at the third prediction instant includes the triggering event; the measurement of the target indicator of the at least one indicator at the fourth prediction instant includes the triggering event, and the measurement of each of the at least one indicator other than the target indicator at the fourth prediction instant includes the non-triggering event.

12. The method according to any one of claims 7 to 11, characterized in that, the at least one indicator includes one or more of: a probability that a measured best beam is a predicted best beam, a probability that a measured best beam is one of a predicted top K best beams, a probability that a predicted best beam is one of a measured top K best beams, a difference between a measured RSRP of a measured k-th best beam and a predicted RSRP of the measured k-th best beam, a difference between a predicted RSRP of a predicted k-th best beam and a measured RSRP of the predicted k-th best beam, a difference between an average of measured RSRPs of a measured top K best beams and an average of predicted RSRPs of the measured top K best beams, or a difference between an average of predicted RSRPs of a predicted top K best beams and an average of measured RSRPs of the predicted top K best beams.

13. A method of communication, comprising: comprising: receiving fifth indication information; determining, according to the fifth indication information, a plurality of measurement results including a measurement result of a first indicator at each of a plurality of prediction instants; sending sixth indication information indicating the plurality of measurement results.

14. The method of claim 13, wherein, before the determining, according to the fifth indication information, a plurality of monitoring results, the method further comprises: receiving seventh indication information indicating performance monitoring of the first indicator at each of the plurality of prediction instants.

15. The method according to claim 13 or 14, characterized in that, the first indicator is any one of: a probability that a measured best beam is a predicted best beam, a probability that a measured best beam is one of a predicted top K best beams, a probability that a predicted best beam is one of a measured top K best beams, a difference between a measured RSRP of a measured k-th best beam and a predicted RSRP of the measured k-th best beam, a difference between a predicted RSRP of a predicted k-th best beam and a measured RSRP of the predicted k-th best beam, a difference between an average of measured RSRPs of a measured top K best beams and an average of predicted RSRPs of the measured top K best beams, or a difference between an average of predicted RSRPs of a predicted top K best beams and an average of measured RSRPs of the predicted top K best beams.

16. A communications device, characterized by comprising modules for implementing the method of any one of claims 1 to 15.

17. A communications device, characterized by A computer program product tangibly embodied in a non-transitory machine readable storage medium containing instructions that, when executed, cause a processor to perform the method of any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that, A computer program for storing, which, when run on a computer, causes the method of any one of claims 1 to 15 to be performed.

19. A computer program product, characterised in that, Comprising: A computer program or instructions, which, when run, cause the method of any one of claims 1 to 15 to be performed.

Images