Communication method, terminal, network device and communication system

Abstract

The present disclosure relates to a communication method, a terminal, a network device, and a communication system. The method comprises: determining at least one reference signal resource, the at least one reference signal resource being used for beam measurement; determining a first report on the basis of the beam measurement result of the at least one reference signal resource, the first report comprising data for performance monitoring of a first artificial intelligence (AI) model, and the first AI model being used for performing beam or beam pair failure prediction; and sending the first report. According to embodiments of the present disclosure, the performance of an AI model is improved, the beam failure probability is reduced, and the communication performance based on beam transmission is improved.

Description

Communication method, terminal, network device and communication system Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to a communication method, a terminal, a network device, and a communication system. Background Art

[0002] In New Radio (NR), especially in operating frequency range 2, beam-based transmission and reception are required to ensure coverage.

[0003] Summary of the Invention

[0004] Beam management based on artificial intelligence (AI) models or AI functions requires monitoring model performance and reporting beam information. However, there is a phenomenon that inaccurate beam information reporting leads to reduced communication performance.

[0005] The embodiments of the present disclosure provide a communication method, a terminal, a network device, and a communication system.

[0006] According to a first aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: determining at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; determining a first report based on the beam measurement result of the at least one reference signal resource, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; and sending the first report.

[0007] According to a second aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: receiving a first report, the first report being used for performance monitoring of a first artificial intelligence (AI) model, the first AI model being used for beam or beam pair failure prediction; the first report being determined by a terminal based on a beam measurement result of at least one reference signal resource.

[0008] According to a third aspect of an embodiment of the present disclosure, a communication method is proposed, comprising: a terminal determining at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; determining a first report based on the beam measurement result of the at least one reference signal resource, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for predicting beam or beam pair failure; and sending the first report to a network device.

[0009] According to a fourth aspect of an embodiment of the present disclosure, a terminal is proposed, including: a processing module for determining at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; determining a first report based on the beam measurement result of the at least one reference signal resource, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for predicting beam or beam pair failure; and a transceiver module for sending the first report.

[0010] According to a fifth aspect of an embodiment of the present disclosure, a network device is proposed, including: a transceiver module, configured to receive a first report, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; the first report is determined by a terminal based on a beam measurement result of at least one reference signal resource.

[0011] According to a sixth aspect of an embodiment of the present disclosure, a terminal is proposed, comprising: one or more processors; wherein the processor is configured to execute the communication method of the first aspect.

[0012] According to a seventh aspect of an embodiment of the present disclosure, a network device is proposed, comprising: one or more processors; wherein the processor is used to execute the communication method of the second aspect.

[0013] According to an eighth aspect of an embodiment of the present disclosure, a communication system is provided, including a terminal and a network device, wherein the terminal is configured to implement the communication method of the first aspect, and the network device is configured to implement the communication method of the second aspect.

[0014] According to a ninth aspect of an embodiment of the present disclosure, a storage medium is provided, wherein the storage medium stores instructions, and wherein when the instructions are executed on a communication device, the communication device executes the communication method of any one of the first and second aspects.

[0015] Through the embodiments of the present disclosure, the performance of the AI ​​model is improved, the probability of beam failure is reduced, and the communication performance based on beam transmission is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0017] FIG1 is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0018] FIG2 is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure.

[0019] FIG3A is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0020] FIG3B is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0021] FIG3C is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0022] FIG4A is a flow chart showing a communication method according to an embodiment of the present disclosure.

[0023] FIG4B is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0024] FIG5 is an interactive diagram illustrating a communication method according to an embodiment of the present disclosure.

[0025] FIG6A is a schematic diagram of the structure of a terminal proposed in an embodiment of the present disclosure.

[0026] FIG6B is a schematic diagram of the structure of a network device proposed in an embodiment of the present disclosure.

[0027] FIG7A is a schematic structural diagram of a communication device proposed in an embodiment of the present disclosure.

[0028] FIG7B is a schematic diagram of the structure of the chip proposed in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The embodiments of the present disclosure provide a communication method, a terminal, a network device, and a communication system.

[0030] In a first aspect, an embodiment of the present disclosure proposes determining at least one reference signal resource, where the at least one reference signal resource is used for beam measurement; determining a first report based on the beam measurement result of the at least one reference signal resource, where the first report is used for performance monitoring of a first artificial intelligence (AI) model, where the first AI model is used for beam or beam pair failure prediction; and sending the first report.

[0031] In the above embodiment, the terminal determines the performance monitoring data of the first AI model based on the reference signal resource. Since the first AI model is used for beam failure prediction, performance monitoring of the model used for beam failure prediction is achieved, and the performance monitoring data is reported to the network device, so that the network device can make corresponding adjustments in time when the performance of the first AI model is poor, thereby improving the performance of the AI ​​model, reducing the probability of beam failure, and improving the communication performance based on beam transmission.

[0032] In combination with some embodiments of the first aspect, in some embodiments, the first report includes at least one of the following: a performance value of a first AI model; first data, the first data is data used to calculate the performance value of the first AI model; a first event, the first event is triggered based on a comparison result between the performance value of the first AI model and a threshold value; first information, the first information is used to represent a model management operation.

[0033] In the above embodiment, through the above content, the terminal can realize performance detection of the first AI model, thereby reducing the probability of beam failure due to poor model performance.

[0034] In combination with some embodiments of the first aspect, in some embodiments, the performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: beam failure or beam pair failure probability prediction accuracy; wireless link quality difference, the wireless link quality difference is the difference between the predicted wireless link quality and the measured wireless link quality; bit error rate BLER difference, the BLER difference is the difference between the predicted BLER and the measured BLER; beam or beam pair failure time difference, the beam or beam pair failure time difference is the predicted beam or beam pair failure time and the measured beam or beam pair failure time. The difference in failure time; the prediction accuracy of the failure time of the beam or beam pair; the prediction accuracy of the new beam or new beam pair; the prediction accuracy of the beam or beam pair with the layer 1 reference signal received power L1-RSRP difference within the first threshold, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, where the difference The difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair. The difference between L1-RSRP, wherein the predicted L1-RSRP difference includes at least one of the following: an average value of the predicted L1-RSRP difference, a cumulative distribution function of the predicted L1-RSRP difference, a proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0035] In the above embodiment, the terminal can detect the performance of the first AI model, thereby reducing the probability of beam failure due to poor model performance.

[0036] In conjunction with some embodiments of the first aspect, in some embodiments, the difference in wireless link quality includes at least one of the following:

[0037] The difference between the predicted wireless link quality value within a specified time and the measured wireless link quality value within a specified time, or the difference between the minimum predicted wireless link quality value within a specified time and the minimum measured wireless link quality value within a specified time.

[0038] In combination with some embodiments of the first aspect, in some embodiments, the BLER difference includes at least one of the following: a difference between a BLER value predicted within a specified time and a BLER value measured within the specified time, or a difference between a maximum BLER value predicted within the specified time and a maximum BLER value measured within the specified time.

[0039] In combination with some embodiments of the first aspect, in some embodiments, the time difference of the failure of the beam or beam pair includes at least one of the following: the difference between the failure time of the beam or beam pair predicted within the specified time and the failure time of the beam or beam pair measured within the specified time.

[0040] In combination with some embodiments of the first aspect, in some embodiments, the first data includes at least one of the following: when the first AI model is deployed on the terminal side, the first data includes: the first AI model output information and at least one item of measurement information corresponding to the first AI model output information; when the first AI model is deployed on the network side, the first data includes: the first AI model input information and at least one item of measurement information corresponding to the first AI model output information.

[0041] In combination with some embodiments of the first aspect, in some embodiments, the first AI model input information includes at least one of the following: measured first AI model input information; predicted current first AI model input information, predicted current first AI model input information is obtained based on the second AI model prediction; predicted first AI model input information at a future time, predicted first AI model input information at a future time is obtained based on the third AI model prediction; specified time; first beam quality threshold.

[0042] In the above embodiment, different inputs and outputs are set for different communication scenarios to which the first AI model is applicable, so that the first AI model can perform beam failure prediction in different communication scenarios.

[0043] In combination with some embodiments of the first aspect, in some embodiments, the measured first AI model input information includes at least one of the following: the identifiers of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the specified M beams in the measured first beam set. or L1-RSRP of a random N beams or beam pairs in the first beam set, where M is an integer greater than or equal to 1 and M is less than L; the measured L1-SINR of specified M beams or beam pairs in the first beam set; the measured L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1 and N is less than L; the measured L1-SINR of random N beams or beam pairs in the first beam set; the measured identifiers of random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0044] In the above embodiment, the first AI model implements beam failure prediction in the following scenario: predicting the probability that the radio link quality of the current best K beams will fall below a second quality threshold within a specified time, or the value of the radio link quality. The second AI model predicts the best K beams, while the first AI model predicts beam failure. The first and second AI models are different.

[0045] In combination with some embodiments of the first aspect, in some embodiments, the current first AI model input information is predicted, including at least one of the following: the identifiers of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of the best K beams or beam pairs in the predicted first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of all L beams or beam pairs in the predicted first beam set; the L1-RSRPs of specified M beams or beam pairs in the predicted first beam set, where M is greater than or an integer greater than or equal to 1, and M is less than L; the predicted L1-SINRs of specified M beams or beam pairs in the first beam set; the predicted L1-RSRPs of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; the predicted L1-SINRs of random N beams or beam pairs in the first beam set; the predicted identifiers of random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0046] In the above embodiment, the first AI model implements beam failure prediction in the following scenario: predicting the probability that the radio link quality of the current best K beams will fall below a second quality threshold within a specified time, or the value of the radio link quality. The second AI model predicts the best K beams, while the first AI model predicts beam failure. The first and second AI models are different.

[0047] In combination with some embodiments of the first aspect, in some embodiments, the first AI model input information or the second AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the measured second beam set, and the second beam information of the second beam set is used to input into the first AI model, wherein the second beam information includes an identifier, at least one of L1-RSRP and L1-SINR; L1-RSRP of multiple beams or beam pairs in the measured second beam set; L1-SINR of multiple beams or beam pairs in the measured second beam set; specified time; first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0048] In the above embodiment, the first AI model implements beam failure prediction in the following scenario: predicting the probability that the radio link quality of the best K beams at the current time will fall below a second quality threshold within a specified time, or the value of the radio link quality. The first AI model is used to predict both the best K beams and beam failure.

[0049] In combination with some embodiments of the first aspect, in some embodiments, the first AI model input information for predicting the future time includes at least one of the following: an identifier of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-RSRP of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; a layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; and a L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time. L1-RSRP of specified M beams or beam pairs; L1-SINR of specified M beams or beam pairs in the first beam set predicted in at least one future time; L1-RSRP of random N beams or beam pairs in the first beam set predicted in at least one future time; L1-SINR of random N beams or beam pairs in the first beam set predicted in at least one future time; identifiers of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; specified time corresponding to at least one future time; first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0050] In the above embodiment, the first AI model implements beam failure prediction in the following scenario: predicting the probability that the radio link quality of the best K beams in the future will fall below a second quality threshold within a specified time, or the value of the radio link quality. The third AI model predicts the best K beams, while the first AI model predicts beam failure. The first and third AI models are different.

[0051] In combination with some embodiments of the first aspect, in some embodiments, the first AI model input information or the third AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0052] In the above embodiment, the first AI model implements beam failure prediction in the following scenario: predicting the probability that the radio link quality of the best K beams in the future will fall below a second quality threshold within a specified time, or the value of the radio link quality. The first AI model is used to predict both the best K beams and beam failure.

[0053] In combination with some embodiments of the first aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within a specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; the lowest value of the wireless link quality value within the specified time; the highest value of the BLER value within the specified time; the beam failure time; and the identifier of the new beam.

[0054] In combination with some embodiments of the first aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identifier of the measured new beam.

[0055] In combination with some embodiments of the first aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; the lowest value of the wireless link quality value within the specified time; the highest value of the BLER value within the specified time; the beam failure time; the identifier of the new beam; the identifier of the best K beams or beam pairs in the first beam set; the L1-RSRP of the best K beams or beam pairs in the first beam set; the L1-SINR of the best K beams or beam pairs in the first beam set; the L1-RSRP of all L beams or beam pairs in the first beam set; the L1-SINR of all L beams or beam pairs in the first beam set.

[0056] In combination with some embodiments of the first aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the identifier of the measured new beam; a measurement value corresponding to the identifier of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the measured first beam set.

[0057] In combination with some embodiments of the first aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time.

[0058] In combination with some embodiments of the first aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; and a measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured.

[0059] In combination with some embodiments of the first aspect, in some embodiments, the first AI model outputs information including at least one of the following: a radio link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the radio link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the radio link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time; and the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time.

[0060] In combination with some embodiments of the first aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; a measurement value corresponding to the BLER value within a specified time corresponding to at least one future time measured. The measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time measured.

[0061] In combination with some embodiments of the first aspect, in some embodiments, the quality of the wireless link is determined based on at least one of the following: a signal-to-noise ratio (SNR) based on one beam; a signal-to-interference-and-noise ratio (SINR) based on one beam; an SNR or SINR determined based on the situation where two beams receive a physical downlink control channel (PDCCH).

[0062] In combination with some embodiments of the first aspect, in some embodiments, the first beam quality threshold, the specified time and at least one of the second beam quality threshold are determined based on at least one of the following: radio resource control RRC signaling; broadcast information; system information; protocol specified default value.

[0063] In combination with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following: information for activating the first AI model; information for deactivating the first AI model; information for switching the first AI model; and information for falling back to non-AI mode.

[0064] In the above embodiment, when the performance monitoring result of the first AI model is poor, the first AI model can be adjusted accordingly in a timely manner, thereby reducing the probability of beam failure and improving the communication performance based on beam transmission.

[0065] On the second aspect, an embodiment of the present disclosure proposes receiving a first report, the first report is used for performance monitoring of a first artificial intelligence AI model, and the first AI model is used for beam or beam pair failure prediction; the first report is determined by the terminal based on the beam measurement result of at least one reference signal resource.

[0066] In combination with some embodiments of the second aspect, in some embodiments, the first report includes at least one of the following: a performance value of a first AI model; first data, the first data is data used to calculate the performance value of the first AI model; a first event, the first event is triggered based on a comparison result between the performance value of the first AI model and a threshold value; first information, the first information is used to represent a model management operation.

[0067] In combination with some embodiments of the second aspect, in some embodiments, the performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: accuracy of prediction of beam failure or beam pair failure probability; difference in wireless link quality, the difference in wireless link quality is the difference between the predicted wireless link quality and the measured wireless link quality; difference in bit error rate BLER, the difference in BLER is the difference between the predicted BLER and the measured BLER; difference in beam or beam pair failure time, the difference in beam or beam pair failure time is the difference between the predicted beam or beam pair failure time and the measured beam or beam pair failure time; accuracy of prediction of beam or beam pair failure time; accuracy of prediction of new beam or new beam pair; accuracy of prediction of beam or beam pair whose layer 1 reference signal received power L1-RSRP difference is within a first threshold, the L1-RSRP difference is the best predicted beam or beam pair The method comprises the following steps: a first step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a second step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a second step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a third step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a third step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a fourth step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a fourth step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a fifth step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a fifth step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; a fifth step of determining the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted ... The difference between the measured L1-RSRP of the best predicted beam or beam pair and the predicted L1-RSRP difference includes at least one of the following: an average value of the predicted L1-RSRP difference, a cumulative distribution function of the predicted L1-RSRP difference, a proportion of the predicted L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0068] In combination with some embodiments of the second aspect, in some embodiments, the degree of difference in wireless link quality includes at least one of the following: the difference between the wireless link quality value predicted within a specified time and the wireless link quality value measured within a specified time, or the difference between the minimum value of the wireless link quality value predicted within a specified time and the minimum value of the wireless link quality value measured within a specified time.

[0069] In combination with some embodiments of the second aspect, in some embodiments, the BLER difference includes at least one of the following: a difference between a BLER value predicted within a specified time and a BLER value measured within the specified time, or a difference between a maximum BLER value predicted within the specified time and a maximum BLER value measured within the specified time.

[0070] In combination with some embodiments of the second aspect, in some embodiments, the time difference of the failure of the beam or beam pair includes at least one of the following: the difference between the failure time of the beam or beam pair predicted within the specified time and the failure time of the beam or beam pair measured within the specified time.

[0071] In combination with some embodiments of the second aspect, in some embodiments, the first data includes at least one of the following: when the first AI model is deployed on the terminal side, the first data includes: the first AI model output information and at least one item of measurement information corresponding to the first AI model output information; when the first AI model is deployed on the network side, the first data includes: the first AI model input information and at least one item of measurement information corresponding to the first AI model output information.

[0072] In combination with some embodiments of the second aspect, in some embodiments, the first AI model input information includes at least one of the following: measured first AI model input information; predicted current first AI model input information, predicted current first AI model input information is obtained based on the second AI model prediction; predicted first AI model input information at a future time, predicted first AI model input information at a future time is obtained based on the third AI model prediction; specified time; first beam quality threshold.

[0073] In combination with some embodiments of the second aspect, in some embodiments, the measured first AI model input information includes at least one of the following: the identification of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the L1-RSRP of the specified M beams in the measured first beam set. The method comprises the following steps: measuring L1-RSRP of a random beam or beam pair in the first beam set, wherein M is an integer greater than or equal to 1 and M is less than L; measuring L1-SINR of specified M beams or beam pairs in the first beam set; measuring L1-RSRP of random N beams or beam pairs in the first beam set, wherein N is an integer greater than or equal to 1 and N is less than L; measuring L1-SINR of random N beams or beam pairs in the first beam set; and measuring identifiers of random N beams or beam pairs in the first beam set; wherein at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0074] In combination with some embodiments of the second aspect, in some embodiments, the current first AI model input information is predicted, including at least one of the following: the identifiers of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of the best K beams or beam pairs in the predicted first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of all L beams or beam pairs in the predicted first beam set; the L1-RSRPs of specified M beams or beam pairs in the predicted first beam set, where M is a large number. an integer greater than or equal to 1, and M is less than L; predicted L1-SINRs of specified M beams or beam pairs in the first beam set; predicted L1-RSRPs of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; predicted L1-SINRs of random N beams or beam pairs in the first beam set; identifiers of the predicted random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0075] In combination with some embodiments of the second aspect, in some embodiments, the first AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the measured second beam set, and the second beam information of the second beam set is used to input into the first AI model, wherein the second beam information includes an identifier, at least one of L1-RSRP and L1-SINR; the measured L1-RSRP of multiple beams or beam pairs in the second beam set; the measured L1-SINR of multiple beams or beam pairs in the second beam set; a specified time; a first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0076] In combination with some embodiments of the second aspect, in some embodiments, the first AI model input information for predicting the future time includes at least one of the following: an identifier of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-RSRP of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; a layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an identifier of the first beam set predicted in the first beam set corresponding to at least one future time. predicting the L1-RSRP of M beams or beam pairs specified in the first beam set in at least one future time; predicting the L1-SINR of the specified M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the L1-RSRP of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the L1-SINR of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the identifiers of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0077] In combination with some embodiments of the second aspect, in some embodiments, the first AI model input information or the third AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0078] In combination with some embodiments of the second aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within a specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; the lowest value of the wireless link quality value within the specified time; the highest value of the BLER value within the specified time; the beam failure time; and the identifier of the new beam.

[0079] In combination with some embodiments of the second aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identifier of the measured new beam.

[0080] In combination with some embodiments of the second aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; the lowest value of the wireless link quality value within the specified time; the highest value of the BLER value within the specified time; the beam failure time; the identifier of the new beam; the identifier of the best K beams or beam pairs in the first beam set; the L1-RSRP of the best K beams or beam pairs in the first beam set; the L1-SINR of the best K beams or beam pairs in the first beam set; the L1-RSRP of all L beams or beam pairs in the first beam set; the L1-SINR of all L beams or beam pairs in the first beam set.

[0081] In combination with some embodiments of the second aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the measured identifier of the new beam; a measurement value corresponding to the measured identifier of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set.

[0082] In combination with some embodiments of the second aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time.

[0083] In combination with some embodiments of the second aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; and a measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured.

[0084] In combination with some embodiments of the second aspect, in some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time; and the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time.

[0085] In combination with some embodiments of the second aspect, in some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; a measurement value corresponding to the BLER value within a specified time corresponding to at least one future time measured. The measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time measured.

[0086] In combination with some embodiments of the second aspect, in some embodiments, the quality of the wireless link is determined based on at least one of the following: a signal-to-noise ratio (SNR) based on one beam; a signal-to-interference-and-noise ratio (SINR) based on one beam; an SNR or SINR determined based on the situation where two beams receive a physical downlink control channel (PDCCH).

[0087] In combination with some embodiments of the second aspect, in some embodiments, the first beam quality threshold, the specified time and at least one of the second beam quality threshold are determined based on at least one of the following: radio resource control RRC signaling; broadcast information; system information; protocol specified default value.

[0088] In combination with some embodiments of the second aspect, in some embodiments, the first information includes at least one of the following: information for activating the first AI model; information for deactivating the first AI model; information for switching the first AI model; and information for falling back to non-AI mode.

[0089] In a third aspect, an embodiment of the present disclosure proposes a communication method, which includes: the terminal determines at least one reference signal resource, and the at least one reference signal resource is used for beam measurement; based on the beam measurement result of the at least one reference signal resource, a first report is determined, and the first report is used for performance monitoring of a first artificial intelligence AI model, and the first AI model is used to predict beam or beam pair failure; and the first report is sent to a network device.

[0090] In a fourth aspect, an embodiment of the present disclosure proposes a terminal, comprising: a processing module for determining at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; determining a first report based on the beam measurement result of the at least one reference signal resource, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; and a transceiver module for sending the first report.

[0091] In a fifth aspect, an embodiment of the present disclosure proposes a network device, including: a transceiver module, used to receive a first report, the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; the first report is determined by the terminal based on the beam measurement result of at least one reference signal resource.

[0092] In a sixth aspect, an embodiment of the present disclosure proposes a terminal, comprising: one or more processors; wherein the processor is used to execute the communication method of the first aspect.

[0093] In a seventh aspect, an embodiment of the present disclosure proposes a network device, comprising: one or more processors; wherein the processor is used to execute the communication method of the second aspect.

[0094] In an eighth aspect, an embodiment of the present disclosure proposes a communication system, comprising: a terminal and a network device, wherein the terminal is configured to implement the communication method of the first aspect, and the network device is configured to implement the communication method of the second aspect.

[0095] In a ninth aspect, an embodiment of the present disclosure proposes a storage medium storing instructions, which, when the instructions are executed on a communication device, enables the communication device to execute any one of the communication methods of the first aspect and the second aspect.

[0096] It is understandable that the above-mentioned terminals, network devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to execute the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding methods.

[0097] The present disclosure provides communication methods, terminals, network devices, and communication systems. In some embodiments, the terms "data processing method," "information processing method," and "communication method" are interchangeable; the terms "data processing device," "information processing device," and "communication device" are interchangeable; and the terms "information processing system," "communication system," and "communication system" are interchangeable.

[0098] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0099] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0100] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0101] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0102] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0103] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0104] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0105] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0106] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0107] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0108] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0109] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0110] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0111] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0112] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0113] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)" "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0114] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0115] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0116] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0117] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0118] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0119] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0120] FIG1 is a schematic diagram illustrating the architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG1 , a communication system 100 includes a terminal 101 and a network device 102 .

[0121] In some embodiments, the terminal 101 includes, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0122] In some embodiments, the network device 102 may include at least one of an access network device and a core network device.

[0123] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a Wi-Fi system, but is not limited thereto.

[0124] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0125] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0126] In some embodiments, a core network device may be a device including one or more network elements, or may be multiple devices or device groups, each including all or part of the one or more network elements. The network element may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0127] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0128] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1 , or a portion thereof, but are not limited thereto. The entities shown in FIG1 are illustrative only. The communication system may include all or part of the entities shown in FIG1 , or may include other entities outside of FIG1 . The number and form of the entities are arbitrary, and the entities may be physical or virtual. The connection relationships between the entities are illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0129] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0130] In the disclosed embodiments, in NR, especially when the communication frequency band is in frequency range 2, since the high-frequency channel attenuates rapidly, beam-based transmission and reception are required to ensure coverage.

[0131] In some traditional beam management processes, network equipment configures a set of reference signal resources for beam measurement. The terminal measures the reference signal resources in this set and reports the IDs of some of the stronger reference signal resources, along with the corresponding layer 1 reference signal received power (L1-RSRP) and / or layer 1 signal to interference plus noise ratio (L1-SINR), to the network equipment.

[0132] In related art, it is assumed that the reference signal resource set configured by a network device includes X reference signal resources, each of which corresponds to a different transmit beam of the network device. For each reference signal resource, the terminal needs to use all receive beams to measure the reference signal. This results in obtaining the beam measurement qualities corresponding to all receive beams. In some cases, one or more best beam measurement qualities and / or the beam identifier corresponding to the best beam measurement quality can be determined. Therefore, the number of beam pairs that the terminal needs to measure is G*H. Here, G represents the number of transmit beams of the network device, and H represents the number of receive beams of the terminal.

[0133] In some embodiments, an AI model and / or AI function is provided to implement beam prediction, wherein an AI function can be considered as one or more AI models that implement the same function and purpose.

[0134] In some embodiments, the AI ​​model used for beam prediction can be referred to as a beam prediction model. Of course, it can also be referred to as a beam prediction AI model, a prediction AI model, a predicted beam model, etc. This disclosure does not limit the names of such AI models.

[0135] In some implementations, when the beam prediction model uses spatial prediction, the terminal measures the L1-RSRP of set B and inputs the measured value into the beam prediction model. The beam prediction model can predict the L1-RSRP of the best beam and / or beam pair in set A, and / or the identifier of the best beam and / or beam pair in set A.

[0136] The relationship between set B and set A includes the following two types:

[0137] The first relationship is that set B is a subset of set A. For example, if set A contains 32 reference signal resources (each reference signal resource corresponds to a beam direction), then set B contains some of them, for example, set B contains 8 of the 32 reference signal resources.

[0138] The second relationship is that set B is a wide beam and set A is a narrow beam. For example, set A contains 32 reference signal resources (each reference signal resource corresponds to a beam direction, and the 32 reference signal resources cover a 120-degree direction). Set B contains another Y reference signal resources, for example, Y = 8. These Y reference signal resources also cover a 120-degree direction, that is, the beam direction of each reference signal resource in set B covers the beam directions of multiple reference signal resources in set A. It can be understood that the relationship between the 32 / Y reference signal resources in set A and the one reference signal resource in set B is QCL Type D.

[0139] It should be understood that the examples of the first and second relationships described above only describe the transmit beam case. When considering beam pairs consisting of transmit and receive beams, the terminal's receive beams must also be considered. For example, if there are 32 transmit beams and 4 receive beams, then set A consists of 32*4 beam pairs, and set B can consist of 32 beam pairs, 16 beam pairs, and so on.

[0140] In some embodiments, if the performance of the beam prediction model does not need to be monitored, assuming that the AI ​​model has been trained in advance, the network device only needs to periodically send the reference signal on the reference resource of set B (for example, the first period). The terminal then measures the L1-RSRP of the reference signal on the reference signal resource in set B and inputs it into the beam prediction model. This outputs the L1-RSRP corresponding to the reference signal resource of set A or the strongest one or more reference signal resource IDs among the 32 reference signal resources in set A.

[0141] In some embodiments, if it is necessary to monitor the performance of the beam prediction model, the network device is required to periodically send the reference signal on the reference signal resource of set A (for example, the second period). Then the terminal needs to measure the L1-RSRP of the reference signal on the reference signal resource of set B. For the terminal side model, the terminal inputs the measured L1-RSRP of the reference signal on the reference signal resource of set B into the beam prediction model, obtains the predicted beam information, and reports it to the network device; for the network side model, the terminal reports the measured L1-RSRP and / or identifier of the reference signal on the reference signal resource of set B to the network device, and the network device inputs the L1-RSRP and / or identifier of the reference signal on the reference signal resource of set B into the beam prediction model to obtain the predicted beam information. At the same time, the terminal also measures the L1-RSRP of the reference signals on all reference signal resources in set A, and reports the measured L1-RSRP and / or identifier of the reference signals on all reference signal resources in set A, and / or the L1-RSRP and / or identifier of the best L beams / beam pairs as the beam information obtained by the traditional method to the base station.

[0142] In various embodiments of the present disclosure, the terms "terminal-side model" and "AI model deployed on the terminal" can be used interchangeably. The terms "network device-side model" and "AI model deployed on the network device" can be used interchangeably.

[0143] In some implementations, when the beam prediction model uses time-domain prediction, the terminal measures the L1-RSRP at a historical time point, set B, and inputs this into the beam prediction model to predict the L1-RSRP at a future time point, set A. In addition to the two aforementioned relationships between set B and set A, there is another relationship in which set B and set A are identical.

[0144] When beam measurement is performed using methods described in related technologies, the base station also needs to transmit reference signals at future times. The terminal measures the reference signals at future times and reports the measured beam information to the network device. Specifically, the terminal needs to measure and report the beam information for all beams and / or beam pairs in set A to the network device.

[0145] In some related technologies, in order to reduce the number of beam pairs measured by the terminal, an AI model is used for beam prediction. For example, the terminal originally needs to measure a total of G*H beam pairs. When using the AI ​​model for beam prediction, for spatial domain beam prediction, the terminal only needs to measure a part of the G*H beam pairs. For example, measure 1 / 8, 1 / 4 of G*H beam pairs, etc. Then, the beam measurement quality of these beam pairs measured is input into the AI ​​model, and the AI ​​model can output the beam information of G*H beam pairs. For time domain beam prediction, the terminal can measure the beam measurement quality of beam pairs at historical times to predict the beam information of beam pairs at future times.

[0146] Of course, for the input and output of some AI models, it is also possible to not consider the beam quality or beam identification of the beam pair, but only consider the beam quality or beam identification of the downlink transmit beam. For example, an AI model based on a downlink beam, rather than an AI model based on a beam pair, is not limited in this disclosure.

[0147] In some embodiments, for transmission based on beams or beam pairs, since the coverage of each beam or beam pair is prioritized, beam failure may occur if the beams or beam pairs are not updated in a timely manner.

[0148] In some embodiments, beam failure may be understood as corresponding radio link quality (radio link quality) being lower than a corresponding radio link quality threshold (Qout).

[0149] In some embodiments, in the event of beam failure, the terminal needs to report the beam failure to the network device, and the reporting method includes at least one of the following: reporting based on a scheduling request (SR), reporting based on a physical uplink shared channel (PUSCH), or reporting based on a random access process.

[0150] In some embodiments, in the event of a beam failure, if the terminal finds a new beam, it will report the relevant information of the new beam to the network device during the process of reporting the beam failure.

[0151] It is clear that in the event of beam failure, the communication performance of the terminal will be degraded or even interrupted.

[0152] In some embodiments, the above problems can be effectively solved by predicting beam failure information based on an AI model.

[0153] However, AI models have a specific lifecycle or scope of application. For example, some AI models are suitable for specific environments, such as suburban areas, urban areas, and indoor environments. Another example is that some AI models are suitable for rush hour, while others are suitable for specific time periods, such as during rush hour when there are fewer people. Another example is that some AI models may be suitable for specific times and environments, such as during the commuting hours when there are fewer people. Therefore, it is necessary to monitor the performance of AI models in real time. If the performance of an AI model does not meet the requirements, it is necessary to promptly update or switch the AI ​​model.

[0154] Based on this, an embodiment of the present disclosure proposes a communication method that enables a terminal to monitor the performance of a model used to predict beam failure, thereby improving the performance of an AI model used to predict beam failure information and reducing the probability of beam failure.

[0155] FIG2 is an interactive diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG2 , the embodiment of the present disclosure relates to a communication method, and the method includes:

[0156] Step S2101: Terminal 101 determines a reference signal resource.

[0157] In some embodiments, terminal 101 obtains reference signal resources.

[0158] In some embodiments, the terminal 101 obtains first information and determines a reference signal resource based on the first information.

[0159] In some embodiments, the first information is used to indicate at least one reference signal resource.

[0160] In some embodiments, the first information is used to indicate at least one reference signal resource set, where the reference signal resource set includes at least one reference signal resource.

[0161] In some embodiments, terminal 101 determines the reference signal resource based on protocol provisions.

[0162] In some embodiments, at least one reference signal resource is used for beam measurement.

[0163] In some embodiments, different reference signal resources in the at least one reference signal resource correspond to different reference signal resource sets.

[0164] Exemplarily, the first reference signal resource corresponds to a first reference signal resource set, and the second reference signal resource corresponds to a second reference signal resource set.

[0165] In some embodiments, different reference signal resources in the at least one reference signal resource correspond to the same reference signal resource set.

[0166] Exemplarily, the first reference signal resource corresponds to the first reference signal resource set, and the second reference signal resource corresponds to the first reference signal resource set.

[0167] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0168] Step S2102: Terminal 101 determines the first report.

[0169] In some embodiments, terminal 101 determines the first report based on at least one reference signal resource.

[0170] In some embodiments, the terminal 101 determines the first report based on a beam measurement result of at least one reference signal resource.

[0171] In some embodiments, the first report is used for first AI model performance monitoring.

[0172] In some embodiments, the first report includes data for monitoring the performance of a first artificial intelligence (AI) model.

[0173] In some embodiments, the first AI model performance monitoring includes at least one of the following: function-based performance monitoring and AI model-based performance monitoring.

[0174] In some embodiments, the first AI model is used to perform beam failure prediction and / or beam pair failure prediction.

[0175] In some embodiments, the first report includes at least one of the following:

[0176] Performance value of the first AI model, first data, first event, and first information.

[0177] In some embodiments, the first data is data used to calculate the performance of the first AI model.

[0178] In some embodiments, the first event is an event triggered based on a comparison result between a value of the first AI model performance and a threshold value.

[0179] For example, event 1 is when the beam failure prediction accuracy is lower than a certain threshold (eg, 80%), triggering event 1. Event 2 is when the beam failure prediction accuracy is higher than a certain threshold (eg, 90%), triggering event 2, and so on.

[0180] In some embodiments, the network device configures the first event.

[0181] In some embodiments, the terminal device determines the first event based on a default rule.

[0182] In some embodiments, the terminal determines whether to trigger the first event, or the specific content of triggering the first event, based on the predicted value output by the terminal-side model and the actually measured value.

[0183] In some embodiments, the first information includes at least one of the following: information activating the first AI model; information deactivating the first AI model; information switching the first AI model; information falling back to non-AI mode; and information refining the first AI model.

[0184] In some embodiments, the first information is used to represent a model management operation.

[0185] In some embodiments, the model management operation includes at least one of the following: activating an AI model, activating an AI function, deactivating an AI model, deactivating an AI function, switching an AI model, switching an AI function, and improving an AI model, etc.

[0186] In some embodiments, the performance value of the first AI model includes a value corresponding to at least one of the following performance indicators:

[0187] Accuracy of prediction of beam failure or beam pair failure probability, variability of radio link quality, variability of Block Error Rate (BLER), variability of failure time of beams or beam pairs, prediction accuracy of failure time of beams or beam pairs, prediction accuracy of new beams or new beam pairs, prediction accuracy of beams or beam pairs with Layer 1 reference signal received power (L1-RSRP) difference within a first threshold, L1-RSRP variability, predicted L1-RSRP variability, terminal throughput, reference signal overhead, uplink control information overhead and predicted delay, prediction accuracy of beams or beam pairs with Layer 1 signal to interference and noise ratio (L1-SINR) within a first threshold, L1-SINR variability, and predicted L1-SINR variability.

[0188] In some embodiments, the beam failure or beam pair failure probability includes: a hard failure probability, and a soft probability.

[0189] It should be understood that a hard probability can be understood as a probability that is neither "0" nor "1." For example, when predicting whether a beam will fail, there are only two possible outcomes: "1" indicating that the beam will fail, and "0" indicating that the beam will not fail. If the AI ​​model outputs a beam failure probability of "1," and the actual measurement indicates that the beam will fail, the prediction is accurate, indicating good or high beam failure prediction accuracy. Conversely, the beam failure prediction accuracy is poor or low.

[0190] It should be understood that the soft probability can be understood as including a probability that is neither "0" nor "1" in addition to "0" and "1". For example: for the prediction of whether the beam fails, the prediction result is: the probability of beam failure is 100%, 80%, 40% or 0. It should be noted that the 80% and 40% here are just examples, and other values ​​can also be used. If the beam failure probability obtained by the AI ​​model output is "1", and the actual measurement corresponding wireless link quality is lower than the first threshold, that is, the probability of beam failure is very high, then it means that the prediction result is accurate, that is, the beam failure prediction accuracy is good, or the beam failure prediction accuracy is high. If the beam failure probability obtained by the AI ​​model output is "0", and the actual measurement corresponding wireless link quality is higher than the second threshold, that is, the probability of beam failure is very small, then it means that the prediction result is accurate, that is, the beam failure prediction accuracy is good, or the beam failure prediction accuracy is high. If the AI ​​model outputs a beam failure probability of "40%," and the actual measured wireless link quality is lower than the second threshold but higher than the first threshold, meaning the beam failure probability is between 0 and 50%, then the prediction is accurate, indicating good or high beam failure prediction accuracy. Otherwise, the beam failure prediction accuracy is poor or low.

[0191] In some embodiments, the wireless link quality is determined based on at least one of:

[0192] The signal-to-noise ratio (SNR) based on one beam; that is, the SNR obtained by receiving the PDCCH based on one beam.

[0193] Signal-to-Interference-plus-Noise Ratio (SINR) based on one beam; that is, the SINR obtained by receiving the PDCCH based on one beam.

[0194] The SNR or SINR is determined based on the situation where two beams receive the Physical Downlink Control Channel (PDCCH).

[0195] In some embodiments, the difference in wireless link quality is a difference between a predicted wireless link quality and a measured wireless link quality.

[0196] In some embodiments, the difference in wireless link quality includes at least one of the following: the difference between the wireless link quality value predicted at a specified time and the wireless link quality value measured at a specified time, or the difference between the minimum wireless link quality value predicted within a specified time and the minimum wireless link quality value measured within a specified time.

[0197] In some embodiments, the BLER difference is the difference between the predicted BLER and the measured BLER.

[0198] In some embodiments, the BLER difference includes at least one of the following: a difference between a predicted BLER value at a specified time and a measured BLER value at the specified time, or a difference between a maximum predicted BLER value within a specified time and a maximum measured BLER value within the specified time.

[0199] The specified time can be the time after the current time plus the first time. The specified time can be the time from the current time to the time after the current time plus the first time.

[0200] In some embodiments, the degree of difference in the time to failure of a beam or beam pair is the degree of difference in the time to failure of a predicted beam or beam pair and the time to failure of a measured beam or beam pair.

[0201] In some embodiments, the time difference of beam or beam pair failure includes at least one of the following: a difference between a predicted beam or beam pair failure time within a specified time period and a measured beam or beam pair failure time within the specified time period. For example, if the predicted beam failure time is 80 ms after the current time, and the measured beam failure time is 60 ms after the current time, then the time difference of beam or beam pair failure is 20 ms or -20 ms.

[0202] In some embodiments, the L1-RSRP difference represents a beam or beam pair prediction accuracy within a first threshold, wherein the L1-RSRP difference is a difference between a measured L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of a best measured beam or beam pair.

[0203] Exemplarily, the first threshold may be 1 dB, and the prediction accuracy of a beam or beam pair with an L1-RSRP difference within the first threshold may be a prediction accuracy of a beam or beam pair with an L1-RSRP difference within 1 dB. The L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair.

[0204] In some embodiments, the L1-SINR difference represents the beam or beam pair prediction accuracy within a first threshold, wherein the L1-SINR difference is the difference between the measured L1-SINR of the best predicted beam or beam pair and the measured L1-SINR of the best beam or beam pair.

[0205] Exemplarily, the first threshold may be, for example, 1 dB, and the beam or beam pair prediction accuracy for which the L1-SINR difference is within the first threshold may be the beam or beam pair prediction accuracy for which the L1-SINR difference is within 1 dB. The L1-SINR difference is the difference between the measured L1-SINR of the best predicted beam or beam pair and the measured L1-SINR of the best beam or beam pair.

[0206] In some embodiments, L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair.

[0207] In some embodiments, L1-SINR difference is a difference between a measured L1-SINR of the best predicted beam or beam pair and a measured L1-SINR of the best beam or beam pair.

[0208] In some embodiments, the L1-RSRP difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair.

[0209] Exemplarily, the L1-RSRP difference can be the average value of the L1-RSRP difference. For example, the AI ​​model is used to perform one or more predictions to obtain A best predicted beams, and these A best predicted beams are measured respectively to obtain the measured L1-RSRP of the A best predicted beams. The difference between the predicted L1-RSRP of the A best predicted beams and the measured L1-RSRP of the measured best beam is calculated respectively, and the average value is taken, which is the average value of the L1-RSRP difference, that is, the L1-RSRP difference. Among them, the A best beams can be the A best beams obtained by using the AI ​​model for one prediction, or the A best beams obtained by using the AI ​​model for multiple predictions.

[0210] For example, the L1-RSRP difference may be a cumulative distribution function of L1-RSRP differences. For example, the value of the cumulative distribution function of L1-RSRP differences at a fixed percentage point is the L1-RSRP difference.

[0211] Exemplarily, the L1-RSRP difference may be a value of a cumulative distribution function at 5%, such as YdB.

[0212] Exemplarily, the L1-RSRP difference may be a ratio of L1-RSRP differences less than or equal to a second threshold. For example, if model AI is used for A predictions, and B predictions have L1-RSRP differences less than or equal to the second threshold, then the L1-RSRP difference is B / A.

[0213] Exemplarily, the L1-RSRP difference may be a ratio of L1-RSRP differences greater than a third threshold. For example, if the AI ​​model is used to perform C predictions, and D L1-RSRP differences are greater than the third threshold, then the L1-RSRP difference is D / C.

[0214] In some embodiments, the L1-SINR difference includes at least one of the following: the average value of the L1-SINR difference, the cumulative distribution function of the L1-SINR difference, the proportion of the L1-SINR difference less than or equal to the second threshold, and the proportion of the L1-SINR difference greater than the third threshold, wherein the L1-SINR difference is the difference between the measured L1-SINR of the best predicted beam or beam pair and the measured L1-SINR of the measured best beam or beam pair.

[0215] Exemplarily, the L1-SINR difference can be the average value of the L1-SINR difference. For example, the AI ​​model is used to perform one or more predictions to obtain A best prediction beams, and the A best prediction beams are measured respectively to obtain the measured L1-SINRs of the A best prediction beams. The difference between the predicted L1-SINR of the A best prediction beams and the measured L1-SINR of the measured best beam is calculated respectively, and the average value is taken, which is the average value of the L1-SINR difference, that is, the L1-SINR difference. Among them, the A best beams can be the A best beams obtained by using the AI ​​model for one prediction, or the A best beams obtained by using the AI ​​model for multiple predictions.

[0216] For example, the L1-SINR difference may be a cumulative distribution function of L1-SINR differences. For example, the value of the cumulative distribution function of L1-SINR differences at a certain fixed percentage point is the L1-SINR difference.

[0217] Exemplarily, the L1-SINR difference may be a value of a cumulative distribution function at 5%, such as YdB.

[0218] Exemplarily, the L1-SINR difference may be a ratio of L1-SINR differences less than or equal to a second threshold. For example, if model AI is used to perform A predictions, and B predictions have L1-SINR differences less than or equal to the second threshold, then the L1-SINR difference is B / A.

[0219] Exemplarily, the L1-SINR difference may be a ratio of L1-SINR differences greater than a third threshold. For example, if the AI ​​model is used to perform C predictions, and D L1-SINR differences are greater than the third threshold, then the L1-SINR difference is D / C.

[0220] The thresholds in this disclosure can be set according to actual conditions, for example, the first threshold, the second threshold and the third threshold can be the same or different.

[0221] In some embodiments, an L1-RSRP difference is predicted, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of the best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair.

[0222] In some embodiments, an L1-SINR difference is predicted, wherein the predicted L1-SINR difference is a difference between a predicted L1-SINR of the best predicted beam or beam pair and a measured L1-SINR of the best predicted beam or beam pair.

[0223] In some embodiments, the predicted L1-RSRP difference includes at least one of the following: the average value of the predicted L1-RSRP difference, the cumulative distribution function of the predicted L1-RSRP difference, the proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than a third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair.

[0224] In some embodiments, the predicted L1-SINR difference includes at least one of the following: an average value of the predicted L1-SINR difference, a cumulative distribution function of the predicted L1-SINR difference, a proportion of the predicted L1-SINR difference less than or equal to the second threshold, and a proportion of the L1-SINR difference greater than a third threshold, wherein the predicted L1-SINR difference is the difference between the predicted L1-SINR of the best predicted beam or beam pair and the measured SINR of the best predicted beam or beam pair.

[0225] In some embodiments, the terminal throughput can be calculated by determining a predicted optimal beam or beam pair, measuring the SINR of the optimal beam or beam pair, and calculating the capacity corresponding to each beam or beam pair based on the Shannon capacity. The difference between the capacities corresponding to the two beams or beam pairs is used as the average UE throughput difference.

[0226] In some embodiments, the terminal throughput may be an average throughput or a throughput at a fixed percentage of a cumulative distribution function, for example, the fixed percentage may be 5% or 95%.

[0227] In some embodiments, the reference signal overhead is how much reference signal resources the AI ​​model requires.

[0228] In some embodiments, the uplink control information overhead is the signaling overhead of sending the measurement results of set B.

[0229] In some embodiments, the delay required for model prediction can be expressed in milliseconds (ms). This means that the AI ​​model inputs multiple beam information measured at time A, and after the AI ​​model predicts the optimal beam at time B, the predicted delay is the difference between time A and time B. For example, the smaller the predicted delay, the better the performance of the AI ​​model.

[0230] In some embodiments, the first data includes at least one of the following:

[0231] When the first AI model is deployed on the terminal side, the first data includes: first AI model output information and at least one item of measurement information corresponding to the first AI model output information; when the first AI model is deployed on the network side, the first data includes: first AI model input information and at least one item of measurement information corresponding to the first AI model output information.

[0232] In some embodiments, the first AI model input information includes at least one of the following: measured first AI model input information; predicted current first AI model input information, where the predicted current first AI model input information is obtained based on the second AI model prediction; predicted first AI model input information at a future time, where the predicted first AI model input information at a future time is obtained based on the third AI model prediction; specified time; and a first beam quality threshold.

[0233] In some embodiments, when the first AI model is applicable to different communication scenarios, the first AI model input information for different communication scenarios is different.

[0234] It is understandable that when the communication scenarios to which the first AI model is applicable are different, the output information of the first AI model in different communication scenarios is different.

[0235] In some embodiments, different communication scenarios include at least one of the following:

[0236] A) The first AI model is used to predict beam failure information for the current best K beams within a specified time period. The beam information for the current best K beams is obtained through actual measurement or prediction by the second AI model, and the first AI model and the second AI model are different.

[0237] -B) The first AI model is used to predict beam failure information of the best K beams at the current time within a specified time. The beam information of the best K beams is also predicted by the first AI model.

[0238] -C) The first AI model is used to predict beam failure information of the best K beams in the future within a specified time period. The beam information of the best K beams is obtained by actual measurement or predicted by a third AI model, and the first AI model and the third AI model are different.

[0239] -D) The first AI model is used to predict beam failure information of the best K beams in the future within a specified time. The beam information of the best K beams is also predicted by the first AI model.

[0240] The beam failure information is the output information of the first AI model. See below for details.

[0241] In some embodiments, when the first AI model is applicable to A) the communication scenario, the first AI model input information includes: measured first AI model input information, or predicted first AI model input information.

[0242] In some embodiments, the measured first AI model input information includes at least one of the following: the identification of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the L1-RSRP of the specified M beams or beam pairs in the measured first beam set. 1-RSRP, where M is an integer greater than or equal to 1 and M is less than L; L1-SINR of specified M beams or beam pairs in the measured first beam set; L1-RSRP of random N beams or beam pairs in the measured first beam set, where N is an integer greater than or equal to 1 and N is less than L; L1-SINR of random N beams or beam pairs in the measured first beam set; identifiers of random N beams or beam pairs in the measured first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0243] Optionally, when the first AI model is applicable to A) the communication scenario, the measured first AI model input information includes at least one of the following: the identifiers of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the L1-RSRP of the specified M beams in the measured first beam set. The L1-RSRP of a beam or beam pair, where M is an integer greater than or equal to 1 and M is less than L; the measured L1-SINR of specified M beams or beam pairs in the first beam set; the measured L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1 and N is less than L; the measured L1-SINR of random N beams or beam pairs in the first beam set; the measured identifiers of random N beams or beam pairs in the first beam set; wherein at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set. The measured first AI model input information needs to be obtained by measuring the reference signal resources in the first reference signal resource set corresponding to the first beam set.

[0244] In some embodiments, the predicted first AI model input information includes at least one of the following: identifiers of the predicted best K beams or beam pairs in the first beam set; predicted L1-RSRPs of the best K beams or beam pairs in the first beam set; predicted layer 1 signal-to-interference-and-noise ratios (L1-SINRs) of the best K beams or beam pairs in the first beam set; predicted L1-RSRPs of all L beams or beam pairs in the first beam set; predicted L1-RSRPs of specified M beams or beam pairs in the first beam set, where M is an integer greater than or equal to 1. and M is less than L; the predicted L1-SINR of specified M beams or beam pairs in the first beam set; the predicted L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; the predicted L1-SINR of random N beams or beam pairs in the first beam set; the predicted identifiers of random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0245] Optionally, when the first AI model is applicable to A) the communication scenario, the predicted first AI model input information includes at least one of the following: the identifiers of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of the best K beams or beam pairs in the predicted first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the predicted first beam set; the L1-RSRPs of all L beams or beam pairs in the predicted first beam set; the L1-RSRPs of the specified M beams or beam pairs in the predicted first beam set, where M is greater than or an integer equal to 1, and M is less than L; the predicted L1-SINR of the specified M beams or beam pairs in the first beam set; the predicted L1-RSRP of the random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; the predicted L1-SINR of the random N beams or beam pairs in the first beam set; the identifiers of the random N beams or beam pairs in the predicted first beam set; wherein, wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set. wherein, the predicted first AI model input information can be obtained through the output information of the second AI model, wherein the input information of the second AI model includes the beam information of the second reference signal resource set. wherein the relationship between the second reference signal resource set and the first reference signal resource set can be the relationship between the above-mentioned set B and set A, that is, the second reference signal resource set is set B, and the first reference signal resource set is set A.

[0246] It can be understood that the relevant descriptions of set B and set A in the embodiments of the present disclosure can be found in the corresponding descriptions of the above embodiments. For the sake of ease of understanding, they will not be repeated here or in subsequent embodiments.

[0247] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within a specified time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; a lowest value of the wireless link quality value within a specified time; a highest value of the BLER value within a specified time; a beam failure time; and an identifier of a new beam.

[0248] Optionally, when the first AI model is applicable to the communication scenario A), the first AI model outputs information including at least one of the following: a radio link quality value at a specified time; a first probability value within the specified time, the first probability value being a probability value that the radio link quality value is lower than a second quality threshold; a BLER value at a specified time; a minimum radio link quality value within the specified time; a maximum BLER value within the specified time; a beam failure time; and an identifier of a new beam. It should be noted that if K is greater than 1, the output information of the first AI model may be outputting at least one of the above items for each of the K beams.

[0249] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identification of the measured new beam.

[0250] Optionally, when the first AI model is applicable to the communication scenario A), the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identifier of the measured new beam. It should be noted that if K is greater than 1, the measurement information corresponding to the output information of the first AI model may be at least one of the above items obtained by measuring each of the K beams separately.

[0251] In some embodiments, the first AI model input information or the second AI model input information includes at least one of the following:

[0252] The measured identifiers of multiple beams or beam pairs in the second beam set, and the second beam information of the second beam set is used to be input into the first AI model or the second AI model, wherein the second beam information includes the identifier, at least one of L1-RSRP and L1-SINR; the measured L1-RSRP of multiple beams or beam pairs in the second beam set; the measured L1-SINR of multiple beams or beam pairs in the second beam set; the specified time; the first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0253] In some embodiments, a first beam quality threshold is used to determine the new beam.

[0254] Exemplarily, when the terminal is searching for a new beam, only a new beam corresponding to a quality value greater than or equal to a first beam quality threshold is determined as a new beam.

[0255] Optionally, when the first AI model is applicable to B) the communication scenario, the first AI model input information includes at least one of the following:

[0256] The measured identifiers of multiple beams or beam pairs in the second beam set, and the second beam information of the second beam set is used to be input into the first AI model, wherein the second beam information includes the identifier, at least one of L1-RSRP and L1-SINR; the measured L1-RSRP of the multiple beams or beam pairs in the second beam set; the measured L1-SINR of the multiple beams or beam pairs in the second beam set; the specified time; the first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0257] It is understandable that when the first AI model is applicable to the communication scenario B), the first AI model is used to predict the K best beams and to predict the beam failures. Therefore, the input information of the first AI model in this case can include the input information of the second AI model.

[0258] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, wherein the first probability value is a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; a lowest value of the wireless link quality value within the specified time; a highest value of the BLER value within the specified time; a beam failure time; an identifier of a new beam; an identifier of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set.

[0259] In some embodiments, the first probability value is the probability value that the radio link quality of a certain beam is lower than the threshold value within a specified time, or the probability value that the BLER corresponding to the radio link quality is higher than the threshold value, that is, the probability value of beam failure.

[0260] Optionally, when the first AI model is applicable to the communication scenario B), the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within a specified time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; a minimum value of the wireless link quality value within a specified time; a maximum value of the BLER value within a specified time; a beam failure time; an identifier of a new beam; an identifier of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set. It should be noted that if K is greater than 1, the output information of the first AI model may be outputting at least one of the above items for each of the K beams.

[0261] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the identifier of the measured new beam; a measurement value corresponding to the identifier of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the measured first beam set.

[0262] Optionally, when the first AI model is applicable to the communication scenario B), the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the measured identifier of the new beam; a measurement value corresponding to the measured identifier of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set. It should be noted that if K is greater than 1, then the measurement information corresponding to the first AI model output information can be at least one of the above items obtained by measuring each of the K beams.

[0263] In some embodiments, when the first AI model is applicable to C) the communication scenario, the first AI model input information includes: predicted first AI model input information of the future time or measured first AI model input information.

[0264] In some embodiments, the first AI model input information of the predicted future time includes at least one of the following: an identifier of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-RSRP of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; a layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; and a number of M beams in the first beam set predicted in the first beam set corresponding to at least one future time. beam or beam pair; L1-SINR of specified M beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; L1-RSRP of random N beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; L1-SINR of random N beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; identifiers of random N beams or beam pairs in the first beam set are predicted in the first beam set corresponding to at least one future time; specified time corresponding to at least one future time; first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0265] Optionally, when the first AI model is applicable to the C) communication scenario, the predicted first AI model input information for the future time includes at least one of the following: an identifier of the predicted best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of the predicted best K beams or beam pairs in the first beam set corresponding to at least one future time; Layer 1 signal-to-interference-and-noise ratio L1-SINR of the predicted best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time L1-RSRP of specified M beams or beam pairs in the first beam set; L1-SINR of specified M beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; L1-SINR of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; identifiers of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; specified time corresponding to at least one future time; first beam quality threshold corresponding to at least one future time; wherein at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set. When the at least one future time corresponds to multiple future times, the above-mentioned input information needs to include at least one of the above items for each future time in the multiple future times. The predicted first AI model input information can be obtained through the output information of the third AI model, wherein the input information of the third AI model includes beam information of the second reference signal resource set at the historical time. The relationship between the second reference signal resource set and the first reference signal resource set may be the relationship between set B and set A, that is, the second reference signal resource set is set B, and the first reference signal resource set is set A.

[0266] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time.

[0267] Optionally, when the first AI model is applicable to the communication scenario C), the first AI model outputs information including at least one of the following: a radio link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the radio link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the radio link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time. It should be noted that when at least one future time corresponds to multiple future times, the above output information needs to include at least one of the above items for each of the multiple future times.

[0268] In some embodiments, the measurement information corresponding to the first AI model output information includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; and a measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured.

[0269] Optionally, when the first AI model is applicable to the C) communication scenario, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the radio link quality value at a specified time corresponding to at least one measured future time; a measurement value corresponding to the first probability value within a specified time corresponding to at least one measured future time; a measurement value corresponding to the BLER value at a specified time corresponding to at least one measured future time; a measurement value corresponding to the lowest value of the radio link quality value within a specified time corresponding to at least one measured future time; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one measured future time; a measurement value corresponding to the beam failure time corresponding to at least one measured future time; and a measurement value corresponding to the identifier of the new beam corresponding to at least one measured future time. It should be noted that when at least one future time corresponds to multiple future times, the above measurement information needs to include at least one of the above items for each of the multiple future times.

[0270] In some embodiments, the first AI model input information or the third AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0271] In some embodiments, a first beam quality threshold is used to determine the new beam.

[0272] Exemplarily, when the terminal is searching for a new beam, only a new beam corresponding to a quality value greater than or equal to a first beam quality threshold is determined as a new beam.

[0273] Optionally, when the first AI model is applicable to the communication scenario D), the first AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a designated time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set. When the at least one future time corresponds to multiple future times, the above input information needs to include at least one of the above items for each of the multiple future times.

[0274] It is understandable that when the first AI model is applicable to the communication scenario D), the first AI model is used to predict the best K beams and the beam prediction failure. Therefore, the input information of the first AI model in this case can include the input information of the third AI model.

[0275] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-RSRP of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-SINR of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-RSRP of all L beams or beam pairs in a first beam set corresponding to at least one future time; and the L1-SINR of all L beams or beam pairs in a first beam set corresponding to at least one future time.

[0276] In some embodiments, the first probability value is the probability value that the radio link quality of a certain beam is lower than the threshold value within a specified time, or the probability value that the BLER corresponding to the radio link quality is higher than the threshold value, that is, the probability value of beam failure.

[0277] Optionally, when the first AI model is applicable to the D) communication scenario, the first AI model outputs information including at least one of the following: a radio link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the radio link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the radio link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time; the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time; and the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time. It should be noted that, when at least one future time corresponds to multiple future times, the above output information needs to include at least one of the above items for each of the multiple future times.

[0278] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time; a measurement value corresponding to the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one future time; a measurement value corresponding to the beam failure time corresponding to at least one future time; a measurement value corresponding to at least one unmeasured time. The measurement value corresponding to the identifier of the new beam corresponding to the incoming time; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time measured.

[0279] Optionally, when the first AI model is applicable to the communication scenario D), the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the radio link quality value at a specified time corresponding to at least one measured future time; a measurement value corresponding to the first probability value within a specified time corresponding to at least one measured future time; a measurement value corresponding to the BLER value at a specified time corresponding to at least one measured future time; a measurement value corresponding to the lowest value of the radio link quality value within the specified time corresponding to at least one measured future time; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one measured future time; and a measurement value corresponding to the beam failure time corresponding to at least one measured future time. The measurement value corresponding to the identifier of the new beam corresponding to at least one measured future time; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one measured future time; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one measured future time; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one measured future time; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one measured future time; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one measured future time. It should be noted that when at least one future time corresponds to multiple future times, the above measurement information needs to include at least one of the above items for each of the multiple future times.

[0280] In some embodiments, at least one of the first beam quality threshold, the specified time, and the second beam quality threshold is determined based on at least one of: radio resource control RRC signaling; broadcast information; system information, and a protocol-specified default value.

[0281] In some embodiments, the first beam quality threshold is determined based on at least one of: radio resource control (RRC) signaling; broadcast information; system information, and a default value specified by the protocol.

[0282] In some embodiments, the designated time is determined based on at least one of: radio resource control (RRC) signaling; broadcast information; system information, and a protocol-specified default value.

[0283] In some embodiments, the designated time may be close to the period of periodic reporting of beam reports.

[0284] In some embodiments, the specified time may include at least one of the period of beam reporting, the time when the Medium Access Control Control Element (MAC CE) activates the Transmission Configuration Indicator (TCI) state, the time when the downlink control information (DCI) indicates the codepoint corresponding to the TCI state, and the time when the terminal sends the Hybrid Automatic Repeat Request Acknowledgement (HARQ-ACK) feedback corresponding to the DCI.

[0285] In some embodiments, the specified time may also include at least one of the following:

[0286] The terminal can indicate the search space period corresponding to the DCI format of the new beam; the time when the DCI indicates the code point corresponding to the TCI state and the time when the terminal sends the hybrid automatic repeat request acknowledgement (HARQ-ACK) feedback corresponding to the DCI.

[0287] In some embodiments, the second beam quality threshold is determined based on at least one of: radio resource control (RRC) signaling; broadcast information; system information, and a default value specified by the protocol.

[0288] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0289] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" may be used interchangeably. For example, a codebook may be a collection of one or more codewords / precoding matrices.

[0290] In some embodiments, terms such as "uplink", "uplink", "physical uplink" can be interchangeable with each other, and terms such as "downlink", "downlink", "physical downlink" can be interchangeable with each other, and terms such as "side", "sidelink", "side communication", "sidelink communication", "direct connection", "direct link", "direct communication", "direct link communication" can be interchangeable with each other.

[0291] In some embodiments, the terms "downlink control information (DCI)", "downlink (DL) assignment", "DL DCI", "uplink (UL) grant", "UL DCI" and the like may be used interchangeably.

[0292] In some embodiments, the terms "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based" and the like may be used interchangeably.

[0293] In some embodiments, the terms "search space", "search space set", "search space configuration", "search space set configuration", "control resource set (CORESET)", "CORESET configuration" and the like may be used interchangeably.

[0294] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0295] Step S2103 , the terminal 101 sends a first report to the network device 102 .

[0296] In some embodiments, network device 102 receives a first report.

[0297] In some embodiments, network device 102 receives a first report from terminal 101 .

[0298] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0299] In step S2104 , the network device 102 selects a beam.

[0300] In some embodiments, the network device 102 selects a beam based on the first report.

[0301] In some embodiments, the network device 102 selects a beam based on a predicted probability of beam failure.

[0302] For example, the terminal reports multiple beams, and the network device 102 may select a beam whose L1-RSRP is higher than a certain power threshold but whose beam failure probability is lower than a certain probability threshold as the current beam indicating the terminal.

[0303] Exemplarily, the terminal reports multiple beams, and the network device 102 may select a beam whose L1-RSRP is lower than a certain power threshold but whose beam failure probability is lower than a certain probability threshold as the current beam indicating the terminal.

[0304] For example, the terminal reports multiple beams, and the network device 102 may select a beam whose L1-RSRP is higher than a certain power threshold but whose beam failure probability is higher than a certain probability threshold as the current beam indicating the terminal.

[0305] The communication method involved in the embodiments of the present disclosure may include at least one of steps S2101 to S2104. For example, step S2103 may be implemented as an independent embodiment, step S2101 may be implemented as an independent embodiment, and steps S2101+S2102+S2103+S2104 may be implemented as independent embodiments, but the present disclosure is not limited thereto.

[0306] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0307] In some embodiments, steps S2101 and S2102 may be executed in an exchanged order or simultaneously, steps S2102 and S2103 may be executed in an exchanged order or simultaneously, and steps S2101 and S2103 may be executed in an exchanged order or simultaneously.

[0308] In some embodiments, steps S2101, S2102, and S2103 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0309] In some embodiments, steps S2101 , S2102 , and S2104 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0310] In some embodiments, steps S2101, S2103, and S2104 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0311] In some embodiments, steps S2102, S2103, and S2104 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0312] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 .

[0313] In some embodiments, FIG3A is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3A , the present disclosure embodiment relates to a communication method, the method including

[0314] Step S3101: Determine reference signal resources.

[0315] The optional implementation of step S3101 can refer to the optional implementation of step S2101 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0316] Step S3102, determine the first report.

[0317] The optional implementation of step S3102 can refer to the optional implementation of step S2102 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0318] Step S3103: Send the first report.

[0319] The optional implementation of step S3103 can refer to the optional implementation of step S2103 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0320] The communication method involved in the embodiments of the present disclosure may include at least one of steps S3101 to S3103. For example, step S3101 can be implemented as an independent embodiment, step S3102 can be implemented as an independent embodiment, step S3103 can be implemented as an independent embodiment, steps S3101+S3102 can be implemented as an independent embodiment, steps S3101+S3103 can be implemented as an independent embodiment, steps S3101+S3103 can be implemented as an independent embodiment, and steps S3101+S3102+S3103 can be implemented as an independent embodiment, but are not limited thereto.

[0321] In some embodiments, steps S3102 and S3103 may be executed in an exchanged order or simultaneously, steps S3101 and S3103 may be executed in an exchanged order or simultaneously, and steps S3102 and S3103 may be executed in an exchanged order or simultaneously.

[0322] In some embodiments, steps S3101 and S3103 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0323] In some embodiments, steps S3102 and S3103 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0324] FIG3B is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3B , the embodiment of the present disclosure relates to a communication method, and the method includes:

[0325] Step S3201: Determine reference signal resources and determine a first report.

[0326] The optional implementation of step S3201 can be found in step S2101 and step S2102 of Figure 2, the optional implementation of step S3101 and step S3102 of Figure 3A, and other related parts in the embodiments involved in Figures 2 and 3A, which will not be repeated here.

[0327] Step S3202: Send the first report.

[0328] The optional implementation of step S3202 can refer to the optional implementation of step S2103 in Figure 2, the optional implementation of step S3103 in Figure 3A, and other related parts of the embodiments involved in Figures 2 and 3A, which will not be repeated here.

[0329] The communication method involved in the embodiment of the present disclosure may include at least one of steps S3201 and S3202. For example, step S3201 may be implemented as an independent embodiment, and step S3202 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0330] In some embodiments, step S3201 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0331] In the embodiment of the present disclosure, step S3201 can be combined with steps S3102-S3103 of Figure 3A, and step S3202 can be combined with steps S3101, S3102, and S3103 of Figure 3A.

[0332] FIG3C is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3C , the embodiment of the present disclosure relates to a communication method, which includes:

[0333] Step S3301, determine the first report.

[0334] The optional implementation of step S3301 can be found in step S2101 and step S2102 of Figure 2, the optional implementation of step S3101 and step S3102 of Figure 3A, the optional implementation of step S3201 of Figure 3B and other related parts in the embodiments involved in Figures 2, 3A and 3B, which will not be repeated here.

[0335] Step S3302: Send the first report.

[0336] The optional implementation of step S3301 can refer to the optional implementation of step S2103 in Figure 2, step S3103 in Figure 3A, step S3202 in Figure 3B, and other related parts in the embodiments involved in Figures 2, 3A, and 3B, which will not be repeated here.

[0337] In some embodiments, at least one reference signal resource is determined, and the at least one reference signal resource is used for beam measurement; based on the beam measurement result of the at least one reference signal resource, a first report is determined, and the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used to predict beam or beam pair failure; and the first report is sent.

[0338] In some embodiments, the first report includes at least one of the following: a performance value of the first AI model; first data, the first data is data used to calculate the value of the first AI model performance; a first event, the first event is triggered based on the comparison result of the value of the first AI model performance and the threshold value; first information, the first information is used to represent the model management operation.

[0339] In some embodiments, the performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: beam failure or beam pair failure probability prediction accuracy; wireless link quality difference, the wireless link quality difference is the difference between the predicted wireless link quality and the measured wireless link quality; bit error rate BLER difference, the BLER difference is the difference between the predicted BLER and the measured BLER; beam or beam pair failure time difference, the beam or beam pair failure time difference is the difference between the predicted beam or beam pair failure time and the measured beam or beam pair failure time; beam or beam pair failure time prediction accuracy; new beam or new beam pair prediction accuracy; beam or beam pair layer 1 reference signal received power L1-RSRP difference within a first threshold value, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the measured L1-RSRP of the best predicted beam or beam pair. The difference between RSRP and the measured L1-RSRP of the measured best beam or beam pair, wherein the difference includes at least one of the following: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; the predicted L1-RSRP difference, the predicted L1-RSRP difference is the predicted L1-RSRP of the best predicted beam or beam pair. The difference between the SRP and the measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference includes at least one of the following: the average value of the predicted L1-RSRP difference, the cumulative distribution function of the predicted L1-RSRP difference, the proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0340] In some embodiments, the difference in wireless link quality includes at least one of the following: the difference between the wireless link quality value predicted within a specified time and the wireless link quality value measured within a specified time, or the difference between the minimum wireless link quality value predicted within a specified time and the minimum wireless link quality value measured within a specified time.

[0341] In some embodiments, the BLER difference includes at least one of the following: a difference between a predicted BLER value within a specified time and a measured BLER value within the specified time, or a difference between a maximum predicted BLER value within the specified time and a maximum measured BLER value within the specified time.

[0342] In some embodiments, the time difference of the beam or beam pair failure includes at least one of the following: a difference between the predicted beam or beam pair failure time within a specified time and the measured beam or beam pair failure time within the specified time.

[0343] In some embodiments, the first data includes at least one of the following: when the first AI model is deployed on the terminal side, the first data includes: the first AI model output information and at least one item of measurement information corresponding to the first AI model output information; when the first AI model is deployed on the network side, the first data includes: the first AI model input information and at least one item of measurement information corresponding to the first AI model output information.

[0344] In some embodiments, the first AI model input information includes at least one of the following: measured first AI model input information; predicted current first AI model input information, where the predicted current first AI model input information is obtained based on the second AI model prediction; predicted first AI model input information at a future time, where the predicted first AI model input information at a future time is obtained based on the third AI model prediction; specified time; and a first beam quality threshold.

[0345] In some embodiments, the measured first AI model input information includes at least one of the following: the identification of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the L1-RSRP of the specified M beams or beam pairs in the measured first beam set. 1-RSRP, where M is an integer greater than or equal to 1 and M is less than L; L1-SINR of specified M beams or beam pairs in the measured first beam set; L1-RSRP of random N beams or beam pairs in the measured first beam set, where N is an integer greater than or equal to 1 and N is less than L; L1-SINR of random N beams or beam pairs in the measured first beam set; identifiers of random N beams or beam pairs in the measured first beam set; wherein, the at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0346] In some embodiments, the current first AI model input information is predicted, including at least one of the following: identifiers of the best K beams or beam pairs in the predicted first beam set; L1-RSRPs of the best K beams or beam pairs in the predicted first beam set; Layer 1 signal-to-interference-and-noise ratios (L1-SINRs) of the best K beams or beam pairs in the predicted first beam set; L1-RSRPs of all L beams or beam pairs in the predicted first beam set; L1-RSRPs of specified M beams or beam pairs in the predicted first beam set, where M is an integer greater than or equal to 1. number, and M is less than L; predicted L1-SINRs of specified M beams or beam pairs in the first beam set; predicted L1-RSRPs of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; predicted L1-SINRs of random N beams or beam pairs in the first beam set; identifiers of the predicted random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0347] In some embodiments, the first AI model input information or the second AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the measured second beam set, and the second beam information of the second beam set is used to input into the first AI model, wherein the second beam information includes an identifier, at least one of L1-RSRP and L1-SINR; the measured L1-RSRP of multiple beams or beam pairs in the second beam set; the measured L1-SINR of multiple beams or beam pairs in the second beam set; a specified time; a first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0348] In some embodiments, the first AI model input information for predicting a future time includes at least one of the following: an identifier of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-RSRP of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; a layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; and a prediction of specified M beams in the first beam set corresponding to at least one future time. or beam pair; predicting the L1-RSRP of specified M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the L1-RSRP of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the L1-SINR of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; predicting the identifiers of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0349] In some embodiments, the first AI model input information or the third AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0350] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, wherein the first probability value is a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at the specified time; a lowest value of the wireless link quality value within the specified time; a highest value of the BLER value within the specified time; a beam failure time; and an identifier of a new beam.

[0351] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identification of the measured new beam.

[0352] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; a lowest value of the wireless link quality value within the specified time; a highest value of the BLER value within the specified time; a beam failure time; an identifier of the new beam; an identifier of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set.

[0353] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the identifier of the measured new beam; a measurement value corresponding to the identifier of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the measured first beam set.

[0354] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time.

[0355] In some embodiments, the measurement information corresponding to the first AI model output information includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; and a measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured.

[0356] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-RSRP of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-SINR of the best K beams or beam pairs in a first beam set corresponding to at least one future time; the L1-RSRP of all L beams or beam pairs in a first beam set corresponding to at least one future time; and the L1-SINR of all L beams or beam pairs in a first beam set corresponding to at least one future time.

[0357] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time; a measurement value corresponding to the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one future time; a measurement value corresponding to the beam failure time corresponding to at least one future time; a measurement value corresponding to at least one unmeasured time. The measurement value corresponding to the identifier of the new beam corresponding to the incoming time; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time measured.

[0358] In some embodiments, the wireless link quality is determined based on at least one of the following: a signal-to-noise ratio (SNR) based on one beam; a signal-to-interference-plus-noise ratio (SINR) based on one beam; an SNR or SINR determined based on the situation where two beams receive a physical downlink control channel (PDCCH).

[0359] In some embodiments, at least one of the first beam quality threshold, the specified time, and the second beam quality threshold is determined based on at least one of: radio resource control RRC signaling; broadcast information; system information; a protocol-specified default value.

[0360] In some embodiments, the first information includes at least one of the following: information for activating the first AI model; information for deactivating the first AI model; information for switching the first AI model; and information for falling back to a non-AI mode.

[0361] In the embodiment of the present disclosure, step S3301 may be combined with steps S3102-S3103 of FIG. 3A , and step S3301 may be combined with step S3202 of FIG. 3B .

[0362] FIG4A is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4A , the embodiment of the present disclosure relates to a communication method, and the method includes:

[0363] Step S4101, receiving the first report.

[0364] The optional implementation of step S4101 can refer to the optional implementation of step S2103 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0365] Step S4102, select a beam.

[0366] The optional implementation of step S4102 can refer to the optional implementation of step S2104 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0367] The communication method involved in the embodiment of the present disclosure may include at least one of steps S4101 to S4102. For example, step S4101 may be implemented as an independent embodiment, and step S4102 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0368] In some embodiments, step S4101 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0369] FIG4B is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4B , the embodiment of the present disclosure relates to a communication method, and the method includes:

[0370] Step S4201, receiving the first report.

[0371] The optional implementation of step S4201 can refer to the optional implementation of step S2103 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0372] In some embodiments, the network device 102 obtains the first report sent from the terminal 101, but is not limited thereto and may also obtain the first report from other entities.

[0373] In some embodiments, a first report is received, the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; the first report is determined by the terminal based on a beam measurement result of at least one reference signal resource.

[0374] In some embodiments, the first report includes at least one of the following: a performance value of a first AI model; first data, the first data is data used to calculate the value of the performance of the first AI model; a first event, the first event is triggered based on a comparison result between the value of the first AI model performance and a threshold value; first information, the first information is used to represent a model management operation.

[0375] In some embodiments, the performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: beam failure or beam pair failure probability prediction accuracy; wireless link quality difference, the wireless link quality difference is the difference between the predicted wireless link quality and the measured wireless link quality; bit error rate BLER difference, the BLER difference is the difference between the predicted BLER and the measured BLER; beam or beam pair failure time difference, the beam or beam pair failure time difference is the difference between the predicted beam or beam pair failure time and the measured beam or beam pair failure time; beam or beam pair failure time prediction accuracy; prediction accuracy of the new beam or new beam pair; prediction accuracy of the beam or beam pair with a layer 1 reference signal received power L1-RSRP difference within a first threshold, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference being the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes the following to At least one item: the average value of the L1-RSRP difference, the cumulative distribution function of the L1-RSRP difference, the proportion of the L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; predicted L1-RSRP difference, the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair The difference between the SRPs, wherein the predicted L1-RSRP difference includes at least one of the following: the average value of the predicted L1-RSRP difference, the cumulative distribution function of the predicted L1-RSRP difference, the proportion of the predicted L1-RSRP difference less than or equal to the second threshold, and the proportion of the L1-RSRP difference greater than the third threshold, wherein the predicted L1-RSRP difference is the difference between the predicted L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best predicted beam or beam pair; terminal throughput; reference signal overhead; uplink control information overhead; predicted delay.

[0376] In some embodiments, the difference in wireless link quality includes at least one of the following: the difference between the wireless link quality value predicted within a specified time and the wireless link quality value measured within a specified time, or the difference between the minimum wireless link quality value predicted within a specified time and the minimum wireless link quality value measured within a specified time.

[0377] In some embodiments, the BLER difference includes at least one of the following: a difference between a predicted BLER value within a specified time and a measured BLER value within the specified time, or a difference between a maximum predicted BLER value within the specified time and a maximum measured BLER value within the specified time.

[0378] In some embodiments, the time difference of the beam or beam pair failure includes at least one of the following: a difference between the predicted beam or beam pair failure time within a specified time and the measured beam or beam pair failure time within the specified time.

[0379] In some embodiments, the first data includes at least one of the following: when the first AI model is deployed on the terminal side, the first data includes: the first AI model output information and at least one item of measurement information corresponding to the first AI model output information; when the first AI model is deployed on the network side, the first data includes: the first AI model input information and at least one item of measurement information corresponding to the first AI model output information.

[0380] In some embodiments, the first AI model input information includes at least one of the following: measured first AI model input information; predicted current first AI model input information, where the predicted current first AI model input information is obtained based on the second AI model prediction; predicted first AI model input information at a future time, where the predicted first AI model input information at a future time is obtained based on the third AI model prediction; specified time; and a first beam quality threshold.

[0381] In some embodiments, the measured first AI model input information includes at least one of the following: the identification of the best K beams or beam pairs in the measured first beam set; the L1-RSRP of the best K beams or beam pairs in the measured first beam set; the layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the measured first beam set; the L1-SINR of all L beams or beam pairs in the measured first beam set, where L is greater than or equal to 1; the L1-RSRP of all L beams or beam pairs in the measured first beam set; the L1-RSRP of the specified M beams or beam pairs in the measured first beam set. 1-RSRP, where M is an integer greater than or equal to 1 and M is less than L; L1-SINR of specified M beams or beam pairs in the measured first beam set; L1-RSRP of random N beams or beam pairs in the measured first beam set, where N is an integer greater than or equal to 1 and N is less than L; L1-SINR of random N beams or beam pairs in the measured first beam set; identifiers of random N beams or beam pairs in the measured first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0382] In some embodiments, the current first AI model input information is predicted, including at least one of the following: identifiers of the best K beams or beam pairs in the predicted first beam set; L1-RSRPs of the best K beams or beam pairs in the predicted first beam set; Layer 1 signal-to-interference-and-noise ratios (L1-SINRs) of the best K beams or beam pairs in the predicted first beam set; L1-RSRPs of all L beams or beam pairs in the predicted first beam set; L1-RSRPs of specified M beams or beam pairs in the predicted first beam set, where M is greater than or equal to 1. an integer greater than or equal to 1, and M is less than L; a predicted L1-SINR of specified M beams or beam pairs in the first beam set; a predicted L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; a predicted L1-SINR of random N beams or beam pairs in the first beam set; an identifier of the predicted random N beams or beam pairs in the first beam set; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0383] In some embodiments, the first AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the measured second beam set, and second beam information of the second beam set is used to input into the first AI model, wherein the second beam information includes an identifier, at least one of L1-RSRP and L1-SINR; the measured L1-RSRP of multiple beams or beam pairs in the second beam set; the measured L1-SINR of multiple beams or beam pairs in the second beam set; a specified time; a first beam quality threshold; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0384] In some embodiments, the first AI model input information for predicting a future time includes at least one of the following: an identifier of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-RSRP of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; a layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs predicted in the first beam set corresponding to at least one future time; an L1-SINR of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; an L1-RSRP of all L beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; and a number of M beams in the first beam set predicted in the first beam set corresponding to at least one future time. beam or beam pair; L1-SINR of specified M beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; L1-RSRP of random N beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; L1-SINR of random N beams or beam pairs in the first beam set is predicted in the first beam set corresponding to at least one future time; identifiers of random N beams or beam pairs in the first beam set are predicted in the first beam set corresponding to at least one future time; specified time corresponding to at least one future time; first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

[0385] In some embodiments, the first AI model input information or the third AI model input information includes at least one of the following: identifiers of multiple beams or beam pairs in the second beam set measured in multiple historical times; L1-RSRP of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; L1-SINR of multiple beams or beam pairs in the multiple second beam sets measured in multiple historical times; a specified time corresponding to at least one future time; a first beam quality threshold corresponding to at least one future time; wherein, at least one reference signal resource is included in the second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

[0386] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, wherein the first probability value is a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at the specified time; a lowest value of the wireless link quality value within the specified time; a highest value of the BLER value within the specified time; a beam failure time; and an identifier of a new beam.

[0387] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; and a measurement value corresponding to the identification of the measured new beam.

[0388] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time; a first probability value within the specified time, the first probability value being the probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time; a lowest value of the wireless link quality value within the specified time; a highest value of the BLER value within the specified time; a beam failure time; an identifier of the new beam; an identifier of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set.

[0389] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at the measured specified time; a measurement value corresponding to the first probability value within the measured specified time; a measurement value corresponding to the BLER value at the measured specified time; a measurement value corresponding to the lowest value of the wireless link quality value within the measured specified time; a measurement value corresponding to the highest value of the BLER value within the measured specified time; a measurement value corresponding to the measured beam failure time; a measurement value corresponding to the identifier of the measured new beam; a measurement value corresponding to the identifier of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the measured first beam set; a measurement value corresponding to the L1-SINR of all L beams or beam pairs in the measured first beam set.

[0390] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; the highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; and an identifier of a new beam corresponding to at least one future time.

[0391] In some embodiments, the measurement information corresponding to the first AI model output information includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time measured; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to the lowest value of the wireless link quality value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the highest value of the BLER value within the specified time corresponding to at least one future time measured; a measurement value corresponding to the beam failure time corresponding to at least one future time measured; and a measurement value corresponding to the identifier of the new beam corresponding to at least one future time measured.

[0392] In some embodiments, the first AI model outputs information including at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; a first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value that the wireless link quality value is lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a highest value of the BLER value within a specified time corresponding to at least one future time; a beam failure time corresponding to at least one future time; an identifier of a new beam corresponding to at least one future time; an identifier of the best K beams or beam pairs in a first beam set corresponding to at least one future time; L1-RSRP of the best K beams or beam pairs in a first beam set corresponding to at least one future time; L1-SINR of the best K beams or beam pairs in a first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in a first beam set corresponding to at least one future time; L1-SINR of all L beams or beam pairs in a first beam set corresponding to at least one future time.

[0393] In some embodiments, the measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to the wireless link quality value at a specified time corresponding to at least one future time; a measurement value corresponding to the first probability value within a specified time corresponding to at least one future time; a measurement value corresponding to the BLER value at a specified time corresponding to at least one future time; a measurement value corresponding to the lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a measurement value corresponding to the highest value of the BLER value within a specified time corresponding to at least one future time; a measurement value corresponding to the beam failure time corresponding to at least one future time; a measurement value corresponding to at least one unmeasured time. The measurement value corresponding to the identifier of the new beam corresponding to the incoming time; the measurement value corresponding to the identifier of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; the measurement value corresponding to the L1-SINR of all L beams or beam pairs in the first beam set corresponding to at least one future time measured.

[0394] In some embodiments, the wireless link quality is determined based on at least one of the following: a signal-to-noise ratio (SNR) based on one beam; a signal-to-interference-plus-noise ratio (SINR) based on one beam; an SNR or SINR determined based on the situation where two beams receive a physical downlink control channel (PDCCH).

[0395] In some embodiments, at least one of the first beam quality threshold, the specified time, and the second beam quality threshold is determined based on at least one of: radio resource control RRC signaling; broadcast information; system information; a protocol-specified default value.

[0396] In some embodiments, the first information includes at least one of the following: information for activating the first AI model; information for deactivating the first AI model; information for switching the first AI model; and information for falling back to a non-AI mode.

[0397] Figure 5 is an interactive diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 5, the embodiment of the present disclosure relates to a communication method, which includes:

[0398] Step S5101: Terminal 101 determines a reference signal resource.

[0399] The optional implementation of step S5101 can refer to the optional implementation of step S2101 in Figure 2, step S3101 in Figure 3A, step S3201 in Figure 3B, and other related parts in the embodiments involved in Figures 2, 3A, and 3B, which will not be repeated here.

[0400] Step S5102: Terminal 101 determines the first report.

[0401] The optional implementation of step S5102 can be found in the optional implementation of step S2102 in Figure 2, step S3102 in Figure 3A, step S3201 in Figure 3B, step S3301 in Figure 3C, and other related parts in the embodiments involved in Figures 2, 3A, 3B, and 3C, which will not be repeated here.

[0402] Step S5103 , the terminal 101 sends a first report to the network device 102 .

[0403] For the optional implementation of step S5103, please refer to the optional implementation of step S2103 in Figure 2, step S3103 in Figure 3A, step S3202 in Figure 3B, step S3302 in Figure 3C, step S4101 in Figure 4A, step S4201 in Figure 4B and other related parts in the embodiments involved in Figures 2, 3A, 3B, 3C, 4A and 4B, which will not be repeated here.

[0404] In some embodiments, the above method may include the method described in the above embodiments of the communication system side, terminal side, network device side, etc., which will not be repeated here.

[0405] This embodiment also provides a communication method for improving AI model performance, reducing the probability of beam failure, and improving communication performance based on beam transmission.

[0406] In some embodiments, the terminal receives first information, determines a reference signal resource based on the first information, obtains a first report, and sends the first report to the network device.

[0407] In some embodiments, the first report includes data for model performance monitoring, the data including data for calculating a performance metric, or a calculated performance metric, or an event triggered based on a comparison of the performance metric with a threshold, or an operational decision made for model management (deactivating the model, activating the model, switching the model, or falling back to a non-AI mode).

[0408] In some embodiments, the performance metric used for model performance monitoring includes at least one of the following:

[0409] Beam failure probability prediction accuracy, radio link quality (RLQ) value difference, bit error rate (BLER) value difference, beam failure time difference or beam failure time prediction accuracy, new beam prediction accuracy, and traditional performance metrics.

[0410] In some embodiments, the accuracy of beam failure probability prediction includes at least one of the following: if the prediction is a hard probability, then if the prediction that the beam will fail is actually the beam will fail, then the prediction is accurate, otherwise it is inaccurate; if the prediction is a soft probability, then if the probability of predicting that it is higher than Qout is greater than 50%, and it is actually higher than Qout, then the prediction is accurate, otherwise it is inaccurate.

[0411] In some embodiments, the difference of the radio link quality value includes at least one of the following: if the predicted radio link quality value at a specified time is used, then the measured radio link quality value at the specified time is used, and the difference between the predicted value and the measured value is used; if the predicted radio link quality value within the specified time is used, then the lowest measured radio link quality value within the specified time is used, and the difference between the predicted lowest value and the measured lowest value is used.

[0412] In some embodiments, the BLER value difference includes at least one of the following: if the predicted BLER value at a specified time is a predicted BLER value, then the measured BLER value at the specified time is considered, and the difference between the predicted value and the measured value is the difference; if the predicted BLER value within the specified time is a minimum value of the predicted BLER, then the minimum value of the measured BLER within the specified time is considered, and the difference between the predicted minimum value and the measured minimum value is the difference.

[0413] In some embodiments, the difference in beam failure time or the prediction accuracy of beam failure time includes at least one of the following:

[0414] If beam failure is predicted to occur within a specified time, the difference between the predicted time of beam failure and the measured time of beam failure is the beam failure time difference; or if the difference between the predicted time of beam failure and the measured time of beam failure is below a threshold value, the prediction is accurate; otherwise, the prediction is inaccurate.

[0415] In some embodiments, the accuracy of the new beam prediction includes at least one of the following: if a beam failure is predicted to occur within a specified time, then the measured beam failure will also occur. If the predicted new beam contains the measured new beam, the prediction is accurate; otherwise, the prediction is inaccurate.

[0416] In some embodiments, a traditional performance metric includes at least one of the following:

[0417] Beam prediction accuracy of top 1 / K beam(pair), beam prediction accuracy of beams or beam pairs with L1-RSRP within 1 dB, L1-RSRP difference, predicted L1-RSRP difference, average UE throughput, reference signal overhead, uplink control information overhead, and predicted latency.

[0418] In some embodiments, with respect to beam prediction accuracy, correct prediction means: the predicted strongest beam (pair) ID contains the actual strongest beam (pair) ID or the predicted strongest beam (pair) ID is contained in the actual strongest N beam (pair) IDs. The downlink transmit beam ID can be equivalent to the reference signal resource ID, such as an SSB ID or a CSI-RS ID or an SRS ID. The downlink receive beam ID is the Rx beam ID of the terminal. The beam pair ID is the ID corresponding to the combination of the downlink transmit beam and the downlink receive beam. The strongest means that the L1-RSRP or L1-SINR is the strongest. This indicator can be the accuracy of the beam information output based on multiple derivations of the model, such as a ratio.

[0419] In some embodiments, the prediction accuracy for beams or beam pairs within 1 dB of L1-RSRP difference refers to the accuracy when the actual L1-RSRP of the predicted best beam (pair) and the actual L1-RSRP of the best beam (pair) are within 1 dB of each other. This metric can be the accuracy of beam information output from multiple model derivations, for example, a ratio.

[0420] In some embodiments, the L1-RSRP difference refers to the difference between the actual L1-RSRP of the predicted optimal beam (pair) and the actual L1-RSRP of the actual optimal beam, such as an average value of X dB, or a value of Y dB at the 5% percentile of the cumulative distribution function. It can also be the proportion of L1-RSRP differences below or above a threshold.

[0421] In some embodiments, the predicted L1-RSRP difference refers to the difference between the actual L1-RSRP of the predicted best beam (pair) and the predicted L1-RSRP of the best beam of the predicted best beam (pair), such as an average of X dB or a cumulative distribution function of Y dB at the 5% percentile. Alternatively, it can be the percentage of predicted L1-RSRP differences below or above a threshold.

[0422] In some embodiments, for the average terminal throughput, or the UE throughput at the 5% cumulative distribution function, the SINRs corresponding to the predicted strongest beam (pair) and the actual strongest beam (pair) are obtained, and the capacity is calculated based on the Shannon capacity. The capacity difference is the indicator.

[0423] In some embodiments, the reference signal overhead, ie, how much reference signal resources the model requires, is mainly affected by the size of set B corresponding to the model input and the number of historical measurement times during time domain prediction.

[0424] In some embodiments, with respect to the uplink control information overhead, if it is a network-side (NW-side) model, the measurement results of set B need to be reported to the network, ie, the signaling overhead of the report.

[0425] In some embodiments, the predicted delay may be in milliseconds (ms).

[0426] In some embodiments, the data used to calculate the performance metric for model performance monitoring includes at least one of the following:

[0427] When the model is on the terminal side, the terminal needs to report the predicted value of the model output and the corresponding measured value of each value. The output value includes what is described in the above model output, and the measured value is a measurement value corresponding to each output value.

[0428] When the model is on the network side, the model output values ​​are also on the network side, so the terminal only needs to report the measured values ​​for each value corresponding to the predicted value of the model output. In addition, for the input of the network-side model, the terminal also needs to report the model input information. However, the model input information and the measured values ​​used for model performance monitoring can be in the same report or in different reports.

[0429] In some embodiments, the terminal reports an event triggered based on a performance metric.

[0430] For example, the network device configures events. For example, if event 1 indicates that the beam failure prediction accuracy is less than 80%, event 1 is triggered; if event 2 indicates that the beam failure prediction accuracy is greater than 90%, event 2 is triggered; if event 3 indicates that the difference in the Radio link quality value is less than 1dB, event 3 is triggered; if event 4 indicates that the difference in the Radio link quality value is greater than 3dB, event 4 is triggered... Therefore, the terminal determines whether to trigger and which event to trigger based on the predicted value output by the terminal-side model and the actual measured value, and then reports the corresponding event ID, and can further report the value of the performance metric corresponding to the triggering event.

[0431] In some embodiments, the terminal makes a judgment based on the predicted value of the terminal side model and the actual measured value to determine whether it is necessary to activate or deactivate or switch the AI ​​model or function (the above AI model performance monitoring can be based on the performance monitoring of the model or function), and informs the network side model terminal of the decision.

[0432] In some embodiments, the input and output of the model are divided into multiple cases.

[0433] In some embodiments, Case 1 may include predicting the probability or radio link quality value of the current K best beams being lower than Qout within a specified time period, and the current K best beams are the best K beams actually measured, not the best K beams predicted by the AI ​​model. Alternatively, the best K beams may be output by the AI ​​model, but the model used to predict the best K beams and the model used to predict the beam failure are different. This means that the best K beams were already obtained before the beam prediction failed.

[0434] In some embodiments, for the scenario 1, the model input includes at least one of the following: at least one of L1-RSRP, L1-SINR, and beam (pair) ID (reference signal resource ID and / or Rx beam ID) of only the best K beams actually measured;

[0435] Includes the L1-RSRP or L1-SINR of all beams in set A;

[0436] Includes L1-RSRP or L1-SINR of fixed multiple beams in set A;

[0437] At least one of L1-RSRP, L1-SINR, and beam (pair) ID (reference signal resource ID and / or Rx beam ID) of a plurality of randomly selected beams in set A;

[0438] Model input can also include specified time, Qin value, etc.

[0439] In some embodiments, for the scenario 1, the model output includes at least one of the following (for each best beam or for the best beam):

[0440] The probability that the radio link quality is lower than Qout within a specified time;

[0441] The radio link quality includes SNR and SINR, and then the BLER corresponding to the radio link quality is obtained. If the BLER is higher than Qout, it means that the beam has failed.

[0442] The probability value can be a hard probability, that is, if the BLER is found to be higher than Qout, the probability is 1, otherwise the probability is 0. The probability value can also be a soft probability. For example, if the BLER is found to be higher than Qout and the difference above Qout is greater than a threshold, the probability is 1, otherwise the probability is 80%; if the BLER is found to be lower than Qout and the difference below Qout is greater than a threshold, the probability is 0, otherwise the probability is 30%.

[0443] The radio link quality value or BLER value at a specified time;

[0444] That is, predict the value of radio link quality or BLER at the time point corresponding to the specified time;

[0445] The lowest value of radio link quality or the highest value of BLER within a specified time;

[0446] That is, predict the lowest value of radio link quality or the highest value of BLER before the time point corresponding to the specified time and after the current time;

[0447] If the lowest value of radio link quality or the highest value of BLER is greater than Qout, it means that beam failure will occur in the middle;

[0448] Furthermore, if the previous outputs determine that beam failure will occur within a specified time, the time when beam failure will occur can be further given, as well as a new beam identifier;

[0449] The RSRP of the new beam is higher than that of Qin;

[0450] The new beam can be one or more.

[0451] In some embodiments, the case 2 scenario may include: predicting the probability that the radio link quality of the best K beams at the current time is lower than Qout or the value of the radio link quality within a specified time, and the best K beams at the current time and the beam failure prediction are predicted by the same model output, that is, one model simultaneously predicts the best K beams and the beam failure information corresponding to the best K beams.

[0452] In some embodiments, for the scenario of case 2, the model input includes at least one of the following: at least one of the L1-RSRP or L1-SINR and beam (pair) ID (reference signal resource ID and / or Rx beam ID) of multiple beams within set B; the model input may also include a specified time, a Qin value, etc.

[0453] In some embodiments, for the scenario of Case 2, the model output includes at least one of the following: the probability that the radio link quality is lower than Qout within a specified time;

[0454] The radio link quality includes SNR and SINR, and then the BLER corresponding to the radio link quality is obtained. If the BLER is higher than Qout, it means that the beam has failed.

[0455] The probability value can be a hard probability, that is, if the BLER is found to be higher than Qout, the probability is 1, otherwise the probability is 0. The probability value can also be a soft probability. For example, if the BLER is found to be higher than Qout and the difference above Qout is greater than a threshold, the probability is 1, otherwise the probability is 80%; if the BLER is found to be lower than Qout and the difference below Qout is greater than a threshold, the probability is 0, otherwise the probability is 30%.

[0456] The radio link quality value or BLER value at a specified time;

[0457] That is, predict the value of radio link quality or BLER at the time point corresponding to the specified time;

[0458] The lowest value of radio link quality or the highest value of BLER within a specified time;

[0459] That is, predict the lowest value of radio link quality or the highest value of BLER before the time point corresponding to the specified time and after the current time;

[0460] If the lowest value of radio link quality or the highest value of BLER is greater than Qout, it means that beam failure will occur in the middle;

[0461] Furthermore, if the previous outputs determine that beam failure will occur within a specified time, the time when beam failure will occur can be further given, as well as a new beam identifier;

[0462] The RSRP of the new beam is higher than that of Qin;

[0463] The new beam can be one or more;

[0464] The above is the same as case 1, but it is also necessary to output the best K beam IDs in set A corresponding to the spatial beam prediction or the best K beam IDs and their L1-RSRP / L1-SINR, or the L1-RSRP / L1-SINR of all beams in set A.

[0465] In some embodiments, the case 3 scenario may include: predicting the probability or radio link quality value of the best K beams in the future time being lower than Qout within a specified time, and the best K beams in the future time have been predicted by another model output, that is, different models predict the best K beams in the future, and beam failure information corresponding to the best K beams.

[0466] In some embodiments, for the case 3 scenario, the model input includes at least one of the following: Compared with case 1, the input may include values ​​corresponding to multiple historical times.

[0467] In some embodiments, for scenario 3, the model output includes at least one of the following: the output also includes beam failure information of the best K beams at multiple future times within a specified time, similar to time-domain beam prediction.

[0468] In some embodiments, the case 4 scenario may include: predicting the probability or radio link quality value of the best K beams in the future time being lower than Qout within a specified time, and the best K beams in the future time and the beam failure prediction are predicted by the same model output, that is, one model simultaneously predicts the best K beams and the beam failure information corresponding to the best K beams.

[0469] In some embodiments, for the Case 4 scenario, the model input includes at least one of the following: compared with Case 2, the input may include values ​​corresponding to multiple historical times.

[0470] In some embodiments, for scenario 4, the model output includes at least one of the following: the output also includes beam failure information of the best K beams at multiple future times within a specified time, similar to time-domain beam prediction.

[0471] In some embodiments, the radio link quality may be calculated based on one beam, or may be calculated based on the situation where two beams simultaneously receive the PDCCH.

[0472] In some embodiments, Qout, Qin or the designated time may be configured by base station RRC signaling, broadcast by system information, or by a default value specified by a protocol.

[0473] In some embodiments, the specified time may include at least one of the following:

[0474] The specified time can be close to the periodic reporting period of the beam report. That is, if there is no beam failure before the next beam report, and the terminal reports the new best beam in time, the base station can update the new beam in time. Of course, this specified time can also be the beam report period + the time when the MAC CE activates the TCI state, the time when the DCI indicates the codepoint corresponding to the TCI state, and the time when the terminal sends the HARQ-ACK feedback corresponding to the DCI;

[0475] The specified time may also only include the period of the search space corresponding to the DCI format (1_1 / 1_2) that can indicate a new beam at the terminal. Because if the base station updates a new beam using DCI before the current beam fails, there will be no beam failure. Further, in addition to including the period of the search space, the specified time may also include the time corresponding to the codepoint of the TCI state indicated by the DCI + the time for the terminal to send the HARQ-ACK feedback corresponding to the DCI.

[0476] In some embodiments, when performing spatial domain beam prediction, set B is different from set A, or set B < set A. When performing temporal domain beam prediction, there is an additional case where Set B = set A.

[0477] In some embodiments, for temporal domain beam prediction, when set B < set A, the set B of multiple historical times remains unchanged, or the beams included in the set B of multiple historical times are completely different, and the set B of multiple historical times can form a set A. For example, if Set B of 4 historical events is input, each set B only includes 1 / 4 of the beams in set A, and the 4 set Bs exactly include all the beams in set A.

[0478] In some embodiments, the base station selects a beam based on probability.

[0479] Exemplarily, for example, if the terminal reports multiple beams, the base station can select a beam with a slightly lower L1-RSRP but a low beam failure probability as the current beam and indicate it to the terminal; or it can select the first beam with the highest L1-RSRP but a slightly higher beam failure probability, and then perform beam update within a short period of time afterwards, indicating the second beam with a slightly lower L1-RSRP but a beam failure probability of 0, such as updating to the second beam before the time when the first beam has a beam failure.

[0480] In the embodiments of the present disclosure, some or all of the steps and their optional implementation manners can be arbitrarily combined with some or all of the steps in other embodiments, and can also be arbitrarily combined with the optional implementation manners in other embodiments.

[0481] The embodiments of the present disclosure also propose a device for implementing any of the above methods. For example, a device is proposed. The above device includes units or modules for implementing each step performed by the terminal in any of the above methods. Again, another device is proposed, including units or modules for implementing each step performed by a network device (such as an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0482] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0483] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0484] Figure 6A is a schematic diagram of the structure of the terminal proposed in an embodiment of the present disclosure. As shown in Figure 6A, the terminal 6100 may include: at least one of a processing module 6101, a transceiver module 6102, etc. In some embodiments, the processing module is used to determine at least one reference signal resource, and the at least one reference signal resource is used for beam measurement; based on the beam measurement result of the at least one reference signal resource, a first report is determined, and the first report includes data for AI model performance monitoring, and the first AI model is used to predict beam or beam pair failure. Optionally, the processing module is used to execute at least one of the other steps (such as steps S2101 and S2102, but not limited thereto) performed by the terminal 101 in any of the above methods, which are not repeated here. In some embodiments, the transceiver module is used to send the first report. Optionally, the transceiver module is used to execute at least one of the communication steps such as sending and / or receiving (such as step S2103, but not limited thereto) performed by the terminal 101 in any of the above methods, which are not repeated here.

[0485] Figure 6B is a structural diagram of the network device proposed in an embodiment of the present disclosure. As shown in Figure 6B, the network device 6200 may include: at least one of the transceiver module 6201, etc. In some embodiments, the above-mentioned transceiver module is used to receive a first report, and the first report includes data for performance monitoring of a first AI model, and the first AI model is used for beam or beam pair failure prediction; the first report is determined by the terminal based on the beam measurement result of at least one reference signal resource. Optionally, the above-mentioned transceiver module is used to execute at least one of the communication steps such as sending and / or receiving (for example: step S2103, but not limited to this) performed by the network device 102 in any of the above methods, which will not be repeated here.

[0486] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0487] In some embodiments, the processing module can be a single module or can include multiple submodules. Optionally, the multiple submodules respectively execute all or part of the steps required to be executed by the processing module. Optionally, the processing module can be interchangeable with the processor.

[0488] Figure 7A is a schematic diagram of the structure of a communication device 7100 proposed in an embodiment of the present disclosure. Communication device 7100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), a chip, a chip system, or a processor that supports a network device to implement any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above methods. Communication device 7100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0489] As shown in Figure 7A, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. Optionally, the communication device 7100 is used to perform any of the above methods. Optionally, one or more processors 7101 are used to call instructions to enable the communication device 7100 to perform any of the above methods.

[0490] In some embodiments, the communication device 7100 further includes one or more transceivers 7102. When the communication device 7100 includes one or more transceivers 7102, the transceiver 7102 performs at least one of the communication steps such as sending and / or receiving in the above method (for example, step S2102 and step S2103, but not limited thereto), and the processor 7101 performs at least one of the other steps (for example, step S2101, but not limited thereto). In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface may be interchangeable, the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be interchangeable, and the terms receiver, receiving unit, receiver, and receiving circuit may be interchangeable.

[0491] In some embodiments, the communication device 7100 further includes one or more memories 7103 for storing data. Alternatively, all or part of the memories 7103 may be located outside the communication device 7100. In alternative embodiments, the communication device 7100 may include one or more interface circuits 7104. Optionally, the interface circuits 7104 are connected to the memories 7103 and may be configured to receive data from the memories 7103 or other devices, or to send data to the memories 7103 or other devices. For example, the interface circuits 7104 may read data stored in the memories 7103 and send the data to the processor 7101.

[0492] The communication device 7100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7A. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0493] 7B is a schematic diagram of the structure of a chip 7200 proposed in an embodiment of the present disclosure. If the communication device 7100 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 7200 shown in FIG7B , but the present disclosure is not limited thereto.

[0494] The chip 7200 includes one or more processors 7201. The chip 7200 is configured to execute any of the above methods.

[0495] In some embodiments, chip 7200 further includes one or more interface circuits 7202. Alternatively, terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 7200 further includes one or more memories 7203 for storing data. Alternatively, all or part of memory 7203 may be located external to chip 7200. Optionally, interface circuit 7202 is connected to memory 7203 and may be used to receive data from memory 7203 or other devices, or may be used to send data to memory 7203 or other devices. For example, interface circuit 7202 may read data stored in memory 7203 and send the data to processor 7201.

[0496] In some embodiments, the interface circuit 7202 performs at least one of the communication steps (e.g., step S2102 and step S2103, but not limited thereto) of the aforementioned method. The interface circuit 7202 performing the communication steps (e.g., step S2102 and step S2103, but not limited thereto) of the aforementioned method means, for example, that the interface circuit 7202 performs data exchange between the processor 7201, chip 7200, memory 7203, or a transceiver device. In some embodiments, the processor 7201 performs at least one of the other steps (e.g., step S2101, but not limited thereto).

[0497] The modules and / or devices described in various embodiments, such as virtual devices, physical devices, and chips, can be arbitrarily combined or separated according to circumstances. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0498] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 7100, the communication device 7100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a temporary storage medium.

[0499] The present disclosure also provides a program product, which, when executed by the communication device 7100, enables the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0500] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

Claims

1. A communication method, characterized in that: The method comprises: determining at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; Determine a first report based on a beam measurement result of the at least one reference signal resource, where the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for predicting beam or beam pair failure; The first report is sent.

2. The method according to claim 1, characterized in that The first report includes at least one of the following: The performance value of the first AI model; First data, where the first data is data used to calculate a performance value of the first AI model; A first event, where the first event is triggered based on a comparison result between a performance value of the first AI model and a threshold value; The first information is used to represent a model management operation.

3. The method according to claim 2, characterized in that The performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: The accuracy of prediction of beam failure or beam pair failure probability; a difference in wireless link quality, where the difference in wireless link quality is a difference between a predicted wireless link quality and a measured wireless link quality; A difference in bit error rate (BLER), wherein the difference in BLER is a difference between a predicted BLER and a measured BLER; a difference in the time of failure of a beam or a pair of beams, wherein the difference in the time of failure of a beam or a pair of beams is a difference between a predicted time of failure of a beam or a pair of beams and a measured time of failure of a beam or a pair of beams; the accuracy of the prediction of the time to failure of a beam or beams; The prediction accuracy of new beams or new beam pairs; The prediction accuracy of the beam or beam pair for which the layer 1 reference signal received power L1-RSRP difference is within a first threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; A predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of a difference in predicted L1-RSRPs, a cumulative distribution function of a difference in predicted L1-RSRPs, a proportion of predicted L1-RSRP differences less than or equal to a second threshold, and a proportion of L1-RSRP differences greater than a third threshold, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair; Terminal throughput; Reference signal overhead; Uplink control information overhead; Predict latency.

4. The method according to claim 2 or 3, characterized in that: The difference in wireless link quality includes at least one of the following: The difference between the predicted wireless link quality value within the specified time and the measured wireless link quality value within the specified time, or the difference between the minimum predicted wireless link quality value within the specified time and the minimum measured wireless link quality value within the specified time.

5. The method according to claim 2 or 3, characterized in that: The BLER difference includes at least one of the following: a difference between a BLER value predicted within a specified time and a BLER value measured within a specified time, or a difference between a maximum BLER value predicted within a specified time and a maximum BLER value measured within a specified time.

6. The method according to claim 2 or 3, characterized in that: The time difference of the failure of the beam or beam pair includes at least one of the following: a difference between the failure time of the beam or beam pair predicted within a specified time and the failure time of the beam or beam pair measured within the specified time.

7. The method according to any one of claims 2 to 6, characterized in that: The first data includes at least one of the following: In the case where the first AI model is deployed on the terminal side, the first data includes: first AI model output information and at least one of measurement information corresponding to the first AI model output information; When the first AI model is deployed on the network side, the first data includes: at least one of the first AI model input information and the measurement information corresponding to the first AI model output information.

8. The method according to claim 7, characterized in that The first AI model input information includes at least one of the following: The measured first AI model input information; Predicting current first AI model input information, wherein the predicted current first AI model input information is obtained based on the prediction of the second AI model; Predicting first AI model input information for a future time, wherein the first AI model input information for predicting a future time is obtained based on prediction by a third AI model; Specify the time; First beam quality threshold.

9. The method according to claim 7 or 8, characterized in that: The measured first AI model input information includes at least one of the following: Identifications of the best K beams or beam pairs in the first set of beams measured; The measured L1-RSRP of the best K beams or beam pairs in the first beam set; The measured layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the first beam set; The measured L1-SINR of all L beams or beam pairs in the first beam set, where L is greater than or equal to 1; The measured L1-RSRP of all L beams or beam pairs in the first beam set; The L1-RSRP of M specified beams or beam pairs in the measured first beam set, where M is an integer greater than or equal to 1, and M is less than L; The measured L1-SINRs of the specified M beams or beam pairs in the first beam set; the measured L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; The measured L1-SINR of random N beams or beam pairs in the first beam set; Identifications of random N beams or beam pairs in the first set of beams measured; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

10. The method according to claim 7 or 8, characterized in that: The predicting of the current first AI model input information includes at least one of the following: Identifications of the best K beams or beam pairs in the predicted first set of beams; The predicted L1-RSRP of the best K beams or beam pairs in the first beam set; The predicted layer 1 signal-to-interference-plus-noise ratio L1-SINR of the best K beams or beam pairs in the first beam set; The predicted L1-RSRP of all L beams or beam pairs in the first beam set; The predicted L1-RSRP of M beams or beam pairs in the first beam set, where M is an integer greater than or equal to 1, and M is less than L; The predicted L1-SINRs of the specified M beams or beam pairs in the first beam set; the predicted L1-RSRPs of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; The predicted L1-SINR of random N beams or beam pairs in the first beam set; the identities of random N beams or beam pairs in the predicted first beam set; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

11. The method according to claim 7 or 8, characterized in that: The first AI model input information or the second AI model input information includes at least one of the following: Identifications of multiple beams or beam pairs in a measured second beam set, where second beam information of the second beam set is used to be input into the first AI model, where the second beam information includes an identification, at least one of L1-RSRP and L1-SINR; The measured L1-RSRP of the plurality of beams or beam pairs in the second beam set; The measured L1-SINRs of the plurality of beams or beam pairs in the second beam set; Specify the time; A first beam quality threshold; The at least one reference signal resource is included in a second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

12. The method according to claim 7 or 8, characterized in that: The first AI model input information for predicting future time includes at least one of the following: Identifications of the predicted best K beams or beam pairs in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to at least one future time; A layer 1 signal-to-interference-plus-noise ratio L1-SINR of predicted best K beams or beam pairs in a first beam set corresponding to at least one future time; Predicting L1-SINRs of all L beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of all L beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of designated M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-SINRs of designated M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-SINRs of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Identifications of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; at least one future time corresponding to a specified time; a first beam quality threshold corresponding to at least one future time; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

13. The method according to claim 7 or 8, characterized in that: The first AI model input information or the third AI model input information includes at least one of the following: Identification of a plurality of beams or beam pairs in a second set of beams measured at a plurality of historical times; L1-RSRP of multiple beams or beam pairs in multiple second beam sets measured at multiple historical times; L1-SINRs of multiple beams or beam pairs in multiple second beam sets measured at multiple historical times; at least one future time corresponding to a specified time; a first beam quality threshold corresponding to at least one future time; The at least one reference signal resource is included in a second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

14. The method according to any one of claims 7 to 10, characterized in that The first AI model output information includes at least one of the following: The wireless link quality value at a specified time; A first probability value within a specified time, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; BLER value at a specified time; The lowest value of the wireless link quality value within a specified time; The highest BLER value within a specified time period; Beam failure time; The identifier of the new beam.

15. The method according to any one of claims 7 to 10 and 14, characterized in that: The measurement information corresponding to the output information of the first AI model includes at least one of the following: The measured value corresponding to the wireless link quality value at the specified time of measurement; The measured value corresponding to the first probability value within the specified time of measurement; The measured value corresponding to the BLER value at the specified time of measurement; The measured value corresponding to the lowest value of the wireless link quality value within the specified measured time; The measured value corresponding to the highest BLER value within the specified time period; The measured value corresponding to the measured beam failure time; The measured value corresponding to the identifier of the new beam measured.

16. The method according to claim 7 or 11, characterized in that: The first AI model output information includes at least one of the following: The wireless link quality value at a specified time; A first probability value within a specified time, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; BLER value at a specified time; The lowest value of the wireless link quality value within a specified time; The highest BLER value within a specified time period; Beam failure time; Identification of the new beam; Identification of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set.

17. The method according to any one of claims 7, 11 or 16, characterized in that: The measurement information corresponding to the output information of the first AI model includes at least one of the following: The measured value corresponding to the wireless link quality value at the specified time of measurement; The measured value corresponding to the first probability value within the specified time of measurement; The measured value corresponding to the BLER value at the specified time of measurement; The measured value corresponding to the lowest value of the wireless link quality value within the specified measured time; The measured value corresponding to the highest BLER value within the specified time period; The measured value corresponding to the measured beam failure time; The measured value corresponding to the identifier of the new beam measured; The measured values ​​corresponding to the identifiers of the best K beams or beam pairs in the first beam set measured; The measured values ​​corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; The measured values ​​corresponding to the L1-SINRs of the best K beams or beam pairs in the measured first beam set; The measured values ​​corresponding to L1-RSRP of all L beams or beam pairs in the measured first beam set; The measured values ​​corresponding to the L1-SINRs of all L beams or beam pairs in the first beam set.

18. The method according to claim 7 or 12, characterized in that: The first AI model output information includes at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; A first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a maximum value of the BLER value within a specified time corresponding to at least one future time; At least one future time corresponding to a beam failure time; The identifier of at least one new beam corresponding to a future time.

19. The method according to any one of claims 7, 13 or 18, characterized in that: The measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to a radio link quality value at a specified time corresponding to at least one future time measured; A measurement value corresponding to a first probability value within a specified time corresponding to at least one future time measured; a measured value corresponding to a BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to a lowest value of the radio link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a beam failure time corresponding to at least one future time measured; A measurement value corresponding to an identifier of a new beam corresponding to at least one future time measured.

20. The method according to claim 7 or 13, characterized in that The first AI model output information includes at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; A first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a maximum value of the BLER value within a specified time corresponding to at least one future time; At least one future time corresponding to a beam failure time; an identification of at least one new beam corresponding to a future time; Identifications of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time; L1-SINRs of all L beams or beam pairs in the first beam set corresponding to at least one future time.

21. The method according to claim 7, 13 or 20, characterized in that The measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to a radio link quality value at a specified time corresponding to at least one future time measured; A measurement value corresponding to a first probability value within a specified time corresponding to at least one future time measured; a measured value corresponding to a BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to a lowest value of the radio link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a beam failure time corresponding to at least one future time measured; a measurement value corresponding to an identifier of a new beam corresponding to at least one future time measured; The measured values ​​corresponding to the identifiers of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; A measurement value corresponding to L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; A measured value corresponding to L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; The measured values ​​corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; The measured values ​​corresponding to the L1-SINRs of all L beams or beam pairs in the first beam set corresponding to at least one future time are measured.

22. The method according to any one of claims 3 to 21, characterized in that The quality of the wireless link is determined based on at least one of the following: The signal-to-noise ratio (SNR) based on one beam; Signal-to-interference-plus-noise ratio (SINR) based on one beam; The SNR or SINR is determined based on the case where the physical downlink control channel PDCCH is received by two beams.

23. The method according to any one of claims 8 to 21, characterized in that At least one of the first beam quality threshold, the specified time, and the second beam quality threshold is determined based on at least one of the following: Radio Resource Control (RRC) signaling; Broadcast information; System information; The protocol specifies the default value.

24. The method according to claim 2, characterized in that The first information includes at least one of the following: Information for activating the first AI model; Deactivating information of the first AI model; Switching information of the first AI model; Information about falling back to non-AI mode.

25. A communication method, characterized in that: The method comprises: receiving a first report, the first report being used for performance monitoring of a first artificial intelligence (AI) model, the first AI model being used for beam or beam pair failure prediction; The first report is determined by the terminal based on a beam measurement result of at least one reference signal resource.

26. The method according to claim 25, characterized in that The first report includes at least one of the following: The performance value of the first AI model; First data, where the first data is data used to calculate a performance value of the first AI model; A first event, where the first event is triggered based on a comparison result between a performance value of the first AI model and a threshold value; The first information is used to represent a model management operation.

27. The method according to claim 26, characterized in that The performance value of the first AI model includes a value corresponding to at least one of the following performance indicators: The accuracy of prediction of beam failure or beam pair failure probability; a difference in wireless link quality, where the difference in wireless link quality is a difference between a predicted wireless link quality and a measured wireless link quality; A difference in bit error rate (BLER), wherein the difference in BLER is a difference between a predicted BLER and a measured BLER; a difference in the time of failure of a beam or a pair of beams, wherein the difference in the time of failure of a beam or a pair of beams is a difference between a predicted time of failure of a beam or a pair of beams and a measured time of failure of a beam or a pair of beams; the accuracy of the prediction of the time to failure of a beam or beams; The prediction accuracy of new beams or new beam pairs; The prediction accuracy of the beam or beam pair for which the layer 1 reference signal received power L1-RSRP difference is within a first threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; L1-RSRP difference, the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair, wherein the difference includes at least one of the following: an average value of the L1-RSRP difference, a cumulative distribution function of the L1-RSRP difference, a proportion of the L1-RSRP difference less than or equal to a second threshold, and a proportion of the L1-RSRP difference greater than a third threshold, wherein the L1-RSRP difference is the difference between the measured L1-RSRP of the best predicted beam or beam pair and the measured L1-RSRP of the best beam or beam pair; A predicted L1-RSRP difference, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair, wherein the predicted L1-RSRP difference comprises at least one of the following: an average value of a difference in predicted L1-RSRPs, a cumulative distribution function of a difference in predicted L1-RSRPs, a proportion of predicted L1-RSRP differences less than or equal to a second threshold, and a proportion of L1-RSRP differences greater than a third threshold, wherein the predicted L1-RSRP difference is a difference between a predicted L1-RSRP of a best predicted beam or beam pair and a measured L1-RSRP of the best predicted beam or beam pair; Terminal throughput; Reference signal overhead; Uplink control information overhead; Predict latency.

28. The method according to claim 26 or 27, characterized in that The difference in wireless link quality includes at least one of the following: The difference between the predicted wireless link quality value within the specified time and the measured wireless link quality value within the specified time, or the difference between the minimum predicted wireless link quality value within the specified time and the minimum measured wireless link quality value within the specified time.

29. The method according to claim 26 or 27, characterized in that The BLER difference includes at least one of the following: a difference between a BLER value predicted within a specified time and a BLER value measured within a specified time, or a difference between a maximum BLER value predicted within a specified time and a maximum BLER value measured within a specified time.

30. The method according to claim 26 or 27, characterized in that The time difference of the failure of the beam or beam pair includes at least one of the following: a difference between the failure time of the beam or beam pair predicted within a specified time and the failure time of the beam or beam pair measured within the specified time.

31. The method according to any one of claims 26 to 30, characterized in that The first data includes at least one of the following: In the case where the first AI model is deployed on the terminal side, the first data includes: first AI model output information and at least one of measurement information corresponding to the first AI model output information; When the first AI model is deployed on the network side, the first data includes: at least one of the first AI model input information and the measurement information corresponding to the first AI model output information.

32. The method according to claim 31, characterized in that The first AI model input information includes at least one of the following: The measured first AI model input information; Predicting current first AI model input information, wherein the predicted current first AI model input information is obtained based on the prediction of the second AI model; Predicting first AI model input information for a future time, wherein the first AI model input information for predicting a future time is obtained based on prediction by a third AI model; Specify the time; First beam quality threshold.

33. The method according to claim 31 or 32, characterized in that The measured first AI model input information includes at least one of the following: Identifications of the best K beams or beam pairs in the first set of beams measured; The measured L1-RSRP of the best K beams or beam pairs in the first beam set; The measured layer 1 signal-to-interference-and-noise ratio L1-SINR of the best K beams or beam pairs in the first beam set; The measured L1-SINR of all L beams or beam pairs in the first beam set, where L is greater than or equal to 1; The measured L1-RSRP of all L beams or beam pairs in the first beam set; The L1-RSRP of M specified beams or beam pairs in the measured first beam set, where M is an integer greater than or equal to 1, and M is less than L; The measured L1-SINRs of the specified M beams or beam pairs in the first beam set; the measured L1-RSRP of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; The measured L1-SINR of random N beams or beam pairs in the first beam set; Identifications of random N beams or beam pairs in the first set of beams measured; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

34. The method according to claim 31 or 32, characterized in that The predicting of the current first AI model input information includes at least one of the following: Identifications of the best K beams or beam pairs in the predicted first set of beams; The predicted L1-RSRP of the best K beams or beam pairs in the first beam set; The predicted layer 1 signal-to-interference-plus-noise ratio L1-SINR of the best K beams or beam pairs in the first beam set; The predicted L1-RSRP of all L beams or beam pairs in the first beam set; The predicted L1-RSRP of M beams or beam pairs in the first beam set, where M is an integer greater than or equal to 1, and M is less than L; The predicted L1-SINRs of the specified M beams or beam pairs in the first beam set; the predicted L1-RSRPs of random N beams or beam pairs in the first beam set, where N is an integer greater than or equal to 1, and N is less than L; The predicted L1-SINR of random N beams or beam pairs in the first beam set; the identities of random N beams or beam pairs in the predicted first beam set; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

35. The method according to claim 31 or 32, characterized in that The first AI model input information includes at least one of the following: Identifications of multiple beams or beam pairs in a measured second beam set, where second beam information of the second beam set is used to be input into the first AI model, where the second beam information includes an identification, at least one of L1-RSRP and L1-SINR; The measured L1-RSRP of the plurality of beams or beam pairs in the second beam set; The measured L1-SINRs of the plurality of beams or beam pairs in the second beam set; Specify the time; A first beam quality threshold; The at least one reference signal resource is included in a second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

36. The method according to claim 31 or 32, characterized in that The first AI model input information for predicting future time includes at least one of the following: Identifications of the predicted best K beams or beam pairs in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to at least one future time; A layer 1 signal-to-interference-plus-noise ratio L1-SINR of predicted best K beams or beam pairs in a first beam set corresponding to at least one future time; Predicting L1-SINRs of all L beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of all L beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of designated M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-SINRs of designated M beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-RSRPs of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Predicting L1-SINRs of random N beams or beam pairs in the first beam set in the first beam set corresponding to at least one future time; Identifications of random N beams or beam pairs in the first beam set predicted in the first beam set corresponding to at least one future time; at least one future time corresponding to a specified time; a first beam quality threshold corresponding to at least one future time; The at least one reference signal resource is included in a first reference signal resource set, and the first beam set is determined based on the first reference signal resource set.

37. The method according to claim 31 or 32, characterized in that The first AI model input information or the third AI model input information includes at least one of the following: Identification of a plurality of beams or beam pairs in a second set of beams measured at a plurality of historical times; L1-RSRP of multiple beams or beam pairs in multiple second beam sets measured at multiple historical times; L1-SINRs of multiple beams or beam pairs in multiple second beam sets measured at multiple historical times; at least one future time corresponding to a specified time; a first beam quality threshold corresponding to at least one future time; The at least one reference signal resource is included in a second reference signal resource set, and the second beam set is determined based on the second reference signal resource set.

38. The method according to any one of claims 31 to 34, characterized in that The first AI model output information includes at least one of the following: The wireless link quality value at a specified time; A first probability value within a specified time, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; BLER value at a specified time; The lowest value of the wireless link quality value within a specified time; The highest BLER value within a specified time period; Beam failure time; The identifier of the new beam.

39. The method according to any one of claims 31 to 34 and 38, characterized in that The measurement information corresponding to the output information of the first AI model includes at least one of the following: The measured value corresponding to the wireless link quality value at the specified time of measurement; The measured value corresponding to the first probability value within the specified time of measurement; The measured value corresponding to the BLER value at the specified time of measurement; The measured value corresponding to the lowest value of the wireless link quality value within the specified measured time; The measured value corresponding to the highest BLER value within the specified time period; The measured value corresponding to the measured beam failure time; The measured value corresponding to the identifier of the new beam measured.

40. The method according to claim 31 or 35, characterized in that The first AI model output information includes at least one of the following: The wireless link quality value at a specified time; A first probability value within a specified time, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; BLER value at a specified time; The lowest value of the wireless link quality value within a specified time; The highest BLER value within a specified time period; Beam failure time; Identification of the new beam; Identification of the best K beams or beam pairs in the first beam set; L1-RSRP of the best K beams or beam pairs in the first beam set; L1-SINR of the best K beams or beam pairs in the first beam set; L1-RSRP of all L beams or beam pairs in the first beam set; L1-SINR of all L beams or beam pairs in the first beam set.

41. The method according to claim 31, 35 or 40, characterized in that The measurement information corresponding to the output information of the first AI model includes at least one of the following: The measured value corresponding to the wireless link quality value at the specified time of measurement; The measured value corresponding to the first probability value within the specified time of measurement; The measured value corresponding to the BLER value at the specified time of measurement; The measured value corresponding to the lowest value of the wireless link quality value within the specified measured time; The measured value corresponding to the highest BLER value within the specified time period; The measured value corresponding to the measured beam failure time; The measured value corresponding to the identifier of the new beam measured; The measured values ​​corresponding to the identifiers of the best K beams or beam pairs in the first beam set measured; The measured values ​​corresponding to the L1-RSRP of the best K beams or beam pairs in the measured first beam set; The measured values ​​corresponding to the L1-SINRs of the best K beams or beam pairs in the measured first beam set; The measured values ​​corresponding to L1-RSRP of all L beams or beam pairs in the measured first beam set; The measured values ​​corresponding to the L1-SINRs of all L beams or beam pairs in the first beam set.

42. The method according to claim 31 or 36, characterized in that The first AI model output information includes at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; A first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a maximum value of the BLER value within a specified time corresponding to at least one future time; At least one future time corresponding to a beam failure time; The identifier of at least one new beam corresponding to a future time.

43. The method according to claim 31, 36 or 42, characterized in that The measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to a radio link quality value at a specified time corresponding to at least one future time measured; A measurement value corresponding to a first probability value within a specified time corresponding to at least one future time measured; a measured value corresponding to a BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to a lowest value of the radio link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a beam failure time corresponding to at least one future time measured; A measurement value corresponding to an identifier of a new beam corresponding to at least one future time measured.

44. The method according to claim 31 or 37, characterized in that The first AI model output information includes at least one of the following: a wireless link quality value at a specified time corresponding to at least one future time; A first probability value within a specified time corresponding to at least one future time, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; a BLER value at a specified time corresponding to at least one future time; a lowest value of the wireless link quality value within a specified time corresponding to at least one future time; a maximum value of the BLER value within a specified time corresponding to at least one future time; At least one future time corresponding to a beam failure time; an identification of at least one new beam corresponding to a future time; Identifications of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to at least one future time; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time; L1-SINRs of all L beams or beam pairs in the first beam set corresponding to at least one future time.

45. The method of claim 31, 37 or 44, wherein: The measurement information corresponding to the output information of the first AI model includes at least one of the following: a measurement value corresponding to a radio link quality value at a specified time corresponding to at least one future time measured; A measurement value corresponding to a first probability value within a specified time corresponding to at least one future time measured; a measured value corresponding to a BLER value at a specified time corresponding to at least one future time measured; a measurement value corresponding to a lowest value of the radio link quality value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a highest value of the BLER value within a specified time corresponding to at least one future time measured; a measurement value corresponding to a beam failure time corresponding to at least one future time measured; a measurement value corresponding to an identifier of a new beam corresponding to at least one future time measured; The measured values ​​corresponding to the identifiers of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; A measurement value corresponding to L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; A measured value corresponding to L1-SINR of the best K beams or beam pairs in the first beam set corresponding to at least one future time measured; The measured values ​​corresponding to the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to at least one future time measured; The measured values ​​corresponding to the L1-SINRs of all L beams or beam pairs in the first beam set corresponding to at least one future time are measured.

46. ​​The method according to any one of claims 27 to 45, characterized in that The quality of the wireless link is determined based on at least one of the following: The signal-to-noise ratio (SNR) based on one beam; Signal-to-interference-plus-noise ratio (SINR) based on one beam; The SNR or SINR is determined based on the case where the physical downlink control channel PDCCH is received by two beams.

47. The method according to any one of claims 28 to 45, characterized in that At least one of the first beam quality threshold, the specified time, and the second beam quality threshold is determined based on at least one of the following: Radio Resource Control (RRC) signaling; Broadcast information; System information; The protocol specifies the default value.

48. The method according to claim 26, characterized in that The first information includes at least one of the following: Information for activating the first AI model; Deactivating information of the first AI model; Switching information of the first AI model; Information about falling back to non-AI mode.

49. A communication method, characterized in that: The method includes: a terminal determines at least one reference signal resource, and the at least one reference signal resource is used for beam measurement; based on the beam measurement result of the at least one reference signal resource, a first report is determined, and the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used to predict beam or beam pair failure; and the first report is sent to a network device.

50. A terminal, characterized in that: include: A processing module, configured to determine at least one reference signal resource, wherein the at least one reference signal resource is used for beam measurement; Determine a first report based on a beam measurement result of the at least one reference signal resource, where the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for predicting beam or beam pair failure; A transceiver module is used to send the first report.

51. A network device, characterized in that: include: A transceiver module, configured to receive a first report, wherein the first report is used for performance monitoring of a first artificial intelligence (AI) model, and the first AI model is used for beam or beam pair failure prediction; The first report is determined by the terminal based on a beam measurement result of at least one reference signal resource.

52. A terminal, characterized in that: include: one or more processors; The processor is used to execute the communication method according to any one of claims 1 to 24.

53. A network device, characterized in that: include: one or more processors; The processor is used to execute the communication method described in any one of claims 25 to 48.

54. A communication system, characterized in that: It comprises a terminal and a network device, wherein the terminal is configured to implement the communication method according to any one of claims 1 to 24, and the network device is configured to implement the communication method according to any one of claims 25 to 48.

55. A storage medium storing instructions, characterized in that: When the instruction is executed on a communication device, the communication device is caused to execute the communication method according to any one of claims 1 to 24 or 25 to 48.

Images