Communication method and system, and device and storage medium

Abstract

The present disclosure relates to a communication method and system, and a device and a storage medium. The method comprises: determining a reference signal resource, wherein the reference signal resource is used for performing beam measurement; on the basis of a beam measurement result of the reference signal resource, determining first information, wherein the first information comprises at least one piece of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, the first AI model being used for performing beam failure prediction or beam pair failure prediction; and sending the first information. Therefore, beam failure prediction is performed on the basis of an AI model, so as to generate beam or beam pair failure information, such that a network device can better select beams for communication transmission on the basis of the information, thus reducing the probability of beam failure.

Description

Communication method, device, system and storage medium Technical Field

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

[0002] During NR (New Radio) communication, especially when the communication frequency band is in frequency range 2 (millimeter wave band, frequency range: 24.25GHz-52.6GHz, maximum channel bandwidth 400MHz), due to the rapid attenuation of high-frequency channels, beam-based transmission and reception are required to ensure coverage. In the beam management process of related technologies, the base station configures a reference signal resource set for beam measurement. The terminal measures the reference signal resources in the reference signal resource set and then reports the IDs of the strongest X reference signal resources and the corresponding L1 (physical layer)-RSRP (Reference Signal Receiving Power) and / or L1 (physical layer)-SINR (Signal to Interference plus Noise Ratio).

[0003] Summary of the Invention

[0004] In order to overcome the technical problem of decreased communication performance in related technologies, the present disclosure provides a communication method, device, system and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a first device. The method includes:

[0006] determining a reference signal resource for performing beam measurement;

[0007] determining, based on a beam measurement result of the reference signal resource, first information including at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction;

[0008] The first information is sent.

[0009] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a second device. The method includes:

[0010] Receive first information, where the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0011] According to a third aspect of an embodiment of the present disclosure, there is provided a first device, including:

[0012] an execution module, configured to determine a reference signal resource, where the reference signal resource is used for beam measurement;

[0013] a processing module configured to determine first information based on a beam measurement result of the reference signal resource, the first information comprising at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction;

[0014] The transceiver module is configured to send the first information.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a second device is provided, including:

[0016] The transceiver module is configured to receive first information, where the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0017] According to a fifth aspect of an embodiment of the present disclosure, there is provided a first device, including:

[0018] one or more processors;

[0019] The first device is used to execute the communication method described in any one of the first aspects above.

[0020] According to a sixth aspect of an embodiment of the present disclosure, a second device is provided, including:

[0021] one or more processors;

[0022] The second device is used to execute the communication method described in any one of the second aspects of the embodiments of this disclosure.

[0023] According to the seventh aspect of an embodiment of the present disclosure, a communication system is provided, including a first device and a second device, wherein the first device is configured to implement the communication method described in any one of the first aspects of the present disclosure, and the second device is configured to implement the communication method described in any one of the second aspects of the present disclosure.

[0024] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is provided, which stores instructions. When the instructions are executed on a communication device, the communication device executes the communication method as described in any one of the first aspect and the second aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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.

[0026] FIG1 is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0027] FIG2 is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure.

[0028] FIG3 is a flowchart showing a communication method according to an embodiment of the present disclosure.

[0029] FIG4 is a flowchart showing a communication method according to an embodiment of the present disclosure.

[0030] FIG5 is a flowchart showing a communication method according to an embodiment of the present disclosure.

[0031] FIG6 is a schematic structural diagram of a first device proposed in an embodiment of the present disclosure.

[0032] FIG7 is a schematic structural diagram of a second device proposed in an embodiment of the present disclosure.

[0033] FIG8 is a schematic structural diagram of a network device 8100 proposed in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] The embodiments of the present disclosure provide a communication method, device, system, and storage medium.

[0035] In a first aspect, an embodiment of the present disclosure provides a communication method, which is performed by a first device. The method includes:

[0036] determining a reference signal resource for performing beam measurement;

[0037] determining, based on a beam measurement result of the reference signal resource, first information including at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction;

[0038] The first information is sent.

[0039] In the above technical solution, a first device determines a reference signal resource, which is used for beam measurement. Based on the beam measurement results of the reference signal resource, the device determines first information, which includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information. The first AI model is used to predict beam failure or beam pair failure and transmits the first information. Beam failure prediction based on the AI ​​model generates beam or beam pair failure information, enabling network devices to better select beams for communication transmission based on this information, thereby reducing the probability of beam failure.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, the input information includes at least one of the following:

[0041] first input information determined by measurement;

[0042] Second input information, where the second input information is determined by predicting the input information of the first AI model at the current time using a second AI model;

[0043] third input information, where the third input information is determined by predicting the input information of the first AI model at a future time using a third AI model;

[0044] A specified time, where the specified time is used to indicate a time for performing the beam failure prediction or the beam pair failure prediction;

[0045] a first quality threshold, where the first quality threshold is used to indicate a determination condition of a beam failure or a beam pair failure;

[0046] A second quality threshold is used to determine a decision condition for a new beam.

[0047] In conjunction with some embodiments of the first aspect, in some embodiments, the first input information includes at least one of the following:

[0048] Identifications of best K beams or beam pairs in a first beam set determined by measurement, the first beam set being determined based on a first reference signal resource set including the reference signal resources;

[0049] Physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measurement;

[0050] A physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by measurement;

[0051] L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement, where L is an integer greater than or equal to 1;

[0052] L1-RSRPs of all L beams or beam pairs in the first beam set determined by measurement;

[0053] L1-RSRPs of designated M beams or beam pairs in the first beam set determined by measurement, where M is an integer greater than or equal to 1;

[0054] L1-SINRs of the designated M beams or beam pairs determined by measurement;

[0055] L1-RSRPs of any N beams or beam pairs in the first beam set determined through measurement, where N is an integer greater than or equal to 1, and N is less than L;

[0056] L1-SINRs of the arbitrary N beams or beam pairs determined by measurement;

[0057] The identities of the arbitrary N beams or beam pairs are determined by measurements.

[0058] In conjunction with some embodiments of the first aspect, in some embodiments, the second input information includes at least one of the following:

[0059] Identities of best K beams or beam pairs in a first beam set determined by prediction, the first beam set being determined based on a first reference signal resource set, the reference signal resource set including the reference signal resource;

[0060] Physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by prediction;

[0061] A physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by prediction;

[0062] L1-SINRs of all L beams or beam pairs in the first beam set determined by prediction;

[0063] L1-RSRPs of all L beams or beam pairs in the first beam set determined by prediction;

[0064] L1-RSRPs of M beams or beam pairs specified in the first beam set determined by prediction, where M is an integer greater than or equal to 1;

[0065] L1-SINRs of the designated M beams or beam pairs determined by prediction;

[0066] L1-RSRPs of any N beams or beam pairs in the first beam set determined by prediction, where N is an integer greater than or equal to 1 and N is less than L;

[0067] L1-SINRs of the arbitrary N beams or beam pairs determined by prediction;

[0068] The identities of the arbitrary N beams or beam pairs are determined by prediction.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, the first input information or the input information of the second AI model includes at least one of the following:

[0070] Identifiers of multiple beams or beam pairs in a second beam set determined by measurement, wherein second beam information of the second beam set is used to be input into the first AI model, wherein the second beam information includes an identifier and at least one of an L1-RSRP and an L1-SINR, and the second beam set includes the reference signal resource;

[0071] L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measurement;

[0072] L1-SINRs of multiple beams or beam pairs in the second beam set determined through measurement.

[0073] In conjunction with some embodiments of the first aspect, in some embodiments, the third input information includes at least one of the following:

[0074] identifiers of predicted best K beams or beam pairs in a first beam set corresponding to the future time, where the first beam set is determined based on a first reference signal resource set, and the first reference signal resource set includes the reference signal resources;

[0075] L1-RSRPs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time;

[0076] L1-SINRs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time;

[0077] Predicting L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time;

[0078] L1-RSRPs of all L beams or beam pairs in the predicted first beam set corresponding to the future time;

[0079] L1-RSRPs of the predicted M beams or beam pairs in the first beam set corresponding to the future time, where M is an integer greater than or equal to 1;

[0080] the predicted L1-SINRs of the specified M beams or beam pairs in the first beam set corresponding to the future time;

[0081] The predicted L1-RSRPs of any N beams or beam pairs in the first beam set corresponding to the future time, where N is an integer greater than or equal to 1 and is less than L;

[0082] The predicted L1-SINRs of any N beams or beam pairs in the first beam set corresponding to the future time;

[0083] The identifiers of any N beams or beam pairs in the predicted first beam set in the first beam set corresponding to the future time.

[0084] In conjunction with some embodiments of the first aspect, in some embodiments, the first input information or the input information of the third AI model includes at least one of the following:

[0085] Identifications of a plurality of beams or beam pairs in a second beam set determined by measurements at a plurality of historical times;

[0086] L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measurement during the multiple historical times;

[0087] L1-SINRs of multiple beams or beam pairs in the second beam set determined by measurement during the multiple historical times;

[0088] The second beam set is determined based on a second reference signal resource set, and the second reference signal resource set includes the reference signal resources.

[0089] In conjunction with some embodiments of the first aspect, in some embodiments, the output information includes at least one of the following:

[0090] a radio link quality value of a first beam at a first time, where the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time;

[0091] a first probability value of the first beam in a first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0092] a block error rate (BLER) value of the first beam at the first time;

[0093] a first minimum radio link quality value, where the first minimum radio link quality value is the lowest radio link quality value of the first beam in the first period;

[0094] a first highest BLER value, where the first highest BLER value is a highest BLER value of the first beam in the first period;

[0095] a beam failure time of the first beam;

[0096] The identifier of the new beam.

[0097] In conjunction with some embodiments of the first aspect, in some embodiments, the output information further includes at least one of the following:

[0098] Identification of the best K beams or beam pairs in the first beam set;

[0099] L1-RSRP of the best K beams or beam pairs in the first beam set;

[0100] L1-SINR of the best K beams or beam pairs in the first beam set;

[0101] L1-RSRP of all L beams or beam pairs in the first beam set;

[0102] L1-SINR of all L beams or beam pairs in the first beam set.

[0103] In conjunction with some embodiments of the first aspect, in some embodiments, the output information includes at least one of the following:

[0104] a radio link quality value of a first beam at a first time in the future time, where the first beam at the future time is the best K beams or beam pairs at the future time determined by measurement or prediction;

[0105] a first probability value of the first beam at the future time within the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0106] a BLER value of the first beam at the future time at the first time;

[0107] a second minimum radio link quality value, where the second minimum radio link quality value is the lowest radio link quality value of the first beam at the future time within the first period;

[0108] a second highest BLER value, where the second highest radio link quality value is the highest BLER value of the first beam at the future time within the first period;

[0109] a beam failure time corresponding to the first beam at the future time;

[0110] The identifier of the new beam corresponding to the future time.

[0111] In conjunction with some embodiments of the first aspect, in some embodiments, the output information includes at least one of the following:

[0112] Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0113] L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0114] L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0115] L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time;

[0116] L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time.

[0117] In conjunction with some embodiments of the first aspect, in some embodiments, the measurement information includes at least one of the following:

[0118] a radio link quality value of the first beam at a first time determined by measurement;

[0119] a first probability value of the first beam in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0120] a BLER value of the first beam at the first time determined by measurement;

[0121] a lowest value of the radio link quality value of the first beam determined by measurement within the first period;

[0122] a highest BLER value of the first beam in the first period determined by measurement;

[0123] a beam failure time of the first beam determined by measurement;

[0124] The identification of the new beam determined by measurements;

[0125] Identifications of the best K beams or beam pairs in the first set of beams determined by measurements;

[0126] L1-RSRP of the best K beams or beam pairs in the first beam set determined by measurement;

[0127] L1-SINRs of the best K beams or beam pairs in the first beam set determined by measurement;

[0128] L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement;

[0129] The L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement.

[0130] In conjunction with some embodiments of the first aspect, in some embodiments, the measurement information includes at least one of the following:

[0131] a radio link quality value of a first beam at a first time at a future time determined by measurement;

[0132] a first probability value of the first beam at the future time within a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0133] a BLER value of the first beam at the first time at the future time determined by measurement;

[0134] a lowest value of the radio link quality value of the first beam at the future time determined by measurement within the first period;

[0135] a highest BLER value of the first beam at the future time within the first period determined by measurement;

[0136] a beam failure time of the first beam at the future time determined by measurement;

[0137] an identifier of a new beam corresponding to the future time determined by measurement;

[0138] Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0139] L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0140] L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0141] L1-RSRPs of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0142] The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time are determined through measurement.

[0143] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0144] Determining a wireless link quality value, where determining the wireless link quality value includes at least one of the following:

[0145] The signal-to-noise ratio (SNR) determined based on a beam;

[0146] SINR determined based on one beam;

[0147] The SNR or SINR is determined based on information about the physical downlink control channel (PDCCH) received by two beams.

[0148] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0149] The specified time, future time, first time, first period, first quality threshold, or second quality threshold is determined by at least one of the following methods:

[0150] Determined by radio resource control protocol RRC signaling;

[0151] Determined based on broadcast information or system information;

[0152] Determined based on default rule information.

[0153] In a second aspect, an embodiment of the present disclosure provides a communication method, which is performed by a second device. The method includes:

[0154] Receive first information, where the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0155] In conjunction with some embodiments of the second aspect, in some embodiments, the input information includes at least one of the following:

[0156] first input information determined by measurement;

[0157] Second input information, where the second input information is determined by predicting the input information of the first AI model at the current time using a second AI model;

[0158] third input information, where the third input information is determined by predicting the input information of the first AI model at a future time using a third AI model;

[0159] A specified time, where the specified time is used to indicate a time for performing the beam failure prediction or the beam pair failure prediction;

[0160] a first quality threshold, where the first quality threshold is used to indicate a determination condition of a beam failure or a beam pair failure;

[0161] A second quality threshold is used to determine a decision condition for a new beam.

[0162] In conjunction with some embodiments of the second aspect, in some embodiments, the first input information includes at least one of the following:

[0163] Identifications of best K beams or beam pairs in a first beam set determined by measurement, the first beam set being determined based on a first reference signal resource set including the reference signal resources;

[0164] Physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measurement;

[0165] A physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by measurement;

[0166] L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement, where L is an integer greater than or equal to 1;

[0167] L1-RSRPs of all L beams or beam pairs in the first beam set determined by measurement;

[0168] L1-RSRPs of designated M beams or beam pairs in the first beam set determined by measurement, where M is an integer greater than or equal to 1;

[0169] L1-SINRs of the designated M beams or beam pairs determined by measurement;

[0170] L1-RSRPs of any N beams or beam pairs in the first beam set determined through measurement, where N is an integer greater than or equal to 1, and N is less than L;

[0171] L1-SINRs of the arbitrary N beams or beam pairs determined by measurement;

[0172] The identities of the arbitrary N beams or beam pairs are determined by measurements.

[0173] In conjunction with some embodiments of the second aspect, in some embodiments, the second input information includes at least one of the following:

[0174] Physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by prediction;

[0175] A physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by prediction;

[0176] L1-SINRs of all L beams or beam pairs in the first beam set determined by prediction;

[0177] L1-RSRPs of all L beams or beam pairs in the first beam set determined by prediction;

[0178] L1-RSRPs of M beams or beam pairs specified in the first beam set determined by prediction, where M is an integer greater than or equal to 1;

[0179] L1-SINRs of the designated M beams or beam pairs determined by prediction;

[0180] L1-RSRPs of any N beams or beam pairs in the first beam set determined by prediction, where N is an integer greater than or equal to 1 and N is less than L;

[0181] L1-SINRs of the arbitrary N beams or beam pairs determined by prediction;

[0182] The identities of the arbitrary N beams or beam pairs are determined by prediction.

[0183] In conjunction with some embodiments of the second aspect, in some embodiments, the first input information or the input information of the second AI model includes at least one of the following:

[0184] Identifiers of multiple beams or beam pairs in a second beam set determined by measurement, wherein second beam information of the second beam set is used to be input into the first AI model, wherein the second beam information includes an identifier and at least one of an L1-RSRP and an L1-SINR, and the second beam set includes the reference signal resource;

[0185] L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measurement;

[0186] L1-SINRs of multiple beams or beam pairs in the second beam set determined through measurement.

[0187] In conjunction with some embodiments of the second aspect, in some embodiments, the third input information includes at least one of the following:

[0188] identifiers of predicted best K beams or beam pairs in a first beam set corresponding to the future time, where the first beam set is determined based on a first reference signal resource set, and the first reference signal resource set includes the reference signal resources;

[0189] L1-RSRPs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time;

[0190] L1-SINRs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time;

[0191] Predicting L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time;

[0192] L1-RSRPs of all L beams or beam pairs in the predicted first beam set corresponding to the future time;

[0193] L1-RSRPs of the predicted M beams or beam pairs in the first beam set corresponding to the future time, where M is an integer greater than or equal to 1;

[0194] the predicted L1-SINRs of the specified M beams or beam pairs in the first beam set corresponding to the future time;

[0195] The predicted L1-RSRPs of any N beams or beam pairs in the first beam set corresponding to the future time, where N is an integer greater than or equal to 1 and is less than L;

[0196] The predicted L1-SINRs of any N beams or beam pairs in the first beam set corresponding to the future time;

[0197] The identifiers of any N beams or beam pairs in the predicted first beam set in the first beam set corresponding to the future time.

[0198] In conjunction with some embodiments of the second aspect, in some embodiments, the first input information or the input information of the third AI model includes at least one of the following:

[0199] Identifications of a plurality of beams or beam pairs in a second beam set determined by measurements at a plurality of historical times;

[0200] L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measurement during the multiple historical times;

[0201] L1-SINRs of multiple beams or beam pairs in the second beam set determined by measurement during the multiple historical times;

[0202] The second beam set is determined based on a second reference signal resource set, and the second reference signal resource set includes the reference signal resources.

[0203] In conjunction with some embodiments of the second aspect, in some embodiments, the output information includes at least one of the following:

[0204] a radio link quality value of a first beam at a first time, where the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time;

[0205] a first probability value of the first beam in a first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0206] a block error rate (BLER) value of the first beam at the first time;

[0207] a first minimum radio link quality value, where the first minimum radio link quality value is the lowest radio link quality value of the first beam in the first period;

[0208] a first highest BLER value, where the first highest BLER value is a highest BLER value of the first beam in the first period;

[0209] a beam failure time of the first beam;

[0210] The identifier of the new beam.

[0211] In conjunction with some embodiments of the second aspect, in some embodiments, the output information further includes at least one of the following:

[0212] Identification of the best K beams or beam pairs in the first beam set;

[0213] L1-RSRP of the best K beams or beam pairs in the first beam set;

[0214] L1-SINR of the best K beams or beam pairs in the first beam set;

[0215] L1-RSRP of all L beams or beam pairs in the first beam set;

[0216] L1-SINR of all L beams or beam pairs in the first beam set.

[0217] In conjunction with some embodiments of the second aspect, in some embodiments, the output information includes at least one of the following:

[0218] a radio link quality value of a first beam at a first time in the future time, where the first beam at the future time is the best K beams or beam pairs at the future time determined by measurement or prediction;

[0219] a first probability value of the first beam at the future time within the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0220] a BLER value of the first beam at the future time at the first time;

[0221] a second minimum radio link quality value, where the second minimum radio link quality value is the lowest radio link quality value of the first beam at the future time within the first period;

[0222] a second highest BLER value, where the second highest radio link quality value is the highest BLER value of the first beam at the future time within the first period;

[0223] a beam failure time corresponding to the first beam at the future time;

[0224] The identifier of the new beam corresponding to the future time.

[0225] In conjunction with some embodiments of the second aspect, in some embodiments, the output information includes at least one of the following:

[0226] Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0227] L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0228] L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0229] L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time;

[0230] L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time.

[0231] In conjunction with some embodiments of the second aspect, in some embodiments, the measurement information includes at least one of the following:

[0232] a radio link quality value of the first beam at a first time determined by measurement;

[0233] a first probability value of the first beam in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0234] a BLER value of the first beam at the first time determined by measurement;

[0235] a lowest value of the radio link quality value of the first beam determined by measurement within the first period;

[0236] a highest BLER value of the first beam in the first period determined by measurement;

[0237] a beam failure time of the first beam determined by measurement;

[0238] The identification of the new beam determined by measurements;

[0239] Identifications of the best K beams or beam pairs in the first set of beams determined by measurements;

[0240] L1-RSRP of the best K beams or beam pairs in the first beam set determined by measurement;

[0241] L1-SINRs of the best K beams or beam pairs in the first beam set determined by measurement;

[0242] L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement;

[0243] The L1-SINRs of all L beams or beam pairs in the first beam set are determined by measurement.

[0244] In conjunction with some embodiments of the second aspect, in some embodiments, the measurement information includes at least one of the following:

[0245] a radio link quality value of a first beam at a first time at a future time determined by measurement;

[0246] a first probability value of the first beam at the future time within a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0247] a BLER value of the first beam at the first time at the future time determined by measurement;

[0248] a lowest value of the radio link quality value of the first beam at the future time determined by measurement within the first period;

[0249] a highest BLER value of the first beam at the future time within the first period determined by measurement;

[0250] a beam failure time of the first beam at the future time determined by measurement;

[0251] an identifier of a new beam corresponding to the future time determined by measurement;

[0252] Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0253] L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0254] L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0255] L1-RSRPs of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0256] The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time are determined through measurement.

[0257] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0258] Determining a wireless link quality value, where determining the wireless link quality value includes at least one of the following:

[0259] The signal-to-noise ratio (SNR) determined based on a beam;

[0260] SINR determined based on one beam;

[0261] The SNR or SINR is determined based on information about the physical downlink control channel (PDCCH) received by two beams.

[0262] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0263] The specified time, future time, first time, first period, first quality threshold, or second quality threshold is determined by at least one of the following methods:

[0264] Determined by radio resource control protocol RRC signaling;

[0265] Determined based on broadcast information or system information;

[0266] Determined based on default rule information.

[0267] In a third aspect, an embodiment of the present disclosure provides a first device, including:

[0268] an execution module, configured to determine a reference signal resource, where the reference signal resource is used for beam measurement;

[0269] a processing module configured to determine first information based on a beam measurement result of the reference signal resource, the first information comprising at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction;

[0270] The transceiver module is configured to send the first information.

[0271] In a fourth aspect, an embodiment of the present disclosure provides a second device, including:

[0272] The transceiver module is configured to receive first information, where the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0273] In a fifth aspect, an embodiment of the present disclosure provides a first device, including:

[0274] one or more processors;

[0275] The first device is used to execute the communication method described in any one of the first aspects of the embodiments of this disclosure.

[0276] According to a sixth aspect, a second device includes:

[0277] one or more processors;

[0278] The second device is used to execute the communication method described in any one of the second aspects of the embodiments of this disclosure.

[0279] In the seventh aspect, an embodiment of the present disclosure provides a communication system, comprising a first device and a second device, wherein the first device is configured to implement the communication method described in any one of the first aspects of the embodiment of the present disclosure, and the second device is configured to implement the communication method described in any one of the second aspects of the embodiment of the present disclosure.

[0280] In an eighth aspect, an embodiment of the present disclosure provides a storage medium storing instructions, which, when the instructions are executed on a communication device, enables the communication device to execute a communication method as described in any one of the first aspect of the embodiment of the present disclosure and the second aspect of the embodiment of the present disclosure.

[0281] It is understandable that the first device, the second device, the communication system, the storage medium, the program product, the computer program, the chip, or the chip system described above are all used to perform the method 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 and will not be repeated here.

[0282] In some embodiments, the terms "communication method," "information processing method," and "communication method" are interchangeable; "communication device," "information processing device," and "communication device" are interchangeable; and "information processing system," "communication system," and "communication system" are interchangeable.

[0283] 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.

[0284] 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.

[0285] 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.

[0286] 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.

[0287] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0288] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0289] 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.

[0290] 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.

[0291] 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.

[0292] 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.

[0293] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0294] 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.

[0295] 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.

[0296] 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.

[0297] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0298] 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.

[0299] 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.

[0300] 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.

[0301] 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.

[0302] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0303] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0304] 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.

[0305] FIG1 is a schematic diagram of 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 , an access network device 102 , and a core network device 103 .

[0306] 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.

[0307] 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.

[0308] 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.

[0309] 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.

[0310] 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.

[0311] 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).

[0312] In related technologies, a base station configures a reference signal resource set containing X reference signals, each corresponding to a different base station transmit beam. For each reference signal, a terminal must use all receive beams to measure the reference signal, obtain the beam measurement quality corresponding to all receive beams, and determine the optimal beam measurement quality. Therefore, the number of beam pairs that the terminal needs to measure is M*N, where M is the number of base station transmit beams and N is the number of terminal receive beams.

[0313] In some implementations, in order to reduce the number of beam pairs measured by the terminal, a prediction method based on an AI model is proposed. For example, if the total number of beam pairs that the terminal needs to measure is M*N (where M is the number of beams transmitted by the base station and N is the number of beams received by the terminal), when beam measurement is performed based on the AI ​​model, the number of beam measurements can be reduced through beam prediction. The beam prediction of the AI ​​model may include:

[0314] (1) For spatial beam prediction, if the prediction is based on beam pairs, the terminal only needs to measure a portion of the M*N beam pairs, such as 1 / 8 beams, 1 / 4 beams, etc. in M*N, and then input the measured beam measurement quality of these beam pairs into the AI ​​model, and the AI ​​model can output the beam information of the M*N beam pairs. If the prediction is based on the transmit beam, the terminal only needs to measure a portion of the M beam pairs, such as 1 / 8 beams, 1 / 4 beams, etc. in M, and then input the measured beam measurement quality of these beams into the AI ​​model, and the AI ​​model can output the beam information of the M beams.

[0315] (2) For time-domain beam prediction, the terminal can measure the beam quality of the beam or beam pair at historical time to predict the beam information of the beam or beam pair at future time.

[0316] In some embodiments, it is proposed to predict the beam measurement results of a specified beam or beam pair based on an AI model, including spatial domain beam prediction (predicting beam B based on beam group A): predicting the measurement results of the beams in set A based on the measurement results of the beams in set B. And time domain beam prediction (predicting the beam measurement results of future beams based on the beam measurement results of historical beams): predicting the beams of set A in the future based on the measurement results of set B in the historical time. The relationship between set A and set B can be: set B is a subset of set A, or set B is a wide beam and set A is a narrow beam, or the time domain beam prediction also includes a set B that is the same as set A, and predicts the beam measurement results of set A at a specified future time based on the beam measurement results of set B at the current time.

[0317] In some implementations, the beam prediction principle of the AI ​​model is as follows:

[0318] 1. For spatial prediction: The terminal measures the L1-RSRP of set B and inputs it into the AI ​​model to predict the L1-RSRP and / or the best K beam IDs of set A. The relationship between set B and set A includes the following two types:

[0319] (1) Set B is a subset of set A. For example, if set A contains 32 reference signals (each corresponding to a beam direction), then set B contains 8 of them.

[0320] (2) Set B is a wide beam, and set A is a narrow beam. For example, set A contains 32 reference signals (each reference signal corresponds to a beam direction, and the 32 reference signals cover a 120° direction). Set B contains another 8 reference signals, and these 8 reference signals also cover a 120° direction. That is, the beam direction of each reference signal in set B covers the beam directions of multiple reference signals in set A. This can be understood as the relationship between the 32 reference signals in set A and the same reference signal in set B being QCL (quasi co-location) Type D.

[0321] 2. For time-domain prediction, the terminal measures the L1-RSRP of set B at a historical time, inputs it into the AI ​​model, and predicts the L1-RSRP and / or optimal K beam IDs of set A at a future time. In addition to the two aforementioned relationships, set B and set A can also be identical.

[0322] (1) If the L1-RSRP of set A at a future time is predicted based on the AI ​​model, the reference signal of set A at the future time may not be sent. The beam information is obtained based on the output of the AI ​​model and then reported to the base station.

[0323] (2) In one embodiment, a reference signal at a future time also needs to be sent. The terminal measures the reference signal at the future time and obtains beam information and reports it to the base station.

[0324] In some embodiments, the AI ​​model output mainly includes L1-RSRP and / or beam (beam or beam pair) ID information. For beam-based transmission, since the coverage range of each beam is limited, if the beam is not updated in time, beam failure may occur, that is, the radio link quality (radio link quality) corresponding to the current beam is lower than the downlink quality lower limit, where the downlink quality lower limit can be represented by Qout. When the above situation occurs, the terminal needs to report the beam failure to the network side based on SR (Scheduling Request) and PUSCH (physical uplink shared channel), or based on the random access process. In some embodiments, the terminal finds a new beam that can be used for link communication, and reports the new beam to the network. In this reporting process, the terminal communicates based on the beam where the beam failure occurs, which will reduce the communication performance of the terminal, or even cause communication interruption, thereby affecting the user experience.

[0325] In view of this, this proposal proposes a communication method to achieve beam failure prediction based on an AI model through communication interaction. The output of the AI ​​model includes not only L1-RSRP and / or beam ID, but also beam failure information. The beam failure information includes the radio link quality (radio link quality) of the beam within a specified time or the probability that the radio link quality value of the beam at a specified time is lower than Qout, etc., so that network devices can select beams for communication transmission based on this information, avoiding the probability of beam failure during terminal communication.

[0326] 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:

[0327] In step S2101, the first device 101 determines a reference signal resource, where the reference signal resource is used for beam measurement.

[0328] For example, a reference signal resource refers to a specific signal used to transmit a reference signal in a wireless communication system. The reference signal resource can be used for communication and positioning between a terminal and a base station. The reference signal resource exists in various forms in a wireless communication system, including a downlink reference signal (DL RS) and an uplink reference signal (UL RS). The reference signal resource can be used to measure and evaluate channel quality, perform initial access procedures, perform positioning and device tracking, etc. The reference signal resource may include a synchronization signal broadcast channel block (SS / PBCH block, SSB) or a channel state information reference signal (CSI-RS).

[0329] In some embodiments, the allocation and configuration of reference signal resources is handled by the Radio Resource Management (RRM) function. The RRM function determines how the reference signal resources are allocated based on network requirements and optimization objectives to maximize system performance and efficiency. By determining the reference signal resources configured in the first device, the beam of the first device is measured to determine the channel quality of the corresponding beam and generate a beam measurement result for the beam.

[0330] In some embodiments, the reference signal resources determined by the first device 101 include one or more. The first device 101 performs beam measurement on the corresponding beam based on the one or more reference signal resources, each reference signal resource corresponding to a different beam. The measurement of multiple reference signal resources can provide more channel state information samples, which can improve the accuracy of channel evaluation.

[0331] Step S2102: The first device 101 determines first information based on the beam measurement result of the reference signal resource.

[0332] For example, after the first device 101 determines the reference signal resource through the above steps, it measures the channel quality of the corresponding beam based on the reference signal resource and generates a beam measurement result. Based on the beam measurement result, first information is generated. The beam measurement result is used to indicate the beam quality information of the corresponding beam, and the beam measurement result can be at least one of the following: L1-RSRP, L1-SINR, radio link quality, SINR, SNR, BLER (BLock Error Rate), corresponding beam ID, etc. The beam ID includes an SSB ID or a CSI-RS ID.

[0333] In some embodiments, the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to predict beam failure or beam pair failure. For example, in this embodiment, the first AI model may be configured in the first device 101 and / or the second device 102, and the first AI model is used to predict beam failure of a beam or beam pair at a specified time or within a specified time based on the input information, and generate output information.

[0334] In some embodiments, for the first AI model in this proposal, a model training process for the first AI model and a model application process for the first AI model are included. The first AI model can be configured in the first device 101 and / or the second device 102. For example, in the model training process of the first AI model, if the first AI model is configured in the second device 102, the second device trains the first AI model through the first information sent by the first device 101, where the first information includes input information and measurement information. In the model application process of the first AI model, the first AI model configured in the first device 101 is a trained AI model, and beam failure prediction is performed on the beam or beam pair through the first AI model in the first device 101. After generating the first information, the first information is sent to the second device 102, where the first information includes the output information of the first AI model. During the model application process of the first AI model, the first AI model configured in the second device 102 is a trained AI model. The first information is sent through the first device 101, and the second device 102 inputs the first message into the first AI model. Based on the output of the first AI model, beam failure prediction information of the beam or beam pair is obtained, wherein the first information includes the input information of the first AI model.

[0335] In some embodiments, the present proposal is a model training process for a first AI model, during which the non-training end of the first AI model sends the input information of the AI ​​model and the measurement information corresponding to the output information to the training end, and the training end of the first AI model performs model training on the AI ​​model based on the received input information and output information. For example, in the model training phase, the first device 101 is a terminal, the first AI model is configured in the second device 102, and the second device 102 is a network device. The first device generates first information through beam measurement results of reference signal resources, and the first information includes the input information of the first AI model and the measurement information corresponding to the output information. The input information and the measurement information are sent as the first information to the second device 102, and the first AI model in the second device 102 is trained through the input information and the measurement information.

[0336] In some embodiments, the first information is used to perform model training on a first AI model in a second device, and the first information includes input information and measurement information.

[0337] In some embodiments, the name of the first information is not limited, for example, it can be "model training information", "model sample information", "sample data information", "input and output information", etc.

[0338] In some embodiments, the present proposal is a model application process based on a first AI model, wherein beam failure prediction or beam pair failure prediction is performed using the first AI model. During the model application process, an application end of the first AI model sends first information to a non-application end. The first information is output information generated by the first AI model through model application of input information, and the output information is used to indicate a beam failure prediction result or a beam pair failure prediction result at a specified time or within a specified time. For example, the first device 101 is a terminal device, and the first AI model is configured in the first device 101. The model output information is sent to the second device 102 through the first device 101. The second device 102 can be a network device. The first device 101 predicts the beam failure information based on the beam measurement result through the first AI model. After generating the model output information, the model output information is sent to the second device 102. The first information includes the output information of the first AI model, and the output information is used to indicate the beam failure prediction result or the beam pair failure prediction result. The first device 101 sends the first information to the second device 102, and the second device 102 can perform new beam allocation based on the first information.

[0339] In some embodiments, the first AI model is used to perform beam failure prediction or beam pair failure prediction. For example, the first device is a network device. The terminal determines the first information by measuring the reference signal resources and sends the first information to the network device. The network device uses the first information as input information of the first AI model and inputs it into the first AI model, and obtains beam failure information or beam pair failure information based on the output of the first AI model.

[0340] In some embodiments, the output information of the first AI model is used to determine a beam failure prediction result for the current best beam or the current best beam pair. This prediction result can be used to indicate the probability or specific time of beam failure for the current best beam or beam pair within a specified time.

[0341] In some embodiments, the output information of the first AI model is used to determine a beam failure prediction result for the best beam at a future time or a beam failure prediction result for the best beam pair. This prediction result can be used to indicate the probability or specific time at which beam failure will occur for the best beam or beam pair at a future time within a specified time.

[0342] It should be noted that in various embodiments of the present invention, the beam failure prediction result and the beam failure information can be replaced with each other; the beam pair failure prediction result and the beam pair failure information can be replaced with each other.

[0343] In some embodiments, the input information includes at least one of the following:

[0344] first input information determined by measurement;

[0345] Second input information, where the second input information is determined by predicting the input information of the first AI model at the current time through the second AI model;

[0346] Third input information, where the third input information is determined by predicting the input information of the first AI model at a future time using a third AI model;

[0347] A specified time is used to indicate a time for performing beam failure prediction or beam pair failure prediction;

[0348] a first quality threshold, where the first quality threshold is used to indicate a determination condition of a beam failure or a beam pair failure;

[0349] The second quality threshold is used to determine the decision condition for the new beam.

[0350] For example, in this embodiment, the input information of the first AI model includes one or more of the following:

[0351] (1) First input information is determined by measuring a reference signal resource through a first device, where the first input information is used to indicate at least one of the LI-RSRP, the L1-SINR, or the beam ID of the beam.

[0352] (2) The second input information is determined by predicting the input information of the first AI model at the current time through the second AI model.

[0353] (3) The third input information is determined by predicting the input information of the first AI model at a future time through the third AI model, where the future time can be a certain time point in the future or a certain time range in the future.

[0354] (4) A specified time, wherein the specified time is used to indicate the time point at which the first AI model performs beam failure prediction, wherein the time point can be a specified future moment or a specified future time range. It should be noted that the various embodiments of the present invention are applicable to both beams and beam pairs. That is, beam failure prediction can also be beam pair failure prediction, beam failure information can also be beam pair failure information, and the optimal beam can also be the optimal beam pair, etc.

[0355] (5) A first quality threshold, which is used to indicate a judgment condition for beam failure or beam pair failure. For example, when the first AI model determines that the wireless link quality of the beam or beam pair is less than the first quality threshold, beam failure will occur in the beam or beam pair.

[0356] (6) A second quality threshold, which is used to determine the judgment condition for a new beam. For example, when the first AI model determines that a beam failure occurs at a specified time, the second quality threshold is used to determine a new beam at the specified time, and the wireless link quality of multiple beams at the specified time is compared with the second quality threshold. If there is a beam with a wireless link quality greater than the second quality threshold, then the beam is determined to be the new beam at the specified time.

[0357] In some embodiments, the first input information includes at least one of the following:

[0358] Identifications of best K beams or beam pairs in a first beam set determined by measurement, the first beam set being determined based on a first reference signal resource set, the first reference signal resource set including reference signal resources;

[0359] The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measurement;

[0360] The physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by measurement;

[0361] L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement, where L is an integer greater than or equal to 1;

[0362] L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement;

[0363] L1-RSRPs of M specified beams or beam pairs in the first beam set determined through measurement, where M is an integer greater than or equal to 1;

[0364] L1-SINRs for the specified M beams or beam pairs determined by measurement;

[0365] L1-RSRP of any N beams or beam pairs in the first beam set determined through measurement, where N is an integer greater than or equal to 1 and N is less than L;

[0366] The L1-SINR of any N beams or beam pairs determined by measurement;

[0367] The identities of any N beams or beam pairs determined by measurements.

[0368] It should be noted that, in this embodiment, the first input information is obtained by measuring the reference signal resources in the first reference signal resource set corresponding to the first beam set.

[0369] For example, in this embodiment, the first AI model can be used to predict beam failure information of the best K beams at the current time, and the best K beams at the current time are the best K beams actually measured. In the input information of the first AI model, the first input information determined through measurement can include at least one of the following:

[0370] (1) Identification of the best K beams or beam pairs in a first beam set determined by measuring reference signal resources in a first reference signal resource set, wherein the first beam set is determined by a first reference signal resource set, the first reference signal resource set including the reference signal resources in the above steps, the best K beams or beam pairs being K beams with the largest L1-RSRP or L1-SINR among the multiple beams or beam pairs, where K is an integer greater than or equal to 1.

[0371] (2) The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measuring the first reference signal resource in the first reference signal resource set, where L1-RSRP is a key parameter that can represent the wireless signal strength in the network and a physical layer measurement requirement, and is used to indicate the wireless link quality of the best K beams or beam pairs.

[0372] (3) The physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by measuring the first reference signal resource in the first reference signal resource set, where L1-SINR is the ratio between the strength of the received useful signal and the strength of the received interference signal (noise and interference).

[0373] (4) L1-SINRs of all L beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set, where L is the number of beams in the first beam set and L is an integer greater than or equal to 1.

[0374] (5) L1-RSRPs of all L beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set.

[0375] (6) LI-RSRP of M beams or beam pairs specified in the first beam set, determined by measuring the first reference signal resource in the first reference signal resource set, where M can be configured by the network device through RRC signaling, system information broadcast, or default protocol specification, and M is an integer greater than or equal to 1, and M<L.

[0376] (7) L1-SINRs of M beams or beam pairs specified in the first beam set, determined by measuring the first reference signal resource in the first reference signal resource set.

[0377] (8) L1-RSRP of any N beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set, where N is an integer greater than or equal to 1 and less than L.

[0378] (9) LI-SINRs of any N beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set.

[0379] (10) Identifications of any N beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set.

[0380] In some embodiments, the second input information determined by the second AI model includes at least one of the following:

[0381] Identifications of best K beams or beam pairs in a first beam set determined by prediction, the first beam set being determined based on a first reference signal resource set, the first reference signal resource set comprising reference signal resources;

[0382] The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by prediction;

[0383] The physical layer signal-to-interference-plus-noise ratio (L1-SINR) of the best K beams or beam pairs determined by prediction;

[0384] L1-SINRs of all L beams or beam pairs in the first beam set determined by prediction;

[0385] L1-RSRP of all L beams or beam pairs in the first beam set determined by prediction;

[0386] L1-RSRPs of M beams or beam pairs specified in the first beam set determined by prediction, where M is an integer greater than or equal to 1;

[0387] L1-SINRs of the specified M beams or beam pairs determined by prediction;

[0388] L1-RSRPs of any N beams or beam pairs in the first beam set determined by prediction, where N is an integer greater than or equal to 1 and N is less than L;

[0389] The L1-SINR of any N beams or beam pairs determined by prediction;

[0390] The identities of any N beams or beam pairs determined by prediction.

[0391] For example, in this embodiment, the second input information determined by the second AI model includes at least one of the following:

[0392] (1) The input information of the first AI model is predicted by the second AI model to determine the identifiers of the best K beams or beam pairs in the first beam set, where the first beam set is determined based on a first reference signal resource set, and the first reference signal resource set includes reference signal resources. The best K beams or beam pairs are the same as those in the above embodiment, and reference may be made to the above embodiment, which will not be repeated here.

[0393] (2) The L1-RSRPs of the best K beams or beam pairs determined by prediction using the second AI model.

[0394] (3) The L1-SINR of the best K beams or beam pairs determined by prediction using the second AI model.

[0395] (4) L1-RSRP of all L beams or beam pairs in the first beam set determined by prediction using the second AI model.

[0396] (5) The LI-SINR of all L beams or beam pairs in the first beam set determined by prediction using the second AI model.

[0397] (6) L1-RSRPs of M beams or beam pairs specified in the first beam set are predicted and determined by the second AI model, where M is the same as M in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0398] (7) L1-SINRs of the specified M beams or beam pairs in the first beam set determined by prediction using the second AI model.

[0399] (8) The L1-RSRP of any N beams or beam pairs in the first beam set is predicted and determined by the second AI model, where N is the same as N in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0400] (9) The L1-SINR of any N beams or beam pairs in the first beam set determined by prediction using the second AI model.

[0401] (10) Identification of any N beams or beam pairs in the first beam set determined by prediction using the second AI model.

[0402] In this example, the input information of the first AI model is obtained based on the output information of the second AI model. The input information of the second AI model includes beam information of the second beam set, which is obtained by measuring the reference signal resources in the second reference signal resource set corresponding to the second beam set. In various embodiments of the present invention, one example of the relationship between the second reference signal resource set and the first reference signal resource set is the relationship between set B and set A described above, that is, the second reference signal resource set is set B and the first reference signal resource is set A.

[0403] In some embodiments, the first input information or the second AI model input information includes at least one of the following:

[0404] Identifiers of multiple beams or beam pairs in a second beam set determined by measurement, and second beam information of the second beam set used for input into the first AI model, where the second beam information includes the identifier and at least one of L1-RSRP and L1-SINR, and the second beam set includes reference signal resources;

[0405] L1-RSRP of a plurality of beams or beam pairs in a second beam set determined by measurement;

[0406] L1-SINRs of the plurality of beams or beam pairs in the second beam set determined through measurement.

[0407] It should be noted that, in this embodiment, the first input information or the input information of the second AI model is obtained by measuring the reference signal resources in the second reference signal resource set corresponding to the second beam set.

[0408] For example, in this embodiment, the first AI model is used to predict beam failure information of the best K beams or beam pairs at the current time, and the best K beams or beam pairs at the current time are predicted and determined by the first AI model. That is, the first AI model simultaneously predicts the best K beams or beam pairs at the current time, and simultaneously predicts beam failure information or beam pair failure information of the best K beams or beam pairs at a specified time. The first input information corresponding to the first AI model determined through measurement includes at least one of the following:

[0409] (1) By measuring reference signal resources in a second reference signal resource set, beam information of a plurality of beams or beam pairs in the second beam set is determined as second beam information of the second beam set; the second beam information includes a beam identifier, at least one of an L1-RSRP and an L1-SINR, and the second beam set corresponds to the second reference signal resource. For example, the second beam information includes IDs of a portion of reference signal resources in the second reference signal resource set, and the L1-RSRP or L1-SINR corresponding to the IDs.

[0410] (2) L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measuring reference signal resources in the second reference signal resource set; for example, the second beam information includes L1-RSRPs corresponding to all reference signal resources in the second reference signal resource set.

[0411] (3) L1-SINRs of multiple beams or beam pairs in the second beam set determined by measuring reference signal resources in the second reference signal resource set. For example, the second beam information includes L1-SINRs corresponding to all reference signal resources in the second reference signal resource set.

[0412] In some embodiments, the third input information is determined by predicting the input information of the first AI model at a future time using a third AI model, and the third input information includes at least one of the following:

[0413] Identifiers of predicted best K beams or beam pairs in a first beam set corresponding to a future time, where the first beam set is determined based on a first reference signal resource set, the first reference signal resource set including reference signal resources;

[0414] The predicted L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0415] The predicted L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0416] Predicting L1-SINRs of all L beams or beam pairs in the first beam set in the first beam set corresponding to the future time;

[0417] Predicting L1-RSRPs of all L beams or beam pairs in the first beam set corresponding to the future time;

[0418] Predicting L1-RSRPs of M beams or beam pairs specified in the first beam set in the first beam set corresponding to the future time, where M is an integer greater than or equal to 1;

[0419] Predicting L1-SINRs of designated M beams or beam pairs in the first beam set at a future time;

[0420] Predicting the L1-RSRP of any N beams or beam pairs in the first beam set corresponding to the future time, where N is an integer greater than or equal to 1 and N is less than L;

[0421] Predicting the L1-SINR of any N beams or beam pairs in the first beam set corresponding to the future time;

[0422] The identifiers of any N beams or beam pairs in the first beam set are predicted in the first beam set corresponding to the future time.

[0423] It should be noted that, when the future time is multiple future times, the above input information includes at least one of the above items corresponding to each future time.

[0424] For example, in this embodiment, the first AI model is used to predict beam failure information of the best K beams or beam pairs at a future time within a specified time, and the best K beams or beam pairs at the future time are predicted and determined by other AI models. That is, in this embodiment, the best K beams or beam pairs at the future time are predicted by other AI models, and the beam failure information or beam pair failure information of the best K beams or beam pairs is predicted by the first AI model. The third input information includes at least one of the following:

[0425] (1) Predicting input information of the first AI model at a future time through a third AI model to determine identifiers of the best K beams or beam pairs in a first beam set corresponding to the future time, where the first beam set is determined based on a first reference signal resource set, which includes reference signal resources. The future time may be a future time point or a future time range.

[0426] (2) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time.

[0427] (3) Predicting the input information of the first AI model at the future time through the third AI model to determine the L1-SINRs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time.

[0428] (4) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-SINR of all L beams or beam pairs in the first beam set corresponding to the future time, where L is the same as L in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0429] (5) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time.

[0430] (6) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-RSRP of M beams or beam pairs specified in the first beam set corresponding to the future time, where M is the same as M in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0431] (7) Predicting the input information of the first AI model at the future time by the third AI model to determine the L1-SINR of the specified M beams or beam pairs in the first beam set corresponding to the future time.

[0432] (8) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-RSRP of any N beams or beam pairs in the first beam set corresponding to the future time, where N is the same as N in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0433] (9) The input information of the first AI model at the future time is predicted by the third AI model to determine the L1-SINR of any N beams or beam pairs in the first beam set corresponding to the future time.

[0434] (10) Predicting the input information of the first AI model at a future time by the third AI model, and determining the identifiers of any N beams or beam pairs in the first beam set corresponding to the future time.

[0435] It should be noted that if there are multiple future times above, the input information includes at least one of the above items corresponding to each future time in the multiple future times. In this example, the input information of the first AI model is obtained based on the output information of the third AI model. The input information of the third AI model includes the beam information of the second beam set, and the beam information of the second beam set is obtained by measuring the reference signal resources in the second reference signal resource set corresponding to the second beam set. In various embodiments of the present invention, one example of the relationship between the second reference signal resource set and the first reference signal resource set is the relationship between set B and set A mentioned above, that is, the second reference signal resource set is set B, and the first reference signal resource is set A.

[0436] In some embodiments, the first input information of the first AI model or the input information of the third AI model includes at least one of the following:

[0437] Identifications of a plurality of beams or beam pairs in the second beam set determined by measurements at a plurality of historical times;

[0438] L1-RSRPs of multiple beams or beam pairs in the second beam set determined by measurements at multiple historical times;

[0439] L1-SINRs of multiple beams or beam pairs in the second beam set determined by measurements at multiple historical times;

[0440] The second beam set is determined based on a second reference signal resource set, and the second reference signal resource set includes reference signal resources.

[0441] For example, in this embodiment, the first AI model and the third AI model can be time domain prediction models. The beam information of the future time is predicted by the beam information measured in the historical time. The first AI model is used to predict the beam failure information of the best K beams or beam pairs in the future time, and the best K beams or beam pairs in the future time are predicted and determined by the first AI model, that is, based on the first AI model, the best K beams or beam pair identifiers of the future time are predicted, and the beam failure information of the predicted best K beams or beam pairs in the future time is predicted. Among them, the input information of the first input information and the input information of the third AI model include at least one of the following:

[0442] (1) Identification of multiple beams or beam pairs in a second beam set determined by measurement in multiple historical times based on the current time, wherein the second beam set is the same as the second beam set in the above embodiment, and reference may be made to the above embodiment, which will not be repeated here. The multiple historical times may be multiple historical time points based on the current time, or multiple historical time ranges.

[0443] (2) L1-RSRP of multiple beams or beam pairs in the second beam set determined by measurement at multiple historical times.

[0444] (3) L1-SINRs of multiple beams or beam pairs in the second beam set determined by measurements at multiple historical times.

[0445] It should be noted that, in this embodiment, the first input information or the input information of the third AI model is obtained by measuring the reference signal resources in the second reference signal resource set corresponding to the second beam set.

[0446] In some embodiments, the output information of the first AI model or the beam failure information includes at least one of the following:

[0447] a radio link quality value of a first beam at a first time, where the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time;

[0448] a first probability value of the first beam in the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0449] The block error rate (BLER) value of the first beam at the first time;

[0450] A first minimum radio link quality value, where the first minimum radio link quality value is the lowest radio link quality value of the first beam in the first period;

[0451] A first highest BLER value, where the first highest BLER value is a highest BLER value of the first beam in the first period;

[0452] Beam failure time of the first beam;

[0453] The identifier of the new beam.

[0454] For example, in this embodiment, the first AI model can be used to predict the beam failure information of the best K beams at the current time, and the best K beams at the current time are the best K beams actually measured. The output information or beam failure information of the first AI model can include at least one of the following:

[0455] (1) A radio link quality value of a first beam at a first time, where the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time, where the first beam may include one or more beams. The first time may be configured by a network device through RRC signaling, or determined through system information broadcast, or determined through factory protocol configuration. The first time is a future time point or a future time range.

[0456] (2) A first probability value of the first beam within the first period, the first probability value being a probability value that the radio link quality value is lower than a second quality threshold, wherein the first period may be a specified time range in the future, or a time range from the current time to a certain moment in the future. The first probability value is used to indicate whether a beam failure occurs for the first beam within the first period. For example, the second quality threshold may be a downlink quality lower limit, and its corresponding BLER is represented by Qout. When the BLER corresponding to the radio link quality of the first beam within the first period is lower than Qout, for example, in some embodiments, the first probability is a value higher than 50%.

[0457] In some embodiments, the first probability value may be a hard probability, the probability value of which is 0 or 1. When it is determined that the wireless link quality is lower than the second quality threshold, the probability value is determined to be 1; when it is determined that the wireless link quality is higher than the second quality threshold, the probability value is determined to be 0.

[0458] In some embodiments, the first probability value may also be a soft probability, with a value of [0, 1]. For example, the soft probability may be determined based on the difference between the wireless link quality and the second quality threshold. For example, when the difference is greater than the first threshold, the soft probability is determined to be 0; when the difference is less than the second threshold, the soft probability is determined to be 100%; when the difference is less than the first threshold but greater than a third threshold, the soft probability is determined to be 30%; and when the difference is greater than the second threshold but less than the third threshold, the soft probability is determined to be 80%. The first threshold is greater than the third threshold and greater than the second threshold.

[0459] (3) The Block Error Rate (BLER) value of the first beam at the first time. BLER refers to the average error rate of the transmission block after CRC (Cyclic Redundancy Check) verification. This value is a long-term statistical average and an important indicator used to reflect the network performance and service quality. The quality of BLER directly affects the user's perception of voice and image quality, throughput, and latency. For example, in voice services, when the BLER target value is set to 1%-3%, the call quality is acceptable. In video call services, when the BLER target value is set to 0.1%-1%, good voice quality can be guaranteed. The BLER value of the first beam at the first time is used to determine whether the first beam has experienced a beam failure.

[0460] (4) A first minimum wireless link quality value, which is the lowest wireless link quality value of the first beam within a first period, where the first period is a specified time range in the future, or a time range from the current time to a certain moment in the future.

[0461] (5) A first highest BLER value. The first highest BLER value is the highest BLER value of the first beam in the first period. The first period is the same as the first period in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0462] (6) The beam failure time at which the first beam fails. The beam failure time is a certain moment in the future or a certain time range in the future.

[0463] (7) An identifier of a new beam, wherein the new beam may be a beam whose wireless link quality is greater than a first quality threshold within a first time or a first period. When the first device communicates within the first time or the first period based on the new beam, the communication quality of the first device can be guaranteed. The identifier of the new beam may include one or more.

[0464] In some embodiments, the output information of the first AI model further includes at least one of the following:

[0465] Identification of the best K beams or beam pairs in the first beam set;

[0466] L1-RSRP of the best K beams or beam pairs in the first beam set;

[0467] L1-SINR of the best K beams or beam pairs in the first beam set;

[0468] L1-RSRP of all L beams or beam pairs in the first beam set;

[0469] L1-SINR of all L beams or beam pairs in the first beam set.

[0470] For example, in this embodiment, the first AI model is used to predict the beam failure information of the best K beams or beam pairs at the current time, and the best K beams or beam pairs at the current time are predicted and determined by the first AI model. That is, the first AI model simultaneously predicts the best K beams or beam pairs at the current time, and predicts the beam failure information or beam pair failure information of the best K beams or beam pairs at a specified time. The output information or beam failure information of the first AI model may further include at least one of the following:

[0471] (1) Identification of the best K beams or beam pairs in the first beam set, where the first beam set is the same as the first beam set in the above embodiment, and reference may be made to the above embodiment, which will not be described in detail here. The best K beams or beam pairs are the K beams or beam pairs with the greatest wireless link quality among multiple beams, and K is the same as K in the above embodiment, and reference may be made to the above embodiment, which will not be described in detail here.

[0472] (2) L1-RSRP of the best K beams or beam pairs in the first beam set.

[0473] (3) L1-SINR of the best K beams or beam pairs in the first beam set.

[0474] (4) L1-RSRP of all L beams or beam pairs in the first beam set, where L is the same as L in the above embodiment. Please refer to the above embodiment and will not be repeated here.

[0475] (5) L1-SINR of all L beams or beam pairs in the first beam set.

[0476] In some embodiments, the output information includes at least one of the following:

[0477] a radio link quality value of a first beam at a first time in the future time, where the first beam at the future time is the best K beams or beam pairs at the future time determined by measurement or prediction;

[0478] a first probability value of the first beam at the future time within the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold;

[0479] a BLER value of the first beam at the future time at the first time;

[0480] a second minimum radio link quality value, where the second minimum radio link quality value is the lowest radio link quality value of the first beam at the future time within the first period;

[0481] a second highest BLER value, where the second highest radio link quality value is the highest BLER value of the first beam at the future time within the first period;

[0482] a beam failure time corresponding to the first beam at the future time;

[0483] The identifier of the new beam corresponding to the future time.

[0484] For example, in this embodiment, the first AI model is used to predict beam failure information of the best K beams or beam pairs at a future time, and the best K beams or beam pairs at the future time are predicted and determined by other AI models. That is, in this embodiment, the best K beams or beam pairs at the future time are predicted by other AI models, and the beam failure information or beam pair failure information of the best K beams or beam pairs is predicted by the first AI model. The output information or beam failure information of the first AI model includes at least one of the following:

[0485] (1) The first beam at a future time is the best K beams or beam pairs at a future time based on the current time, wherein the best K beams or beam pairs are predicted and determined by other AI models or determined by measurement, and the first AI model is used to predict the wireless link quality value of the first beam at a first time in the future, wherein the first time is a certain moment in the future.

[0486] (2) Predicting a first probability value of a first beam in a future time within a first period by using a first AI model, wherein the first period is a time range in the future time, and the first probability value is predicting a wireless link quality value of the first beam in the first period by using the first AI model, and determining a probability value that the wireless link quality value is lower than the second quality threshold according to the wireless link quality value and the second quality threshold. For example, in this embodiment, the probability value can be determined based on the difference between the wireless link quality value and the second quality threshold.

[0487] (3) The BLER value of the first beam at the first time in the future time is predicted by the first AI model, wherein the definition of the BLER value is the same as that in the above embodiment, and can be referred to in the above embodiment, which will not be repeated here.

[0488] (4) The first AI model is used to predict the lowest wireless link value of the first beam in the future time within the first period as the second lowest wireless link quality value, where the first period is a period range in the future time.

[0489] (5) The first AI model is used to predict the highest BLER value of the first beam in the future time within the first period as the second highest BLER value.

[0490] (6) The first beam at a future time, the beam failure time at which a beam failure occurs at a future time.

[0491] (7) When the first beam at a future time is determined by the first AI model, and beam failure occurs in the future time, a new beam that meets the communication quality requirements at the future time is predicted by the first AI model, and an identifier of the new beam is output, where the communication quality requirement can be a first quality threshold. For example, when the wireless link quality value of the beam is determined to be greater than the first quality threshold, the beam is determined to be a new beam, and the identifier of the new beam is output.

[0492] In some embodiments, the output information includes at least one of the following:

[0493] the identities of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0494] L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0495] The L1-SINR of the best K beams or beam pairs in the first beam set corresponding to the future time;

[0496] L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time;

[0497] L1-SINR of all L beams or beam pairs in the first beam set corresponding to the future time.

[0498] It should be noted that, when the future time is multiple future times, the above output includes at least one of the above items corresponding to each future time.

[0499] For example, in this embodiment, the first AI model is used to predict beam failure information of the best K beams or beam pairs at a future time, and the best K beams or beam pairs at the future time are predicted and determined by the first AI model. That is, based on the first AI model, the best K beams or beam pairs at the future time are predicted, and beam failure information of the best K beams or beam pairs is predicted. The output information of the first AI model, i.e., beam failure information, includes at least one of the following:

[0500] (1) Identification of the best K beams or beam pairs in the first beam set corresponding to the future time, wherein the definition of the first beam set is the same as that in the above embodiment, and reference can be made to the above embodiment, which will not be repeated here. It should be noted that when the future time is multiple future times, the above output includes at least one of the above items corresponding to each future time.

[0501] (2) After predicting the first beam set corresponding to the future time through the first AI model, the beam quality of the first beam set is detected to determine the L1-RSRP of the best K beams or beam pairs in the first beam set.

[0502] (3) Detect the wireless link quality of the beams in the first beam set corresponding to the future time, and determine the L1-SINRs of the best K beams or beam pairs in the first beam set.

[0503] (4) Detect the beam qualities of all L beams or beam pairs in the first beam set at the future time, and determine the L1-RSRPs of all L beams or beam pairs.

[0504] (5) Detect the beam qualities of all L beams or beam pairs in the first beam set at the future time, and determine the L1-SINRs of all L beams or beam pairs.

[0505] In some embodiments, the measurement information includes at least one of the following:

[0506] a radio link quality value of the first beam at a first time determined by measurement;

[0507] a first probability value of the first beam in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0508] a BLER value of the first beam at the first time determined by measurement;

[0509] a lowest value of the radio link quality value of the first beam determined by measurement within the first period;

[0510] a highest BLER value of the first beam in the first period determined by measurement;

[0511] a beam failure time of the first beam determined by measurement;

[0512] The identity of the new beam determined by measurements.

[0513] For example, in this embodiment, the first AI model can be used to predict the probability or radio link quality value of the best K beams at the current time that the radio link quality is lower than the second threshold Qout within a specified time, and the best K beams at the current time are the best K beams actually detected. The measurement information includes at least one of the following:

[0514] (1) Measure the reference signal resources to determine the radio link quality value of the first beam at the first time. The definitions of the first beam and the first time are the same as those in the above embodiment, and can be referred to the above embodiment, which will not be repeated here.

[0515] (2) The reference signal resource is measured to determine a first probability value of the first beam within a first period, wherein the first probability value is a probability value that the wireless link quality value is lower than a second quality threshold. The definitions of the first period and the second quality threshold are the same as those in the above embodiment, and can be referred to in the above embodiment, and are not repeated here.

[0516] (3) The reference signal resources are measured to determine the BLER value of the first beam at the first time. The definition of the BLER value is the same as that in the above embodiment, and reference may be made to the above embodiment, which will not be repeated here.

[0517] (4) Measure the reference signal resources and determine the lowest value of the link quality value of the first beam in the first period, where the definition of the first period is the same as

[0518] (5) Measure the reference signal resources to determine the highest BLER value of the first beam in the first period.

[0519] (6) Measure the reference signal resource to determine the beam failure time when the beam failure occurs in the first beam.

[0520] (7) Measure the reference signal resources. When it is determined that the first beam will fail within a future time range, determine a new beam within the future time range and output a beam identifier of the new beam.

[0521] In some embodiments, the measurement information includes at least one of the following:

[0522] Identifications of the best K beams or beam pairs in the first set of beams determined by measurements;

[0523] L1-RSRP of the best K beams or beam pairs in the first beam set determined by measurement;

[0524] L1-SINRs of the best K beams or beam pairs in the first beam set determined by measurement;

[0525] L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement;

[0526] The L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement.

[0527] For example, in this embodiment, the first AI model is used to predict the probability or radio link quality value of the best K beams or beam pairs at the current time being lower than the second quality threshold within a specified time. The best K beams or beam pairs at the current time are predicted and determined by the first AI model. That is, the first AI model simultaneously predicts the best K beams or beam pairs at the current time and predicts beam failure information or beam pair failure information for the best K beams or beam pairs at the specified time. The measurement information corresponding to the output information includes at least one of the following:

[0528] (1) Identification of the best K beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set, where the definition of the first beam set is the same as in the above embodiment, and reference can be made to the above embodiment, and no further details are given here.

[0529] (2) L1-RSRPs of the best K beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set.

[0530] (3) L1-SINRs of the best K beams or beam pairs in the first beam set determined by measuring the first reference signal resources in the first reference signal resource set.

[0531] (4) The L1-RSRPs of all L beams or beam pairs in the first beam set are determined by measuring the first reference signal resource in the first reference signal resource set, where L is the same as L in the above embodiment. The above embodiment can be referred to and will not be repeated here.

[0532] (5) L1-SINRs of all L beams or beam pairs in the first beam set determined by measuring the first reference signal resource in the first reference signal resource set.

[0533] In some embodiments, the measurement information includes at least one of the following:

[0534] a radio link quality value of a first beam at a first time at a future time determined by measurement;

[0535] A first probability value of a first beam at a future time within a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold;

[0536] a BLER value of a first beam at a first time at a future time determined by measurement;

[0537] a lowest value of the radio link quality value of the first beam at a future time determined by measurement within the first period;

[0538] A highest BLER value of the first beam in the first period at a future time determined by measurement;

[0539] a beam failure time of a first beam at a future time determined by measurement;

[0540] The identity of the new beam corresponding to the future time determined by measurement.

[0541] It should be noted that when the future time is multiple future times, the above output includes at least one of the above items corresponding to each future time.

[0542] For example, in this embodiment, the first AI model is used to predict the probability or radio link quality value of the best K beams or beam pairs in the future time being lower than the second quality threshold within a specified time, and the best K beams or beam pairs in the future time are predicted and determined by another AI model. That is, in this embodiment, the best K beams or beam pairs in the future time are predicted by another AI model, and beam failure information or beam pair failure information of the best K beams or beam pairs is predicted by the first AI model. The measurement information includes at least one of the following:

[0543] (1) The wireless link quality value of the first beam at the first time in the future time is determined by measuring the reference signal resource, wherein the first beam and the first time are the same as those in the above embodiment, and can be referred to the above embodiment, and will not be repeated here.

[0544] (2) A first probability value of the first beam at a future time within a first period is determined by measuring the reference signal resource, where the first probability value is a probability value that the wireless link quality value is lower than a second quality threshold, where the second quality threshold is the same as in the above embodiment, and can be referred to in the above embodiment, and will not be repeated here.

[0545] (3) The BLER value of the first beam at the first time in the future time determined by measuring the reference signal resources.

[0546] (4) The lowest value of the radio link quality value of the first beam at a future time within a first period is determined by measuring the reference signal resource, where the first period is the same as that in the above embodiment, and reference can be made to the above embodiment, which will not be repeated here.

[0547] (5) The highest BLER value of the first beam in the first period at a future time determined by measuring the reference signal resources.

[0548] (6) A beam failure time at which a beam failure occurs for the first beam at a future time determined by measuring the reference signal resource.

[0549] (7) Beam failure occurs at a future time determined by measuring the reference signal resources, and an identifier of a new beam that meets the beam quality requirements is determined at the future time.

[0550] In some embodiments, the measurement information includes at least one of the following:

[0551] Identifications of the best K beams or beam pairs in the first beam set corresponding to a future time determined by measurement;

[0552] The L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0553] L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0554] L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement;

[0555] The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement.

[0556] It should be noted that, when the future time is multiple future times, the above output includes at least one of the above items corresponding to each future time.

[0557] For example, in this embodiment, the first AI model is used to predict the radio link quality values ​​of the best K beams or beam pairs at a future time or the probability that the radio link quality is lower than the second quality threshold within a specified time. The best K beams or beam pairs at the future time are predicted and determined by the first AI model. That is, based on the first AI model, the best K beams or beam pairs at the future time are predicted, and beam failure information of the best K beams or beam pairs is predicted. The measurement information includes at least one of the following:

[0558] (1) Identification of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measuring the reference signal resources in the first reference signal resource set, where the definition of the first beam set is the same as that in the above embodiment, and reference can be made to the above embodiment, which is not repeated here.

[0559] (2) The first beam set corresponding to the future time is determined by measuring the reference signal resources in the first reference signal resource set, and the beam quality of the best K beams or beam pairs in the first beam set is measured to determine the L1-RSRP of the best K beams or beam pairs.

[0560] (3) L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to a future time determined by measuring the reference signal resources in the first reference signal resource set.

[0561] (4) L1-RSRPs of all L beams or beam pairs in the first beam set corresponding to a future time are determined by measuring the reference signal resources in the first reference signal resource set, where L is the same as in the above embodiment and can be referred to in the above embodiment, which is not repeated here.

[0562] (5) L1-SINRs of all L beams or beam pairs in the first beam set corresponding to a future time determined by measuring the reference signal resources in the first reference signal resource set.

[0563] In some implementations, the method further includes determining a radio link quality value.

[0564] For example, determining the radio link quality value includes at least one of the following:

[0565] An SNR (Signal to Noise Ratio) determined based on receiving a PDCCH for a beam is used to determine a radio link quality value of the beam according to the SNR of the beam.

[0566] The SINR determined based on the PDCCH received for one beam is used to determine the radio link quality value of the beam according to the SINR of the beam.

[0567] Based on information about the physical downlink control channel (PDCCH) received by two beams, the SNR or SINR is determined, and a radio link quality is calculated based on the simultaneous reception of the PDCCH by two beams. The model used for optimal beam prediction can predict the optimal beam group, and both beams in the group can be used to simultaneously receive the PDCCH transmitted based on the SFN (Single Frequency Network).

[0568] In some embodiments, the method further comprises:

[0569] The specified time, future time, first time, first period, first quality threshold, or second quality threshold is determined by at least one of the following methods:

[0570] Determined by radio resource control protocol RRC signaling;

[0571] Determined based on broadcast information or system information;

[0572] Determined based on default rule information.

[0573] For example, in this embodiment, the specified time, future time, first time, first period, first quality threshold or second quality threshold can be determined through wireless resource control protocol RRC signaling, or determined according to system information broadcast, or determined by default rule information, where the default rule information can be the factory configuration protocol of the terminal.

[0574] In some embodiments, the designated time may be close to the period of periodic beam report reporting. For example, if no beam failure occurs before the next beam report, and the terminal reports the new best beam in time, the base station can update the beam in time. For example, the designated time may also include at least one of the following: the period of beam report, the time when MAC CE (MAC Control Element) activates TCI (transmission configuration indication) state, the time when DCI (Downlink Control Information) indicates the codepoint corresponding to TCI state, and the time when the terminal sends HARQ (Hybrid Automatic Repeat-reQuest)-ACK (ACKnowledge Character) feedback corresponding to DCI.

[0575] In some embodiments, the specified time may also include only the period of the search space corresponding to the DCI downlink control information format of the new beam indicated by the terminal, because if the network device uses DCI to update the new beam before the current beam fails, then beam failure will not occur. In addition to including the period of the search space, the specified time may also include the time when the DCI indicates the TCI-transmission configuration indication state corresponding to the codepoint and the time when the terminal sends the HARQ-ACK feedback corresponding to the DCI.

[0576] Step S2103: The first device 101 sends first information.

[0577] In some implementations, the second device 102 receives the first information.

[0578] In some embodiments, the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0579] In some embodiments, the first information includes measurement information corresponding to the input information and the output information. The first information is sent to the second device 102 to instruct the second device 102 to perform model training on the first AI model based on the first information.

[0580] In some embodiments, the first information includes output information of the first AI model, where the output information is used to indicate a beam failure prediction result or a beam pair failure prediction result. The first information is used to indicate the model output result of the first AI model to the second device 102, so that the second device 102 performs beam reselection or beam configuration based on the model output result to improve communication performance of the communication system.

[0581] Step S2104: The second device 102 receives the first information.

[0582] In some embodiments, the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0583] In the above technical solution, a first device determines a reference signal resource, which is used for beam measurement. Based on the beam measurement results of the reference signal resource, the device determines first information, which includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information. The first AI model is used to predict beam failure or beam pair failure and transmits the first information. Beam failure prediction based on the AI ​​model generates beam or beam pair failure information, enabling network devices to better select beams for communication transmission based on this information, thereby reducing the probability of beam failure.

[0584] FIG3 is a flow chart of a communication method according to an embodiment of the present disclosure. The method is performed by the first device 101. As shown in FIG3 , the method includes the following steps:

[0585] Step S3101: Determine a reference signal resource, where the reference signal resource is used for beam measurement.

[0586] In the embodiments of the present disclosure, the implementation of step S3101 may refer to the embodiment of the aforementioned step S2101 and will not be repeated here.

[0587] Step S3102: Determine first information based on a beam measurement result of a reference signal resource.

[0588] In some embodiments, the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0589] In the embodiments of the present disclosure, the implementation of step S3102 may refer to the embodiment of the aforementioned step S2102 and will not be repeated here.

[0590] Step S3103: Send the first information.

[0591] In the embodiments of the present disclosure, the implementation of step S3103 may refer to the embodiment of the aforementioned step S2103 and will not be repeated here.

[0592] In the above technical solution, a first device determines a reference signal resource, which is used for beam measurement. Based on the beam measurement results of the reference signal resource, the device determines first information, which includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information. The first AI model is used to predict beam failure or beam pair failure and transmits the first information. Beam failure prediction based on the AI ​​model generates beam or beam pair failure information, enabling network devices to better select beams for communication transmission based on this information, thereby reducing the probability of beam failure.

[0593] FIG4 is a flow chart of a communication method according to an embodiment of the present disclosure. The method is performed by the second device 102. As shown in FIG4 , the method includes the following steps:

[0594] Step S4101: The second device receives the first information.

[0595] In some embodiments, the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

[0596] In the embodiments of the present disclosure, the implementation of step S4101 may refer to the embodiment of the aforementioned step S2102 and will not be repeated here.

[0597] In the above technical solution, the second device receives first information, which includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information. The first AI model is used to predict beam failure or beam pair failure. Based on the beam failure prediction performed by the AI ​​model, beam or beam pair failure information is generated. This information allows the network device to better select beams for communication transmission, thereby reducing the probability of beam failure.

[0598] FIG5 is a flowchart of a communication method according to an embodiment of the present disclosure. The method is performed by the first device 101. As shown in FIG5 , the method includes the following steps:

[0599] Step S5101: Obtain model input information of the first AI model.

[0600] In some embodiments, the first AI model is used to predict the probability or radio link quality value of the best K beams at the current time that the radio link quality value is lower than a second quality threshold within a specified time, where the second quality threshold is the lower limit of the downlink quality and can be represented by Qout. The best K beams at the current time are the best K beams actually measured, not the best K beams predicted by the first AI model output. For example, the best K beams can also be output by other AI models, but the models for predicting the best K beams and predicting the failure of the beams are different models. That is, the best K beams have been obtained before the failure of beam prediction by the first AI model.

[0601] In some embodiments, the model input information may include at least one of the following:

[0602] At least one of the actually measured L1-RSRP, L1-SINR, and beam ID (reference signal resource ID and / or Rx beam ID) of the best K beams and beam pairs;

[0603] L1-RSRP or L1-SINR of all beams in the first beam set set A;

[0604] L1-RSRP or L1-SINR of multiple beams specified in set A;

[0605] At least one of L1-RSRP, L1-SINR, and beam ID (reference signal resource ID and / or Rx beam ID) of multiple randomly selected beams or beam pairs in set A.

[0606] In some embodiments, the model input may further include: a specified time for specifying beam failure prediction, a first quality threshold for determining a new beam, wherein the first quality threshold may be a downlink quality upper limit, and the first quality threshold may be represented by Qin.

[0607] Step S5102: Determine model output information through the first AI model based on model input information.

[0608] In some embodiments, the model output information is used to indicate a beam failure prediction result or a beam pair failure prediction result.

[0609] In some embodiments, a model output includes at least one of the following:

[0610] The probability that the radio link quality is lower than Qout within a specified time period, where radio link quality includes the signal-to-noise ratio (SNR) and signal-to-noise ratio (SINR). The corresponding BLER (block error rate) is then obtained. If the BLER is higher than Qout, it indicates that a beam failure has occurred. For example, the probability value can be a hard probability: if the BLER is higher than Qout, the probability is 1; otherwise, the probability is 0. Alternatively, the probability value can be a soft probability: for example, if the BLER is 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 lower than Qout and the difference below Qout is greater than a threshold, the probability is 0; otherwise, the probability is 30%.

[0611] The radio link quality value or BLER value at a specified time, that is, the radio link quality value or BLER value at the time point corresponding to the specified time is predicted;

[0612] The lowest radio link quality value or the highest BLER value within the specified time. This means the lowest radio link quality value or the highest BLER value before the specified time point and after the current time point. If the corresponding BLER of the lowest radio link quality value or the highest BLER value is greater than Qout, it indicates that beam failure has occurred.

[0613] If the previous outputs determine that beam failure will occur within the specified time, the time when the beam failure occurs can be further given, as well as the new beam identifier. The RSRP of the new beam must be higher than Qin, and the new beam can be one or more.

[0614] In some embodiments, the first AI model can also be used to predict the probability or value of the radio link quality of the best K beams at the current time being lower than Qout 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, the first AI model simultaneously predicts the best K beams and the beam failure information corresponding to the best K beams.

[0615] For example, the model input information may further include: at least one of L1-RSRP, L1-SINR or beam ID information (reference signal resource ID and / or Rx beam ID) of multiple beams or beam pairs in the second beam set set B.

[0616] Optionally, the model input may further include a value of a first quality threshold Qin at a specified time.

[0617] For example, the model output information includes at least one of the following:

[0618] The probability that the radio link quality is lower than Qout within a specified time period, where radio link quality includes the signal-to-noise ratio (SNR) and signal-to-noise ratio (SINR). The corresponding BLER (block error rate) is then obtained. If the BLER is higher than Qout, it indicates that a beam failure has occurred. For example, the probability value can be a hard probability: if the BLER is higher than Qout, the probability is 1; otherwise, the probability is 0. Alternatively, the probability value can be a soft probability: for example, if the BLER is 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 lower than Qout and the difference below Qout is greater than a threshold, the probability is 0; otherwise, the probability is 30%.

[0619] The radio link quality value or BLER value at a specified time, that is, the radio link quality value or BLER value at the time point corresponding to the specified time is predicted;

[0620] The lowest radio link quality value or the highest BLER value within the specified time. This means the lowest radio link quality value or the highest BLER value before the specified time point and after the current time point. If the corresponding BLER of the lowest radio link quality value or the highest BLER value is greater than Qout, it indicates that beam failure has occurred.

[0621] If the previous outputs determine that beam failure will occur within the specified time, the time when the beam failure occurs can be further given, as well as the new beam identifier. The RSRP of the new beam must be higher than Qin, and the new beam can be one or more.

[0622] 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.

[0623] In some embodiments, the first AI model can be used to predict 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, as well as beam failure information corresponding to the best K beams.

[0624] For example, the model input information further includes values ​​corresponding to multiple historical times, that is, the probability or radio link quality value of the best K beams at multiple historical times being lower than Qout.

[0625] In some embodiments, the first AI model can predict 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 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.

[0626] For example, the model input information may include values ​​corresponding to multiple historical times, that is, the probability or radio link quality value of the best K beams at multiple historical times being lower than Qout.

[0627] In some implementations, the radio link quality can be calculated based on a single beam or based on two beams simultaneously receiving a PDCCH (Physical Downlink Control Channel). For example, when the radio link quality is calculated based on two beams simultaneously receiving a PDCCH, the model for optimal beam prediction can predict an optimal beam group, where both beams in the group can be used to simultaneously receive a PDCCH transmitted over a single frequency network (SFN).

[0628] In some embodiments, Qout, Qin or the specified time can be configured by base station RRC signaling, system information broadcast, or the default value specified by the protocol. For example, the specified time can be close to the period of the periodic beam report. That is, if there is no beam failure before the next beam report and the terminal timely reports the new best beam, the base station can update the beam in time. Of course, this specified time can also include at least one of the following: the period of the beam report, the time when the MAC CE (MAC Control Element) activates the TCI (transmission configuration indication) state, the time when the DCI (Downlink Control Information) indicates the codepoint corresponding to the TCI state, and the time when the terminal sends the HARQ (Hybrid Automatic Repeat-reQuest)-ACK feedback corresponding to the DCI.

[0629] For example, the specified time can also only include the period of the search space corresponding to the DCI downlink control information format 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 can also include the time when the DCI indicates the codepoint corresponding to the TCI - transmission configuration indication state and the time when the terminal sends the HARQ-ACK feedback corresponding to the DCI.

[0630] In some embodiments, in spatial domain beam prediction, set B is different from set A, or set B < set A; in temporal domain beam prediction, set B is different from set A, or set B < set A, or Set B = set A. For example, for temporal domain beam prediction, when set B < set A, set B remains unchanged for multiple historical times, or the beams included in set B for multiple historical times are completely different, and set B for multiple historical times can form a set A. For instance, when inputting set B for 4 historical times, each set B only contains 1 / 4 of the beams in set A, and the 4 set Bs exactly contain all the beams in set A.

[0631] In some embodiments, how the base station selects a beam based on probability (this does not need to be written in the claims, because it is implemented by the base station and will not be benchmarked, it is only for illustrating the purpose of beam failure prediction). For example, 1. 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 to indicate to the terminal as the current beam; 2. Or it can select the first beam with the highest L1-RSRP but a slightly higher beam failure probability, and then update the beam within a short period of time, indicating the second beam with a slightly lower L1-RSRP but a beam failure probability of 0, for example, updating to the second beam before the beam failure of the first beam occurs.

[0632] In some embodiments, the UE receives reference signal resource configuration information and report configuration information, performs measurements, and reports a report, wherein the contents of the report include: (1) data collection information used to train the model. For example, the terminal needs to report the input and output of the model, and report multiple samples, where one sample corresponds to one input and output of the model; the input information is as described in the above embodiment, and the output information is as described in the above embodiment, which will not be repeated here. (2) data collection information used for model inference: if the model is on the network side, the terminal needs to report information used for model input, as described in the above embodiment, which will not be repeated here; if the model is on the terminal side, the terminal needs to report information for model output, as described in the above embodiment, which will not be repeated here.

[0633] In the above embodiment, a beam failure prediction method based on an AI model is proposed. In addition to L1-RSRP and / or beam (pair) ID, the model output may also include the probability that the radio link quality of a beam within a specified time is lower than Qout (threshold), or the value of the radio link quality of a beam at a specified time. Therefore, network devices can better select beams for communication transmission based on this information and reduce the probability of beam failure.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, and terms such as "physical uplink shared channel (PUSCH)" and "UL data" can be used interchangeably.

[0638] In some embodiments, the terms "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based" and the like may be used interchangeably.

[0639] 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.

[0640] In some embodiments, terms such as "synchronization signal (SS)", "synchronization signal block (SSB)", "reference signal (RS)", "pilot", and "pilot signal" can be used interchangeably.

[0641] In some embodiments, terms such as "moment", "time point", "time", and "time position" can be replaced with each other, and terms such as "duration", "period", "time window", "window", and "time" can be replaced with each other.

[0642] 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.

[0643] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0644] 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.

[0645] In some embodiments, the determination or judgment can be performed by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values ​​(for example, comparison with a predetermined value), but is not limited thereto.

[0646] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0647] 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.

[0648] 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.

[0649] Figure 6 is a structural diagram of the first device proposed in an embodiment of the present disclosure. As shown in Figure 6, the first device 6100 may include: an execution module 6101, a processing module 6102, and a transceiver module 6103. In some embodiments, the above-mentioned execution module 6100 is used to determine a reference signal resource, and the reference signal resource is used for beam measurement. The processing module 6102 is used to determine the first information based on the beam measurement result of the reference signal resource, and the first information includes at least one of the input information of the first AI model, the output information of the first AI model, and the measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction. The transceiver module 6103 is used to send the first information.

[0650] Figure 7 is a structural diagram of the second device proposed in an embodiment of the present disclosure. As shown in Figure 7, the terminal 7100 may include: a transceiver module 7101. In some embodiments, the above-mentioned transceiver module 7100 is used to receive first information, and the first information includes at least one of the input information of the first AI model, the output information of the first AI model, and the measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction. Optionally, the above-mentioned transceiver module is used to perform at least one of the communication steps such as sending and / or receiving performed by the network device 102 in any of the above methods, which will not be repeated here.

[0651] 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.

[0652] Figure 8 is a schematic diagram of the structure of a network device 8100 proposed in an embodiment of the present disclosure. Network device 8100 can be a communications 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 implementing any of the above methods, or a chip, a chip system, or a processor that supports a terminal implementing any of the above methods. Network device 8100 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.

[0653] As shown in Figure 8, the network device 8100 includes one or more processors 8101. The processor 8101 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 communication protocols and communication data, and the central processing unit can be used to control communication devices (such as base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the network device 8100 is used to perform any of the above methods. Optionally, one or more processors 8101 are used to call instructions to enable the network device 8100 to perform any of the above methods.

[0654] In some embodiments, the network device 8100 further includes one or more transceivers 8102. When the network device 8100 includes one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method, and the processor 8101 performs at least one of the other steps. 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.

[0655] In some embodiments, network device 8100 also includes one or more memories 8103 for storing data. Alternatively, all or part of memory 8103 may be located outside of network device 8100. In alternative embodiments, network device 8100 may include one or more interface circuits 8104. Interface circuits 8104 may optionally be connected to memory 8102 and may be configured to receive data from memory 8102 or other devices, or to send data to memory 8102 or other devices. For example, interface circuit 8104 may read data stored in memory 8102 and send the data to processor 8101.

[0656] The network device 8100 described in the above embodiment may be a network device or a terminal, but the scope of the network device 8100 described in the present disclosure is not limited thereto, and the structure of the network device 8100 may not be limited by FIG. 8A. The network device may be an independent device or may be part of a larger device. For example, the network 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.

[0657] The present disclosure also provides a storage medium having instructions stored thereon. When the instructions are executed on the network device 8100, the network device 8100 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 transient storage medium.

[0658] The present disclosure also provides a program product, which, when executed by the network device 8100, enables the network device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0659] 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: Executed by a first device, the method includes: Determining a reference signal resource, where the reference signal resource is used for beam measurement; Determine first information based on the beam measurement result of the reference signal resource, where the first information includes at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction; The first information is sent.

2. The method according to claim 1, characterized in that The input information includes at least one of the following: first input information determined by measurement; Second input information, where the second input information is determined by predicting the input information of the first AI model at the current time through the second AI model; third input information, where the third input information is determined by predicting the input information of the first AI model at a future time through a third AI model; A specified time, where the specified time is used to indicate a time for performing the beam failure prediction or the beam pair failure prediction; a first quality threshold, where the first quality threshold is used to indicate a determination condition of a beam failure or a beam pair failure; A second quality threshold, where the second quality threshold is used to determine a decision condition for a new beam.

3. The method according to claim 2, characterized in that The first input information includes at least one of the following: Identifications of best K beams or beam pairs in a first beam set determined by measurement, the first beam set being determined based on a first reference signal resource set including the reference signal resources; The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measurement; A physical layer signal to interference plus noise ratio L1-SINR of the best K beams or beam pairs determined by measurement; L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement, where L is an integer greater than or equal to 1; L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement; L1-RSRPs of designated M beams or beam pairs in the first beam set determined by measurement, where M is an integer greater than or equal to 1; L1-SINRs of the designated M beams or beam pairs determined by measurement; L1-RSRP of any N beams or beam pairs in the first beam set determined by measurement, where N is an integer greater than or equal to 1, and N is less than L; L1-SINRs of the arbitrary N beams or beam pairs determined by measurement; The identities of the arbitrary N beams or beam pairs are determined by measurements.

4. The method according to claim 2, characterized in that: The second input information includes at least one of the following: Identifications of best K beams or beam pairs in a first beam set determined by prediction, the first beam set being determined based on a first reference signal resource set, the reference signal resource set including the reference signal resource; The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by prediction; A physical layer signal to interference plus noise ratio L1-SINR of the best K beams or beam pairs determined by prediction; L1-SINRs of all L beams or beam pairs in the first beam set determined by prediction; L1-RSRPs of all L beams or beam pairs in the first beam set determined by prediction; L1-RSRPs of designated M beams or beam pairs in the first beam set determined by prediction, where M is an integer greater than or equal to 1; L1-SINRs of the designated M beams or beam pairs determined by prediction; L1-RSRPs of any N beams or beam pairs in the first beam set determined by prediction, where N is an integer greater than or equal to 1, and N is less than L; L1-SINR of the arbitrary N beams or beam pairs determined by prediction; The identities of the arbitrary N beams or beam pairs determined by prediction.

5. The method according to claim 3 or 4, characterized in that: The first input information or the second AI model input information includes at least one of the following: The second beam information of the second beam set is the identifier of the plurality of beams or beam pairs in the second beam set determined by measurement. 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, and the second beam set includes the reference signal resource; L1-RSRP of a plurality of beams or beam pairs in the second beam set determined by measurement; The L1-SINRs of the plurality of beams or beam pairs in the second beam set are determined by measurement.

6. The method according to claim 2, characterized in that The third input information includes at least one of the following: an identifier of the predicted best K beams or beam pairs in a first beam set corresponding to the future time, the first beam set being determined based on a first reference signal resource set, the first reference signal resource set including the reference signal resource; L1-RSRPs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time; L1-SINRs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time; Predicting L1-SINRs of all L beams or beam pairs in the first beam set in the first beam set corresponding to the future time; The predicted L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of the specified M beams or beam pairs in the predicted first beam set corresponding to the future time, where M is an integer greater than or equal to 1; The predicted L1-SINR of the specified M beams or beam pairs in the first beam set corresponding to the future time; The predicted L1-RSRP of any N beams or beam pairs in the first beam set corresponding to the future time, where N is an integer greater than or equal to 1, and N is less than L; The predicted L1-SINR of any N beams or beam pairs in the first beam set corresponding to the future time; The identifiers of any N beams or beam pairs in the predicted first beam set in the first beam set corresponding to the future time.

7. The method according to claim 3 or 6, characterized in that: The first input information or the input information of the third AI model includes at least one of the following: Identifications of a plurality of beams or beam pairs in a second set of beams determined by measurements at a plurality of historical times; L1-RSRPs of a plurality of beams or beam pairs in the second beam set determined by measurement during the plurality of historical times; L1-SINRs of a plurality of beams or beam pairs in the second beam set determined by measurement in the plurality of historical times; The second beam set is determined based on a second reference signal resource set, and the second reference signal resource set includes the reference signal resources.

8. The method according to any one of claims 1 to 7, characterized in that: The output information includes at least one of the following: a radio link quality value of a first beam at a first time, wherein the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time; a first probability value of the first beam in a first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; A block error rate (BLER) value of the first beam at the first time; A first minimum radio link quality value, where the first minimum radio link quality value is the lowest radio link quality value of the first beam in the first period; a first highest BLER value, where the first highest BLER value is a highest BLER value of the first beam in the first period; a beam failure time of the first beam; The identifier of the new beam.

9. The method according to claim 8, characterized in that The output information further includes at least one of the following: 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.

10. The method according to any one of claims 1 to 7, characterized in that: The output information includes at least one of the following: The wireless link quality value of the first beam at the first time in the future time, wherein the first beam at the future time is measured or predicted. The best K beams or beam pairs at a given future time; a first probability value of the first beam at the future time within the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; a BLER value of the first beam at the future time at the first time; a second minimum radio link quality value, where the second minimum radio link quality value is the lowest radio link quality value of the first beam at the future time within the first period; a second highest BLER value, where the second highest radio link quality value is the highest BLER value of the first beam at the future time within the first period; a beam failure time corresponding to the first beam at the future time; The identifier of the new beam corresponding to the future time.

11. The method according to claim 10, characterized in that The output information includes at least one of the following: Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time; The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time.

12. The method according to any one of claims 1 to 11, characterized in that: The measurement information includes at least one of the following: A radio link quality value of a first beam at a first time determined by measurement; A first probability value of the first beam in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; A BLER value of the first beam at the first time determined by measurement; a lowest value of the radio link quality value of the first beam in the first period determined by measurement; a highest value of the BLER value of the first beam in the first period determined by measurement; a beam failure time of the first beam determined by measurement; Identification of new beams determined by measurements; identification of the best K beams or beam pairs in the first set of beams determined by measurements; L1-RSRP of the best K beams or beam pairs in the first beam set determined by measurement; L1-SINRs of the best K beams or beam pairs in the first beam set determined by measurement; L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement; The L1-SINRs of all L beams or beam pairs in the first beam set are determined by measurement.

13. The method according to any one of claims 1 to 11, characterized in that: The measurement information includes at least one of the following: A radio link quality value of a first beam at a first time at a future time determined by measurement; A first probability value of the first beam at the future time in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; A BLER value of the first beam at the future time at the first time determined by measurement; a lowest value of the radio link quality value of the first beam at the future time within the first period determined by measurement; a highest value of the BLER value of the first beam at the future time within the first period determined by measurement; a beam failure time of the first beam at said future time determined by measurement; an identification of a new beam corresponding to the future time determined by measurement; Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement; The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time are determined by measurement.

14. The method according to any one of claims 1 to 13, characterized in that The method further comprises: Determine a wireless link quality value, wherein determining the wireless link quality value includes at least one of the following: The signal-to-noise ratio (SNR) determined based on a beam; SINR determined based on one beam; The SNR or SINR is determined based on information about the situation of receiving the physical downlink control channel PDCCH in two beams.

15. The method according to any one of claims 1 to 14, characterized in that The method further comprises: The specified time, the future time, the first time, the first period, the first quality threshold, or the second quality threshold is determined by at least one of the following methods: Determined by radio resource control protocol RRC signaling; Determined according to broadcast information or system information; Determined based on default rule information.

16. A communication method, characterized in that: Executed by a second device, the method includes: Receive first information, the first information including input information of a first AI model, output information of the first AI model, and at least one of measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

17. The method according to claim 16, characterized in that The input information includes at least one of the following: first input information determined by measurement; Second input information, where the second input information is determined by predicting the input information of the first AI model at the current time through the second AI model; third input information, where the third input information is determined by predicting the input information of the first AI model at a future time through a third AI model; A specified time, where the specified time is used to indicate a time for performing the beam failure prediction or the beam pair failure prediction; a first quality threshold, where the first quality threshold is used to indicate a determination condition of a beam failure or a beam pair failure; A second quality threshold, where the second quality threshold is used to determine a decision condition for a new beam.

18. The method according to claim 17, characterized in that The first input information includes at least one of the following: Identifications of best K beams or beam pairs in a first beam set determined by measurement, the first beam set being determined based on a first reference signal resource set including the reference signal resources; The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by measurement; A physical layer signal to interference plus noise ratio L1-SINR of the best K beams or beam pairs determined by measurement; L1-SINRs of all L beams or beam pairs in the first beam set determined by measurement, where L is an integer greater than or equal to 1; L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement; L1-RSRPs of designated M beams or beam pairs in the first beam set determined by measurement, where M is an integer greater than or equal to 1; L1-SINRs of the designated M beams or beam pairs determined by measurement; L1-RSRP of any N beams or beam pairs in the first beam set determined by measurement, where N is an integer greater than or equal to 1, and N is less than L; L1-SINRs of the arbitrary N beams or beam pairs determined by measurement; The identities of the arbitrary N beams or beam pairs are determined by measurements.

19. The method according to claim 17, characterized in that The second input information includes at least one of the following: The physical layer reference signal received power L1-RSRP of the best K beams or beam pairs determined by prediction; A physical layer signal to interference plus noise ratio L1-SINR of the best K beams or beam pairs determined by prediction; L1-SINRs of all L beams or beam pairs in the first beam set determined by prediction; L1-RSRPs of all L beams or beam pairs in the first beam set determined by prediction; L1-RSRPs of designated M beams or beam pairs in the first beam set determined by prediction, where M is an integer greater than or equal to 1; L1-SINRs of the designated M beams or beam pairs determined by prediction; L1-RSRPs of any N beams or beam pairs in the first beam set determined by prediction, where N is an integer greater than or equal to 1, and N is less than L; L1-SINR of the arbitrary N beams or beam pairs determined by prediction; The identities of the arbitrary N beams or beam pairs determined by prediction.

20. The method according to claim 18 or 19, characterized in that The first input information or the second AI model input information includes at least one of the following: Identifiers of multiple beams or beam pairs in a second beam set determined by measurement, and second beam information of the second beam set is used to be input into the first AI model, wherein the second beam information includes an identifier, at least one of L1-RSRP and L1-SINR, and the second beam set includes the reference signal resource; L1-RSRP of a plurality of beams or beam pairs in the second beam set determined by measurement; The L1-SINRs of the plurality of beams or beam pairs in the second beam set are determined by measurement.

21. The method according to claim 17, characterized in that The third input information includes at least one of the following: an identifier of the predicted best K beams or beam pairs in a first beam set corresponding to the future time, the first beam set being determined based on a first reference signal resource set, the first reference signal resource set including the reference signal resource; L1-RSRPs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time; L1-SINRs of the best K beams or beam pairs predicted in the first beam set corresponding to the future time; Predicting L1-SINRs of all L beams or beam pairs in the first beam set in the first beam set corresponding to the future time; The predicted L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of the specified M beams or beam pairs in the predicted first beam set corresponding to the future time, where M is an integer greater than or equal to 1; The predicted L1-SINR of the specified M beams or beam pairs in the first beam set corresponding to the future time; The predicted L1-RSRP of any N beams or beam pairs in the first beam set corresponding to the future time, where N is an integer greater than or equal to 1, and N is less than L; The predicted L1-SINR of any N beams or beam pairs in the first beam set corresponding to the future time; The identifiers of any N beams or beam pairs in the predicted first beam set in the first beam set corresponding to the future time.

22. The method according to claim 18 or 21, characterized in that The first input information or the input information of the third AI model includes at least one of the following: Identifications of a plurality of beams or beam pairs in a second set of beams determined by measurements at a plurality of historical times; L1-RSRPs of a plurality of beams or beam pairs in the second beam set determined by measurement during the plurality of historical times; L1-SINRs of a plurality of beams or beam pairs in the second beam set determined by measurement in the plurality of historical times; The second beam set is determined based on a second reference signal resource set, and the second reference signal resource set includes the reference signal resources.

23. The method according to any one of claims 16 to 22, characterized in that: The output information includes at least one of the following: a radio link quality value of a first beam at a first time, wherein the first beam is the best K beams or beam pairs determined by measurement or prediction at the first time; a first probability value of the first beam in a first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; A block error rate (BLER) value of the first beam at the first time; A first minimum radio link quality value, where the first minimum radio link quality value is the lowest radio link quality value of the first beam in the first period; a first highest BLER value, where the first highest BLER value is a highest BLER value of the first beam in the first period; a beam failure time of the first beam; The identifier of the new beam.

24. The method according to claim 23, characterized in that The output information further includes at least one of the following: 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.

25. The method according to any one of claims 16 to 22, characterized in that: The output information includes at least one of the following: a radio link quality value of a first beam at a future time at a first time, wherein the first beam at the future time is the best K beams or beam pairs at the future time determined by measurement or prediction; a first probability value of the first beam at the future time within the first period, the first probability value being a probability value of the radio link quality value being lower than a second quality threshold; a BLER value of the first beam at the future time at the first time; a second minimum radio link quality value, where the second minimum radio link quality value is the lowest radio link quality value of the first beam at the future time within the first period; a second highest BLER value, where the second highest radio link quality value is the highest BLER value of the first beam at the future time within the first period; a beam failure time corresponding to the first beam at the future time; The identifier of the new beam corresponding to the future time.

26. The method according to claim 25, characterized in that The output information includes at least one of the following: Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time; The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time.

27. The method according to any one of claims 16 to 26, characterized in that: The measurement information includes at least one of the following: A radio link quality value of a first beam at a first time determined by measurement; A first probability value of the first beam in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; A BLER value of the first beam at the first time determined by measurement; a lowest value of the radio link quality value of the first beam in the first period determined by measurement; a highest value of the BLER value of the first beam in the first period determined by measurement; a beam failure time of the first beam determined by measurement; Identification of new beams determined by measurements; identification of the best K beams or beam pairs in the first set of beams determined by measurements; L1-RSRP of the best K beams or beam pairs in the first beam set determined by measurement; L1-SINRs of the best K beams or beam pairs in the first beam set determined by measurement; L1-RSRP of all L beams or beam pairs in the first beam set determined by measurement; The L1-SINRs of all L beams or beam pairs in the first beam set are determined by measurement.

28. The method according to any one of claims 16 to 26, characterized in that: The measurement information includes at least one of the following: A radio link quality value of a first beam at a first time at a future time determined by measurement; A first probability value of the first beam at the future time in a first period determined by measurement, the first probability value being a probability value of a radio link quality value being lower than a second quality threshold; A BLER value of the first beam at the future time at the first time determined by measurement; a lowest value of the radio link quality value of the first beam at the future time within the first period determined by measurement; a highest value of the BLER value of the first beam at the future time within the first period determined by measurement; a beam failure time of the first beam at said future time determined by measurement; an identification of a new beam corresponding to the future time determined by measurement; Identifications of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-RSRPs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-SINRs of the best K beams or beam pairs in the first beam set corresponding to the future time determined by measurement; L1-RSRP of all L beams or beam pairs in the first beam set corresponding to the future time determined by measurement; The L1-SINRs of all L beams or beam pairs in the first beam set corresponding to the future time are determined by measurement.

29. The method according to any one of claims 16 to 28, characterized in that The method further comprises: Determine a wireless link quality value, wherein determining the wireless link quality value includes at least one of the following: The signal-to-noise ratio (SNR) determined based on a beam; SINR determined based on one beam; The SNR or SINR is determined based on information about the situation of receiving the physical downlink control channel PDCCH in two beams.

30. The method according to any one of claims 16 to 29, characterized in that The method further comprises: The specified time, the future time, the first time, the first period, the first quality threshold, or the second quality threshold is determined by at least one of the following methods: Determined by radio resource control protocol RRC signaling; Determined according to broadcast information or system information; Determined based on default rule information.

31. A first device, characterized in that: include: An execution module is configured to determine a reference signal resource, where the reference signal resource is used for beam measurement; a processing module, configured to determine first information based on a beam measurement result of the reference signal resource, the first information comprising at least one of input information of a first AI model, output information of the first AI model, and measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction; The transceiver module is configured to send the first information.

32. A second device, characterized in that: include: The transceiver module is configured to receive first information, wherein the first information includes input information of a first AI model, output information of the first AI model, and at least one of measurement information corresponding to the output information, wherein the first AI model is used to perform beam failure prediction or beam pair failure prediction.

33. A first device, characterized in that: include: one or more processors; The first device is used to execute the communication method according to any one of claims 1 to 15.

34. A second device, characterized in that: include: one or more processors; Wherein, the second device is used to execute the communication method described in any one of claims 16-30.

35. A communication system, characterized in that: The invention comprises a first device and a second device, wherein the first device is configured to implement the communication method according to any one of claims 1 to 15, and the second device is configured to implement the communication method according to any one of claims 16 to 30.

36. A storage medium storing instructions, characterized in that: When the instructions are executed on a communication device, the communication device is caused to execute the communication method according to any one of claims 1 to 15 and 16 to 30.

Images