Prediction method and communication device

Abstract

The embodiment of the invention discloses a prediction method and a communication device, relates to the technical field of communication, and can reduce the overhead of reporting prediction information of a predicted future moment or time period by terminal equipment. The method comprises the following steps: receiving first indication information, wherein the first indication information is used for indicating execution of a first prediction task; determining a first time unit, the first time unit being one of the at least two candidate time units; and / or determining a first time period length, the first time period length being one of the at least two candidate time period lengths; determining the number N of prediction information contained in each report in at least one report corresponding to the first prediction task, wherein N is a positive integer; a first report corresponding to the first prediction task is determined according to at least two of the first time unit, the first time period length or N, the first report is one of the at least one report, and the first report comprises N pieces of prediction information; and sending the first report. The embodiment of the invention is used in a prediction information reporting process.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a prediction method and a communication device. Background Technology

[0002] With the introduction of artificial intelligence (AI) into wireless communication networks, AI has been widely applied in various scenarios of air interface technology, such as channel state information (CSI) feedback, CSI prediction, beam management, and positioning. Among these, AI-based beam management scenarios include spatial beam prediction and temporal beam prediction. In temporal beam prediction, AI beam prediction models can use historical beam measurement information to predict future beam information, thereby improving the robustness of beam management in scenarios with rapidly changing signals and avoiding frequent beam measurements and switching.

[0003] In AI-based time-domain prediction scenarios, if the AI ​​prediction model resides on the terminal device, the terminal device needs to report prediction information for one or more future moments or time periods to the network device. However, terminal devices typically perform beam prediction and reporting at fixed time intervals. Considering that signal conditions may change at different rates, when the rate of change is slow, the terminal device may report the same prediction information for one or more moments at a time, leading to unnecessary reporting overhead. For example, in a time-domain beam prediction scenario, the beam prediction model on the terminal device needs to report beam prediction information for one or more future moments or time periods to the network device. When the rate of change of signal conditions varies, the rate of change of the optimal beam also varies. When the rate of change of signal conditions is slow, the beam change rate is also slow, and the terminal device may report the same prediction information for one or more moments at a time, resulting in unnecessary reporting overhead. Summary of the Invention

[0004] This application provides a prediction method and communication device that can reduce the overhead of terminal devices reporting prediction information for future moments or time periods.

[0005] Firstly, a prediction method is provided. Optionally, the executing entity of this method can be a terminal device, a component or device applied to the terminal device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the terminal device's functions. The method includes: receiving first indication information, the first indication information being used to instruct the execution of a first prediction task; determining a first time unit, the first time unit being one of at least two candidate time units; and / or determining a first time period length, the first time period length being one of at least two candidate time period lengths; determining the number N of prediction information contained in each of at least one report corresponding to the first prediction task, N being a positive integer; determining a first report corresponding to the first prediction task based on at least two of the first time unit, the first time period length, or N, the first report being one of at least one report, the first report including N prediction information; and sending the first report.

[0006] Therefore, in this application, compared to existing methods that report prediction information using fixed time units and a fixed number of prediction information items, which can lead to the problem of identical prediction information at multiple moments when the signal change rate of the terminal device is slow, resulting in wasted reporting overhead, the terminal device in this application can flexibly select from at least two candidate time units and / or at least two candidate time lengths when the number of prediction information items N is fixed. For example, when the signal change rate of the terminal device is slow, a first time unit or a first time length with a larger time unit can be selected for prediction information reporting. In this way, within the same time length, when the terminal device selects a larger time unit, it is equivalent to reducing the number of prediction information items reported, thereby reducing the measurement overhead and prediction information reporting overhead of the terminal device.

[0007] In one possible design, the method further includes receiving second indication information, which indicates at least two candidate time units or at least two candidate time period lengths. This allows the terminal device to flexibly select the time unit or time period length to report when the network device provides the terminal device with multiple optional time units or time period lengths via the second indication information, thereby reducing unnecessary overhead in reporting predictive information.

[0008] In one possible design, the number N of prediction information may be preset locally on the terminal device, or it may be indicated or configured by the network device; this application does not limit this. For example, if the number N of prediction information is indicated or configured by the network device, the second indication information includes the number N of prediction information, or the number N of prediction information may be indicated to the terminal device in other indication information.

[0009] In one possible design, the first report also indicates a first time unit and / or a first time period length. That is, when sending the first report, the terminal device may also report the first time unit and / or the first time period length selected by the terminal device along with the prediction information to the network device, so that the network device can detect the prediction information according to the time unit or time period length selected by the terminal device.

[0010] In one possible design, the time interval between any two adjacent predictions among the N predictions is the first time unit; or, the time interval length corresponding to any one prediction among the N predictions is the first time unit, and the time intervals corresponding to any two adjacent predictions among the N predictions are temporally continuous and do not overlap; or, the time interval between the earliest prediction and the latest prediction among the N predictions is less than or equal to the first time interval length; or, the sum of the lengths of the time intervals corresponding to each prediction among the N predictions is the first time interval length, and the time intervals corresponding to any two adjacent predictions among the N predictions are temporally continuous and do not overlap.

[0011] In one possible design, the method further includes: if the first prediction task is a periodic or semi-persistent task, and each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, and the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report, then at least one of the following is executed: ignoring the transmission of the report of the Yth period; or, sending third indication information, the third indication information being used to indicate ignoring the transmission of the N prediction information corresponding to the Yth period; where X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1. This design is equivalent to the situation where, when the terminal device switches to a larger time unit to perform the prediction task, the prediction information in the current reporting period may be the same as the prediction information in a subsequent reporting period, resulting in duplicate reporting of prediction information. When the terminal device recognizes that the prediction information for a certain prediction has already been included in the previous reporting period, the terminal device can ignore the reporting of that prediction information to reduce reporting overhead.

[0012] In one possible design, the method further includes: receiving fifth indication information, which indicates a period in which sending prediction information is allowed to be ignored, or a period in which the prediction information corresponding to the previous period is allowed to be reused, or a period in which sending prediction information is not allowed to be ignored, or a period in which the prediction information corresponding to the report of the previous period is not allowed to be reused. This design is equivalent to allowing network devices to specify that, in order to prevent network devices from missing prediction information, terminal devices can only not report or indicate reuse in certain locations, or can specify that they cannot not report or indicate reuse in certain locations.

[0013] In one possible design, the first report also indicates one or more measurement information; the one or more measurement information is used to predict N prediction information. That is, in this design, the first report can carry not only prediction information but also measurement information. This method of reporting measurement information and prediction information simultaneously in one report can reduce the number of times the terminal device reports.

[0014] In one possible design, capability information is sent, which includes at least one of the following: supported time units, supported number of prediction messages, and supported time period lengths. This allows network devices to configure the time unit, number of prediction messages, or time period length based on the terminal device's capability information when configuring via the second indication information, thus avoiding mismatches between the configuration information and the terminal device's capabilities.

[0015] In one possible design, the first time unit is determined by the terminal device from at least two candidate time units. Further, the first time unit is determined based on the at least two candidate time units and the current signal change rate of the terminal device. The faster the signal change rate, the shorter the first time unit; conversely, the slower the signal change rate, the longer the first time unit. This means the terminal device can flexibly select an appropriate first time unit for prediction based on the current signal change rate. Therefore, a larger first time unit effectively reduces the amount of prediction information reported by the terminal device, resulting in lower reporting overhead.

[0016] In one possible design, the length of the first time period is determined by the terminal device from at least two candidate time period lengths. Further, the length of the first time period is determined based on the at least two candidate time period lengths and the current signal change rate of the terminal device. The faster the signal change rate, the shorter the first time period length; conversely, the slower the signal change rate, the longer the first time period length.

[0017] In one possible design, the method further includes: receiving second indication information sent by the network device, the second indication information indicating at least one of the following: the period for the terminal device to report prediction information, the measurement period, the minimum candidate time unit for prediction, or the minimum candidate time period length. This could be because when the network device receives large time units of indication from the terminal device for a continuous period, it indicates that the signal change rate is slow over a relatively long period. In this case, the network device can proactively adjust the period for reporting prediction information, the measurement period, the minimum candidate time unit for prediction, or the minimum candidate time period length, so that the terminal device reports according to the updated information.

[0018] Secondly, a prediction method is provided. Optionally, the executing entity of this method can be a terminal device, a component or device applied to the terminal device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the terminal device's functions. The method includes: receiving first indication information, the first indication information being used to instruct the execution of a first prediction task; determining a first time unit, the first time unit being one of at least two candidate time units; and / or determining a first number of prediction information, the first number of prediction information being one of at least two candidate numbers of prediction information; determining a first time period corresponding to the first prediction task; determining a first report corresponding to the first prediction task based on at least two of the first time unit, the number of first prediction information, or the first time period, the first report including K prediction information, where K is a positive integer; and sending the first report.

[0019] Therefore, in this application, compared to existing methods that report prediction information using fixed time units and fixed numbers of prediction information, which can lead to the problem of identical prediction information at multiple moments when the signal change rate of the terminal device is slow, resulting in wasted reporting overhead, the terminal device in this application can flexibly choose from at least two candidate time units and / or at least two candidate numbers of prediction information when the reporting period or the first time period is fixed. For example, when the signal change rate of the terminal device is slow, a larger first time unit or a smaller number of prediction information can be selected for prediction information reporting. In this way, within the same time length, when the terminal device selects a larger time unit, it is equivalent to reducing the number of prediction information reported, thereby reducing the measurement overhead and reporting overhead of the terminal device.

[0020] In one possible design, the method further includes receiving second indication information, which indicates at least two candidate time units or at least two candidate prediction information numbers. Thus, when the network device provides the terminal device with multiple optional time units or prediction information numbers through the second indication information, the terminal device can flexibly select the reporting time unit to reduce unnecessary prediction information reporting overhead.

[0021] In one possible design, the second indication information is also used to indicate a first time period. Alternatively, the first time period may be sent to the terminal device by the network device before or after the second indication information. Alternatively, the first time period may be preset by the protocol. The first time period can be understood as the time window corresponding to a single report from the terminal device, or the effective time period corresponding to the predicted information included in a single report from the terminal device.

[0022] In one possible design, the second indication information is also used to indicate the length of the first time period. Alternatively, the length of the first time period can be sent to the terminal device by the network device before or after the second indication information. Alternatively, the length of the first time period is preset by the protocol. The length of the first time period can be understood as the length of the time window corresponding to a single report from the terminal device, or the length of the effective time period corresponding to the predicted information included in a single report from the terminal device. In other words, the length of the first time period is the length of the first time segment.

[0023] In one possible design, the first report also indicates a first time unit and / or the number of first prediction information items. That is, when sending the first report, the terminal device may also report the first time unit and / or the number of first prediction information items selected by the terminal device along with the prediction information to the network device, so that the network device can detect the prediction information according to the time unit or the number of prediction information items selected by the terminal device.

[0024] In one possible design, the first time unit is determined by the terminal device from at least two candidate time units. Further, the first time unit is determined based on the at least two candidate time units and the current signal change rate of the terminal device. The faster the signal change rate, the shorter the first time unit; conversely, the slower the signal change rate, the longer the first time unit. This means the terminal device can flexibly select an appropriate first time unit for prediction based on the current signal change rate. Therefore, a larger first time unit effectively reduces the amount of prediction information reported by the terminal device, resulting in lower reporting overhead.

[0025] In one possible design, the number of first predicted information items is determined by the terminal device from at least two candidate first predicted information item numbers. Further, the number of first predicted information items is determined based on the number of at least two candidate predicted information items and the current signal change rate of the terminal device. The faster the signal change rate, the larger the number of first predicted information items; conversely, the slower the signal change rate, the smaller the number of first predicted information items.

[0026] In one possible design, the time period corresponding to the K prediction information is the first time period, or the time period corresponding to each of the K prediction information is included in the first time period.

[0027] In one possible design, the time interval between any two adjacent predictions among the K predictions is the first time unit; or, the length of the time interval corresponding to any one of the K predictions is the first time unit, and the time intervals corresponding to any two adjacent predictions among the K predictions are temporally continuous and do not overlap; or, K is equal to the number of the first predictions, where K is a positive integer.

[0028] In one possible design, the first report comprises a first part and a second part; the first part indicates a first time unit, and the second part indicates K prediction information; or, the first part indicates the number of first prediction information items, and the second part indicates the K prediction information items; the number of bits included in the second part is determined according to the first part. This design takes into account that the number K of the first prediction information items selected by the terminal device is variable, and the number of bits in the second part is also variable.

[0029] In one possible design, the K predictions in the second part are arranged in chronological order, meaning the first prediction corresponds to the earliest time or time period. This eliminates the overhead of reporting the timestamp for each prediction, allowing the network device to know the time or time period corresponding to each prediction.

[0030] In one possible design, the method further includes: if the first prediction task is a periodic or semi-persistent task, and the first report is the report for the Xth period, and the prediction information corresponding to the Yth period after the Xth period is the same as the latest prediction information among the K prediction information in the first report, then at least one of the following is executed: ignoring the transmission of the report for the Yth period; or, sending a third indication information, which indicates that the number of prediction information corresponding to the Yth period is 0; or, sending a fourth indication information, which indicates that the transmission of the prediction information corresponding to the Yth period is ignored; where X and Y are positive integers. This avoids the terminal device repeatedly reporting prediction information, reducing the reporting overhead of the terminal device.

[0031] In one possible design, the method further includes: receiving fifth indication information, which indicates a period in which sending prediction information is allowed to be ignored, or a period in which the prediction information corresponding to the previous period is allowed to be reused, or a period in which sending prediction information is not allowed to be ignored, or a period in which the prediction information corresponding to the report of the previous period is not allowed to be reused. This design is equivalent to allowing network devices to specify that, in order to prevent network devices from missing prediction information, terminal devices can only not report or indicate reuse in certain locations, or can specify that they cannot not report or indicate reuse in certain locations.

[0032] In one possible design, the first report also indicates one or more measurement information; the one or more measurement information is used to predict N prediction information. That is, in this design, the first report can carry not only prediction information but also measurement information. This method of reporting measurement information and prediction information simultaneously in one report can reduce the number of times the terminal device reports.

[0033] In one possible design, capability information is sent, which includes at least one of the following: supported time units, supported number of prediction messages, and supported time period lengths. This allows network devices to configure the time unit, number of prediction messages, or time period length based on the terminal device's capability information when configuring via the second indication information, thus avoiding mismatches between the configuration information and the terminal device's capabilities.

[0034] Thirdly, a communication device is provided. Optionally, the communication device may be a terminal device, a component or device applied to the terminal device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. It includes: a receiving unit for receiving first indication information, the first indication information being used to instruct the execution of a first prediction task; a processing unit for determining a first time unit, the first time unit being one of at least two candidate time units; and / or determining a first time period length, the first time period length being one of at least two candidate time period lengths; the processing unit is further configured to determine the number N of prediction information contained in each of at least one report corresponding to the first prediction task, N being a positive integer; the processing unit is further configured to determine a first report corresponding to the first prediction task based on at least two of the first time unit, the first time period length, or N, the first report being one of at least one report, the first report including N prediction information; and a sending unit for sending the first report.

[0035] In one possible design, the receiving unit is further configured to receive second indication information, which indicates at least two candidate time units or at least two candidate time period lengths.

[0036] In one possible design, the first report is also used to indicate the first time unit and / or the length of the first time period.

[0037] In one possible design, the time interval between any two adjacent predictions among the N predictions is the first time unit; or, the time interval length corresponding to any one prediction among the N predictions is the first time unit, and the time intervals corresponding to any two adjacent predictions among the N predictions are temporally continuous and do not overlap; or, the time interval between the earliest prediction and the latest prediction among the N predictions is less than or equal to the first time interval length; or, the sum of the lengths of the time intervals corresponding to each prediction among the N predictions is the first time interval length, and the time intervals corresponding to any two adjacent predictions among the N predictions are temporally continuous and do not overlap.

[0038] In one possible design, the sending unit is further configured to: if the first prediction task is a periodic task or a semi-persistent task, and each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, and the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report, perform at least one of the following: ignore sending the report of the Yth period; or, send third indication information, the third indication information being used to indicate that the N prediction information corresponding to the Yth period should be ignored; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

[0039] In one possible design, the first report is also used to indicate one or more measurement information; the one or more measurement information is used to predict the prediction information corresponding to the first time unit; or, the one or more measurement information is used to predict the prediction information corresponding to the first time period length.

[0040] In one possible design, the first time unit is determined based on at least two candidate time units and the current signal change rate of the terminal device. The faster the signal changes, the shorter the first time unit; conversely, the slower the signal changes, the longer the first time unit.

[0041] In one possible design, the first report is also used to indicate one or more measurement information. The one or more measurement information is used to predict the prediction information corresponding to the first time unit; or, the one or more measurement information is used to predict the prediction information corresponding to the number of first prediction information items.

[0042] In one possible design, the first report also includes measurement information obtained from signal measurements performed at the measurement time. The system receives second indication information sent by the network device, which indicates at least one of the following: the period for the terminal device to report prediction information, the period for performing signal measurements, the minimum candidate time unit for signal prediction, or the minimum candidate time period length.

[0043] Fourthly, a communication device is provided. Optionally, the communication device may be a terminal device, a component or device applied to the terminal device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. The communication device includes: a receiving unit for receiving first indication information, the first indication information being used to instruct the execution of a first prediction task; a processing unit for determining a first time unit, the first time unit being one of at least two candidate time units; and / or determining a number of first prediction information items, the number of first prediction information items being one of at least two candidate prediction information item numbers; the processing unit is further configured to determine a first time period corresponding to the first prediction task; the processing unit is further configured to determine a first report corresponding to the first prediction task based on at least two of the first time unit, the number of first prediction information items, or the first time period, the first report including K prediction information items, where K is a positive integer; and a sending unit for sending the first report.

[0044] In one possible design, the receiving unit is further configured to receive second indication information, which indicates at least two candidate time units or the number of prediction information for at least two candidates.

[0045] In one possible design, the first report is also used to indicate the first time unit and / or the number of first prediction messages.

[0046] In one possible design, the time period corresponding to the K prediction information is the first time period, or the time period corresponding to each of the K prediction information is included in the first time period.

[0047] In one possible design, the time interval between any two adjacent predictions among the K predictions is the first time unit; or, the length of the time interval corresponding to any one of the K predictions is the first time unit, and the time intervals corresponding to any two adjacent predictions among the K predictions are temporally continuous and do not overlap; or, K is equal to the number of the first predictions, where K is a positive integer.

[0048] In one possible design, the first report includes a first part and a second part; the first part is used to indicate a first time unit, and the second part is used to indicate K prediction information; or, the first part is used to indicate the number of first prediction information, and the second part is used to indicate K prediction information; the number of bits included in the second part is determined according to the first part.

[0049] In one possible design, the sending unit is further configured to, if the first prediction task is a periodic task or a semi-persistent task, the first report is the report of the Xth period, and the prediction information corresponding to the Yth period after the Xth period is the same as the latest prediction information among the K prediction information of the first report, perform at least one of the following: ignore sending the report of the Yth period; or, send a third indication information, the third indication information being used to indicate that the number of prediction information corresponding to the Yth period is 0; or, send a fourth indication information, the fourth indication information being used to indicate that the prediction information corresponding to the Yth period is ignored; X and Y are positive integers.

[0050] In one possible design, the receiving unit is further configured to receive fifth indication information, which indicates a period in which the transmission of prediction information is allowed to be ignored, or a period in which the reuse of prediction information corresponding to the previous period is allowed, or a period in which the transmission of prediction information is not allowed to be ignored, or a period in which the reuse of prediction information corresponding to the report of the previous period is not allowed.

[0051] In one possible design, the transmitting unit is also used to transmit capability information, which includes at least one of the following: supported time units, supported number of prediction information items, and supported time period length.

[0052] Fifthly, a prediction method is provided. Optionally, the executing entity of the method can be a network device, a component or device applied to the network device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device. The method includes: sending first indication information, the first indication information being used to instruct the execution of a first prediction task; receiving a first report, the first report being obtained by executing the first prediction task based on at least two of a first time unit, a first time period length, or N, where N is a positive integer, the first time unit is one of at least two candidate time units, the first time period length is one of at least two candidate time period lengths, and N is the number of prediction information items contained in each of the at least one report corresponding to the first prediction task. The first report is one of at least one reports, and the first report includes N prediction information items.

[0053] For the beneficial effects of the fifth aspect, please refer to the explanation of the first aspect.

[0054] In one possible design, the method further includes sending a second indication message, which indicates at least two candidate time units or at least two candidate time period lengths.

[0055] In one possible design, the first report is also used to indicate a unit of time, and / or, the length of a first time period.

[0056] In one possible design, the method further includes: receiving third indication information, the third indication information being used to indicate ignoring the transmission of N prediction information corresponding to the Y-th period, wherein the first prediction task is a periodic task or a semi-persistent task, each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the X-th period, and the time period corresponding to the Y-th period after the X-th period is included in the time period corresponding to the N prediction information in the first report; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

[0057] Sixthly, a prediction method is provided. Optionally, the executing entity of the method can be a network device, a component or device applied to the network device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device. The method includes: sending first indication information, the first indication information being used to instruct the execution of a first prediction task; receiving a first report, the first report being obtained based on at least two of the following: a first time unit, a first number of prediction information items, or a first time period, all of which are derived from executing the first prediction task. The first time unit is one of at least two candidate time units, the first number of prediction information items is one of at least two candidate prediction information item numbers, and the first time period is the time period of the first prediction task.

[0058] For the beneficial effects of the sixth aspect, please refer to the explanation of the second aspect.

[0059] In one possible design, the method further includes: sending a second indication message, the second indication message being used to indicate at least two candidate time units or the number of prediction messages for at least two candidates.

[0060] In one possible design, the method further includes: receiving a third indication message, which indicates that the number of prediction messages corresponding to the Y-th period is 0; or, receiving a fourth indication message, which indicates that the prediction message corresponding to the Y-th period should be ignored; wherein, the first prediction task is a periodic task or a semi-persistent task, the first report is the report of the X-th period, and the prediction message corresponding to the Y-th period after the X-th period is the same as the latest prediction message among the K prediction messages in the first report; X and Y are positive integers.

[0061] In one possible design, the method further includes: sending a fifth indication message, which indicates a period in which sending prediction information is allowed to be ignored, or a period in which the prediction information corresponding to the previous period is allowed to be reused, or a period in which sending prediction information is not allowed to be ignored, or a period in which the prediction information corresponding to the report of the previous period is not allowed to be reused.

[0062] In a seventh aspect, a communication device is provided. Optionally, the communication device may be a network device, a component or apparatus applied to a network device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device. The communication device includes: a transmitting unit for transmitting first indication information, the first indication information being used to instruct the execution of a first prediction task; and a receiving unit for receiving a first report, the first report being obtained by executing the first prediction task based on at least two of a first time unit, a first time period length, or N, where N is a positive integer, the first time unit is one of at least two candidate time units, the first time period length is one of at least two candidate time period lengths, and N is the number of prediction information items contained in each of the at least one report corresponding to the first prediction task. The first report is one of at least one reports, and the first report includes N prediction information items.

[0063] In one possible design, the sending unit is also used to send second indication information, which indicates at least two candidate time units or at least two candidate time period lengths.

[0064] In one possible design, the first report is also used to indicate the first time unit and / or the length of the first time period.

[0065] In one possible design, the receiving unit is further configured to: receive third indication information, the third indication information being used to indicate ignoring the transmission of N prediction information corresponding to the Yth period, wherein the first prediction task is a periodic task or a semi-persistent task, each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, and the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

[0066] Eighthly, a communication device is provided. Optionally, the communication device may be a network device, a component or apparatus applied to a network device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device. The communication device includes: a transmitting unit for transmitting first indication information, the first indication information being used to instruct the execution of a first prediction task; and a receiving unit for receiving a first report, the first report being obtained by executing the first prediction task based on at least two of the following: a first time unit, a first number of prediction information items, or a first time period. The first time unit is one of at least two candidate time units, the first number of prediction information items is one of at least two candidate prediction information item numbers, and the first time period is the time period of the first prediction task.

[0067] In one possible design, the transmitting unit is also used to transmit second indication information, which indicates at least two candidate time units or the number of prediction information for at least two candidates.

[0068] In one possible design, the receiving unit is further configured to: receive a third indication information, which indicates that the number of prediction information corresponding to the Y-th period is 0; or, receive a fourth indication information, which indicates that the prediction information corresponding to the Y-th period should be ignored; wherein, the first prediction task is a periodic task or a semi-persistent task, the first report is the report of the X-th period, and the prediction information corresponding to the Y-th period after the X-th period is the same as the latest prediction information among the K prediction information in the first report; X and Y are positive integers.

[0069] In one possible design, the sending unit is further configured to: send a fifth indication message, which indicates a period in which sending prediction information is allowed to be ignored, or a period in which the prediction information corresponding to the previous period is allowed to be reused, or a period in which sending prediction information is not allowed to be ignored, or a period in which the prediction information corresponding to the report of the previous period is not allowed to be reused.

[0070] A ninth aspect provides a communication device including at least one processor connected to a memory, the at least one processor being configured to read and execute a program stored in the memory such that the device performs the method described in the first aspect or any possible design of the first aspect, and / or the method described in the second aspect or any possible design of the second aspect.

[0071] In a tenth aspect, a communication device is provided, comprising at least one processor connected to a memory, the at least one processor being configured to read and execute a program stored in the memory such that the device performs the method described in the fifth aspect or any possible design of the fifth aspect, and / or, the method described in the sixth aspect or any possible design of the sixth aspect.

[0072] Eleventhly, a communication system is provided, comprising a first communication device as described in the third and / or fourth aspects, and a second communication device as described in the eighth and / or ninth aspects.

[0073] In a twelfth aspect, a computer-readable storage medium is provided, wherein computer instructions are stored therein, which, when executed on a communication device, cause the communication device to perform the method described in the first aspect or any possible design of the first aspect, and / or the method described in the second aspect or any possible design of the second aspect, and / or the method described in the fifth aspect or any possible design of the fifth aspect, and / or the method described in the sixth aspect or any possible design of the sixth aspect.

[0074] In a thirteenth aspect, a chip is provided that stores computer execution instructions, wherein when the computer execution instructions are executed, the method described in the first aspect or any possible design of the first aspect, and / or the method described in the second aspect or any possible design of the second aspect, and / or the method described in the fifth aspect or any possible design of the fifth aspect, and / or the method described in the sixth aspect or any possible design of the sixth aspect is executed. Attached Figure Description

[0075] Figure 1 A schematic diagram of AI-based beam management provided for embodiments of this application;

[0076] Figure 2 A schematic diagram of a communication system provided in an embodiment of this application;

[0077] Figure 3 This is a schematic diagram of a possible application framework provided for an embodiment of this application;

[0078] Figure 4 This is a schematic diagram of a possible application framework provided for an embodiment of this application;

[0079] Figure 5 A schematic diagram of time-domain beam prediction for aperiodic reporting (AP) and periodic / semi-persistent (P / SP) reporting provided for embodiments of this application;

[0080] Figure 6This is a schematic diagram of beam prediction information reporting provided in an embodiment of this application;

[0081] Figure 7 A flowchart illustrating a prediction method provided in an embodiment of this application;

[0082] Figure 8 This is a schematic diagram of a beam prediction scenario provided in an embodiment of this application;

[0083] Figure 9 A schematic diagram of a first report submission format provided in an embodiment of this application;

[0084] Figure 10 A schematic diagram of a periodic / semi-persistent reporting method provided for an embodiment of this application;

[0085] Figure 11 A schematic diagram of a periodic / semi-persistent reporting method provided for an embodiment of this application;

[0086] Figure 12 This application provides a schematic diagram of a report submission method.

[0087] Figure 13 A flowchart illustrating a prediction method provided in an embodiment of this application;

[0088] Figure 14 A schematic diagram illustrating a periodic or semi-continuous reporting method provided for an embodiment of this application;

[0089] Figure 15 A schematic diagram of a first report submission format provided in an embodiment of this application;

[0090] Figure 16 This is a schematic diagram illustrating an embodiment of the present application that does not report prediction information;

[0091] Figure 17 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0092] Figure 18 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0093] For ease of understanding, the examples provide explanations of some concepts related to the embodiments of this application for reference, as shown below.

[0094] Artificial intelligence (AI) refers to the ability to endow machines with human-like intelligence, such as enabling machines to use computer hardware and software to simulate certain intelligent human behaviors. Machine learning (ML) is an important technological approach to achieving AI. In machine learning methods, machines learn (or train) models using training data. These models represent the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result). The model can also be called an AI model, an ML model, a rule, or other names. An AI model can be considered a specific method for implementing a certain AI function; the AI ​​model represents the mapping relationship or function between the model's input and output. Machine learning can be divided into supervised learning, unsupervised learning, and reinforcement learning.

[0095] Machine learning: learning models or rules from raw data. There are many different machine learning methods, such as neural networks, decision trees, and support vector machines.

[0096] AI model: This refers to a function model that maps an input of a certain dimension to an output of a certain dimension, and its parameters are obtained through machine learning training. For example, f(x) = ax^2 + b is a quadratic function model, which can be regarded as an AI model. a and b correspond to the parameters of the model and can be obtained through machine learning training.

[0097] Neural network: Here it refers to artificial neural network, which is a mathematical model that imitates the behavioral characteristics of animal neural networks to perform distributed parallel information processing. It is a special form of AI model.

[0098] Dataset: The data used for model training, validation, and testing in machine learning. The quantity and quality of the data will affect the effectiveness of machine learning.

[0099] Model training: By selecting an appropriate loss function, the model parameters are trained using optimization algorithms to minimize the loss function value.

[0100] Channel state information (CSI) feedback: In existing Long Term Evolution (LTE) and New Radio (NR) communication systems, network devices need to acquire downlink CSI to determine the resources, modulation and coding scheme (MCS), precoding, and other configurations for scheduling downlink data channels for terminal devices. In Time Division Duplex (TDD) systems, due to the reciprocity of uplink and downlink channels, network devices can obtain uplink CSI by measuring uplink reference signals and then infer a more accurate downlink CSI, for example, using the uplink CSI as the downlink CSI. In frequency division duplex (FDD) systems, uplink and downlink reciprocity cannot be guaranteed. Downlink CSI is obtained by the terminal equipment by measuring downlink reference signals, such as channel state information reference signals (CSI-RS) or synchronizing signal / physical broadcast channel blocks (SSB). Therefore, the terminal equipment needs to generate a CSI report according to the protocol predefined method or the base station configuration, and feed the CSI back to the base station so that it can obtain the downlink CSI.

[0101] In the NR protocol, the configuration and reporting process of downlink CSI is as follows: 1) The network device sends a CSI reporting configuration (CSI-ReportConfig) to the terminal device, specifying the reporting type (reportConfigType), reporting quantity (reportQuantity), etc. The reporting type can be periodic, semi-persistent, or aperiodic, and the reporting quantity can be a rank indicator (RI), channel quality indicator (CQI), precoding matrix indicator (PMI), reference signal received power (RSRP), etc.; 2) The network device sends a CSI-RS to the terminal device, and the terminal device performs channel measurement and interference measurement based on the CSI-RS to obtain the measurement results; 3) Based on the measurement results, the terminal device determines the reporting quantities to be configured and reports the downlink CSI to the network device. This downlink CSI includes information such as RI, CQI, PMI, and RSRP measured by the terminal. If the reporting type in CSI-ReportConfig is configured as periodic, the terminal device reports periodically according to the period specified in the radio resource control (RRC) signaling, without needing to trigger reporting with each signaling transmission. If the reporting type in CSI-ReportConfig is configured as semi-persistent, the initial reporting needs to be triggered by signaling, and once triggered, it reports periodically according to the specified period. If the reporting type in CSI-ReportConfig is configured as non-periodic, then downlink control information (DCI) is required to trigger reporting. Semi-static CSI reporting triggering is more complex. When CSI reports on the physical uplink control channel (PUCCH), triggering uses media access control element (MAC CE) signaling, while when CSI reports on the physical uplink shared channel (PUSCH), triggering uses DCI.

[0102] CSI Reporting Method: The NR protocol specifies the CSI reporting method. A CSI report can be divided into two parts: Part 1 and Part 2. The number of bits in Part 1 is fixed, and the number of bits in Part 2 can be determined based on the content of Part 1. This method can be applied when the number of uplink transmission bits is uncertain, avoiding always using the maximum possible number of uplink transmission bits for feedback, thus saving uplink transmission overhead. For example, for a CSI report configured with RI, CQI, and PMI, Part 1 can contain RI and the first codeword's CQI, and Part 2 can contain the second codeword's CQI and PMI. The number of bits for RI and CQI is specified by the protocol, and the number of bits for PMI can be determined based on RI. Therefore, the base station can determine the number of bits in Part 2 after receiving Part 1. A CSI report can also contain only Part 1, for example, when the reporting quantity is configured as RSRP. This method is suitable for situations where the number of uplink transmission bits is certain.

[0103] Beam Management: NR systems employ beamforming technology, which weights the transmitted signal to create narrower beams with more concentrated energy and stronger directionality for each type of channel and signal. At the same transmit power, narrow beams provide farther coverage than wide beams, but their coverage is limited; a single beam cannot cover all users within a cell, nor can it guarantee that every user receives maximum signal energy. Therefore, the protocol introduces beam scanning. Beam scanning refers to transmitting or receiving beams in a preset manner at time intervals to cover a specific spatial area. Currently, the preset method mainly refers to time-division multiplexing, which improves coverage performance by transmitting or receiving narrow beams in different directions at different times to cover a specific spatial area. Based on the weighting strategy used in beamforming, beamforming is divided into two categories: static beams and dynamic beams. Static beams use predefined weights, meaning a fixed beam is formed within the cell; for example, the number, width, and direction of the beams are determined. Then, based on cell coverage, user distribution, system load, and other information, the optimal beam is selected for each type of channel and signal. Dynamic beamforming refers to beamforming where the weights are calculated based on channel quality, and the beamwidth and direction are adjusted dynamically according to factors such as the location of the user equipment (UE) and channel conditions. Beam scanning is mainly for static beams that use preset weights; dynamic beams, because they use dynamic weights, do not require beam scanning.

[0104] The beam scanning process combines beam measurement, beam reporting, and beam determination to select an optimal beam pair between the base station and the UE. For example, for downlink transmission, beam scanning can find the most suitable transmit and receive beams, aligning the transmit and receive beam directions to achieve optimal receive signal gain and improve communication quality. Specifically, the beam scanning process consists of three steps: P1, P2, and P3.

[0105] P1 Process: The base station performs SSB beam scanning, and the UE performs wide-beam scanning. The base station transmits SSBs using beam scanning, sending SSB beams from different directions in a time-division manner to broadcast synchronization and system messages. The UE receives signals using beam scanning, confirming the received beam. Simultaneously, the UE feeds back the SSB measurement results to the base station, which confirms the transmitted beam. The transmitted and received beams achieve initial alignment. The main purpose of P1 is to find an initial beam pair between the base station and the UE.

[0106] P2 Procedure: The base station performs a CSI-RS beam scan, while the UE's receive beam remains fixed. The base station then scans the area around the SSB beam determined by random access using a narrower CSI-RS beam. The UE feeds back the CSI-RS measurement results to the base station via a measurement report, and the base station confirms the optimal transmit beam. The P2 procedure refines the base station's transmit beam; after the initial beam pair is established, a narrower CSI-RS beam than the SSB beam is selected for beam adjustment to achieve higher signal gain.

[0107] P3 Process: The base station's transmit beam is fixed, and the UE performs narrow beam scanning. The base station's CSI-RS uses a fixed narrow beam, while the UE uses beam scanning for signal reception to confirm a more accurate receive beam. The transmit and receive beams are then finally aligned. The P3 process refines the UE's receive beam, enhancing signal quality through further adjustments.

[0108] As can be seen, beam scanning uses SSB or CSI-RS (CSI-RS for beam measurement) as reference signals for beam measurement. These reference signals are signals known to the terminal equipment, and each reference signal corresponds to a beam. The terminal equipment measures these reference signals and reports their index and / or measurement information to achieve beam management. Therefore, the beam measurement and reporting process is consistent with the CSI configuration and reporting process. For example, during P2, the base station configures the reportQuantity field in CSI-ReportConfig as CRI-RSRP, instructing the UE to report the CRI and its corresponding RSRP.

[0109] Air Interface AI: AI has been introduced into wireless communication networks and is widely used in many application scenarios of air interface technology, such as CSI feedback, CSI prediction, beam management, and positioning. For example, when applying AI in CSI feedback scenarios, an autoencoder architecture can be used for CSI feedback. An autoencoder architecture generally includes an AI encoder and an AI decoder. The AI ​​encoder can be deployed on the terminal device, and the AI ​​decoder can be deployed on the network device. Compared to traditional CSI feedback technology, AI model-based CSI feedback, while maintaining the same CSI feedback performance, can reduce air interface feedback overhead and the computational complexity of the terminal device, showing greater application potential. For example, when applying AI in CSI prediction scenarios, the terminal device or network device can use a prediction model to predict the CSI at future times based on historical CSI and feed it back to the network device. The AI ​​model can reside solely in the terminal device or solely in the network device. By accurately predicting the CSI at future times, the problem of inaccurate CSI feedback information caused by channel time-varying characteristics can be solved. For example, when applying AI in beam management scenarios, terminal devices or network devices can efficiently and accurately identify the best beam using AI models. This AI model can reside solely in the terminal device or solely in the network device. For example, when applying AI models in positioning scenarios, triangulation can be used for location. The terminal device obtains the location information of three surrounding network devices and inputs it into the corresponding AI model. Then, based on the distance, direction, and channel information from the terminal device to the three network devices, the location of the terminal device is obtained.

[0110] Specifically, AI-based beam management includes two typical use cases: spatial beam prediction and temporal beam prediction. For example... Figure 1 The diagram illustrates AI-based beam management. Spatial beam prediction is used, for example... Figure 1 As shown in (a) above, traditional beam measurement requires scanning all beams in the selectable beam set using a P1-P3 process to obtain the optimal beam (maximum RSRP). For systems using massive MIMO antennas, the selectable beam set can be very large (e.g., 1024 beams), and the traditional beam scanning process incurs significant measurement overhead. With the introduction of AI, only a subset of beams (e.g., set B) in the selectable beam set (e.g., set A) can be measured. Based on the measurements of this subset, the top-k optimal beams in the full beam set (set A) can be predicted, thus significantly reducing beam measurement overhead. Time-domain beam prediction is used, for example... Figure 1 As shown in (b) above, the AI ​​beam prediction model can utilize beam measurement information from historical moments (e.g., historical beam information i). t-2 i t-1 Predicting beam information for future moments (e.g., beam information i for future moments)t i t+1 i t+2 …including the top-k optimal beam indices and the corresponding RSRPs of the top-k optimal beams, thereby improving the robustness of beam management in scenarios with rapidly changing channels and avoiding frequent beam measurements and switching. The beam prediction model can be located in the terminal device or network device.

[0111] The technical solutions provided in this application can be applied to various communication systems, such as 5th generation (5G) or new wireless NR systems, LTE systems, LTE FDD systems, LTE TDD systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems such as 6th generation (6G) mobile communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0112] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this disclosure can be replaced by a first network element, and the network device can be replaced by a second network element, both performing the corresponding communication methods described in this disclosure.

[0113] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, leading to increasingly diverse requirements. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, AI technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced.

[0114] Figure 2 (a) in the diagram is a schematic diagram of a communication system applicable to the communication method of this application embodiment. Figure 2 As shown in (a), the communication system 200 may include at least one network device, such as Figure 2 The network device 210 shown; the communication system 200 may also include at least one terminal device, such as Figure 2 The terminal devices 220 and 230 are shown. Network device 210 can communicate with the terminal devices (such as terminal devices 220 and 230) via a wireless link. Communication devices in this communication system, for example, network device 210 and terminal device 220, can communicate using multi-antenna technology.

[0115] Figure 2 (b) is a schematic diagram of another communication system applicable to the communication method of this application embodiment. Compared to Figure 2 As for the communication system 200 shown in (a), Figure 2 The communication system 300 shown in (b) also includes an AI network element 240. The AI ​​network element 240 is used to perform AI-related operations, such as building training datasets or training AI models.

[0116] In one possible implementation, network device 210 can send data related to the training of the AI ​​model to AI network element 240, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. AI network element 240 can send the results of operations related to the AI ​​model to network device 210, which then forwards them to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 210, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 210. Or, the trained AI model may be deployed on the terminal device.

[0117] It should be understood that Figure 2 (b) is illustrated using the example of AI network element 240 being directly connected to network device 210. In other scenarios, AI network element 240 can also be connected to terminal devices. Alternatively, AI network element 240 can be connected to both network device 210 and terminal devices simultaneously. Alternatively, AI network element 240 can also be connected to network device 210 through a third-party network element. This application embodiment does not limit the connection relationship between AI network element and other network elements.

[0118] The AI ​​Element 240 can also be configured as a module in network devices and / or terminal devices, for example, configured in Figure 2 In the network device 210 or terminal device shown.

[0119] It should be noted that, Figure 2 This is a simplified illustration for ease of understanding only. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices. Figure 2 Not shown in the text. In practical applications, this communication system may include multiple network devices or multiple terminal devices. This application does not limit the number of network devices and terminal devices included in the communication system.

[0120] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0121] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0122] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on only one type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry that perform vital sign sensing.

[0123] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0124] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in 6G networks, and equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0125] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0126] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0127] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0128] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0129] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0130] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0131] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0132] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0133] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0134] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0135] AI nodes can be AI network elements or AI modules.

[0136] Figure 3 This is a schematic diagram of a possible application framework in a communication system. For example... Figure 3 As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 3 (Only one is shown in the image). The access network node can be a single RAN node or can include multiple RAN nodes, such as CU and DU. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP.

[0137] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0138] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0139] Optionally, the network device can be a network device equipped with one or more AI modules. The network device can be... Figure 3 The core network equipment, access network node (RAN node), or one or more devices in the OAM are shown. For example, the AI ​​module can be... Figure 4The RAN intelligent controller (RIC) shown can be a near real-time RIC or a non-real-time RIC. For example, a near real-time RIC is set in a RAN node (e.g., in a CU, DU), while a non-real-time RIC is set in an OAM, a cloud server, a core network device, or other network device. The RIC can obtain subsets from multiple end devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset #2, and train based on the training dataset #2. Exemplarily, the near real-time RIC and the non-real-time RIC can also be set up separately as a network element, and the network device can be either a near real-time RIC or a non-real-time RIC.

[0140] Figure 4 This is a schematic diagram of a possible application framework in the communication system of this application. For example... Figure 4 As shown, the communication system includes a RIC. For example, the RIC could be... Figure 3 The AI ​​module shown is used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (Non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0141] This near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers inference results to the DU, and the DU sends them to the RU.

[0142] This non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU; for example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0143] The near real-time RIC and the non-real-time RIC can also be configured as separate network elements. Optionally, the near real-time RIC and the non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in the CU or DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0144] For AI-based temporal prediction, if the model resides on the terminal device, the terminal device needs to report prediction information for one or more future times or time instances to the network device. Alternatively, the terminal device can report prediction information for one or more future time instances in a single report. This prediction information for one or more time instances is obtained based on the model's inference output, with each prediction corresponding to a specific time or time period. A prediction corresponding to a specific time can be understood as the prediction information being valid for that specific time, and a prediction corresponding to a specific time period can be understood as the prediction information being valid within that specific time period. For example, for AI-based temporal beam prediction, the prediction information could be: the indices of the top-k optimal beams, the RSRP of the top-k optimal beams, etc. Figure 5 (a) and Figure 5 (b) shows time-domain beam prediction diagrams for aperiodic reporting (AP) and periodic / semi-persistent (P / SP) reporting, respectively. This diagram illustrates the time when actual measured beam information is available, the time when predicted beam information is available, and a single reporting (including multiple predicted beam information). Figure 5 In example (a), the terminal device uses a measurement at time t1 to predict the beam information (t2 to t4) for the next three times. The network device configures the terminal device to report an APCSI at time t1 and the terminal device reports the predicted beam information values ​​for the next three times at time t1. Figure 5In example (b) of the example, in each cycle, the terminal device uses a measurement value at time t1 to predict the beam information for the next three times (t2 to t4). The network device configures the terminal device to report P / SP CSI, with a reporting period between t1 and t5. The terminal device periodically reports the beam information for the next three times. The predicted beam information value at each time can be understood as either a prediction value for that specific time or a prediction value that is valid for a period of time after that specific time. For example... Figure 5 In example (a), the beam information prediction value at time t2 can be considered as the predicted optimal beam information corresponding to time t2, or as the predicted optimal beam information within the time period from t2 to t3.

[0145] It is known that the terminal device performs beam prediction and reporting at fixed time intervals. However, the optimal beam change rate differs under different channel conditions (e.g., different moving speeds of the terminal device). When the beam change rate is very slow, the optimal beam prediction information for multiple time instances reported in one go may be the same, or the optimal beam prediction information for some adjacent time instances in multiple time instances may be the same, as described above. Figure 5 The reporting method shown will result in unnecessary reporting overhead for the terminal device. For example... Figure 6 Figure (a) shows a schematic diagram of beam prediction information reporting. The optimal beams at times (t2, t3, and t4) corresponding to the three beam prediction information reported at time t1 are the same. Figure 6 Figure (b) shows another type of beam prediction information reporting diagram. The three beam prediction information reported at time t1 correspond to the same optimal beam at two times (t2, t3 and t4), which also has the problem of unnecessary reporting overhead.

[0146] Therefore, this application proposes a prediction method and communication device. This method proposes a way for a terminal device to adaptively report prediction information. For example, the network device provides multiple selectable time units (i.e., time intervals between time instances) and the number N of time instances included in a single report. The terminal device adaptively selects the time unit to report prediction information for N time instances. Thus, when the time unit is larger (i.e., the time interval between time instances is larger), compared to when the time interval between time instances is smaller, the number of reported prediction information is reduced within the same time window length, thus reducing the overhead of the terminal device reporting prediction information. Furthermore, if the number of time instances included in a single report is fixed, when the time unit is larger (i.e., the time interval between time instances is larger), compared to when the time interval between time instances is smaller, the effective time window corresponding to the prediction information reported by the terminal device in a single report is longer, thus reducing measurement overhead.

[0147] Based on this, this application provides a prediction method. In this method, when a terminal device determines to perform a first prediction task, it determines the first report corresponding to the first prediction task based on multiple candidate time units, multiple candidate time periods, or multiple candidate prediction information numbers, and sends the first report. Thus, in a time-domain prediction scenario, the terminal device can adaptively determine the time unit, time period length, or number of prediction information numbers for sending the first report, instead of predicting and reporting at fixed intervals. Therefore, with the same time period length, when the time unit increases or the number of prediction information numbers decreases, it is equivalent to reducing the amount of prediction information, thereby reducing the bit overhead of the terminal device sending the report. Alternatively, with the number of prediction information numbers remaining constant, when the selected time unit increases or the time period length increases, it is equivalent to reducing the amount of prediction information within the same time window, thereby reducing the bit overhead of the terminal device sending the report.

[0148] The embodiments of this application use time-domain beam prediction as a typical use case to illustrate the invention. The method provided in this application is also applicable to other time-domain prediction scenarios, and this application does not limit it.

[0149] like Figure 7 The diagram shows a flowchart of a prediction method. Optionally, the execution subject of this method can be a terminal device, a component or device applied to the terminal device (such as a processor, chip, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device.

[0150] In this method, the terminal device can determine a suitable first time unit based on at least two candidate time units, and / or determine a suitable first time period length based on at least two candidate time period lengths, so as to generate a report corresponding to the prediction task based on at least two of the first time unit, the first time period length, or the number of prediction information. Figure 7 The illustrated process can be applied to aperiodic, periodic, or semi-continuous reporting types. For example... Figure 7 As shown, the method includes the following steps.

[0151] 701. The terminal device receives first instruction information, which is used to instruct the execution of the first prediction task.

[0152] Accordingly, the network device sends a first instruction message. The terminal device receiving the first instruction message includes: the terminal device receiving the first instruction message sent by the network device.

[0153] In some embodiments, where the first prediction task is beam prediction, the first prediction task can be understood as a beam prediction task. The first indication information is used to instruct the terminal device to perform the first prediction task, which can be understood as instructing the terminal device to perform a beam prediction task.

[0154] In some embodiments, the first indication information is further used to indicate measurement resource configuration information for the first prediction task. Alternatively, the measurement resource configuration information may be sent by the network device to the terminal device before the first indication information. The measurement resource configuration information includes an index, period, etc., of at least one measurement resource used for measurement, and the measurement resource may be a reference signal, such as an SSB or CSI-RS. The terminal device performs the first prediction task based on the measurement values ​​corresponding to the measurement resources.

[0155] In some embodiments, the first indication information is further used to indicate reporting configuration / triggering information for the first prediction task. Alternatively, the reporting configuration / triggering information may also be sent by the network device to the terminal device before the first indication information. The reporting configuration / triggering information indicates that measurement and / or prediction is performed using specified measurement resources, and that measurement information and / or prediction information is reported. The reporting configuration / triggering information includes an index of the measurement resources used for measurement and / or prediction, a reporting period, and the measurement information and / or prediction information that needs to be reported. For example, in a signal prediction scenario, the measurement information and / or prediction information that needs to be reported by the terminal device may include, for example, the indices of the top K best reference signals obtained by the terminal device from measuring multiple reference signals and / or the measured values ​​of the measurement quantities corresponding to the top K best reference signals, which may be, for example, RSRP.

[0156] In some embodiments, the terminal device receives second indication information, which indicates at least two candidate time units or at least two candidate time period lengths. The second indication information and the first indication information may be sent in a single message or in separate messages.

[0157] For example, when the second indication information is used to indicate at least two candidate time units, the second indication information includes at least two candidate time units. For example, when the second indication information is used to indicate the length of at least two candidate time periods, the second indication information includes the length of at least two candidate time periods.

[0158] In some embodiments, the second indication information may further include the number N of prediction information contained in a report sent by the terminal device, where N is a positive integer. Alternatively, the number N of prediction information may be sent to the terminal device by the network device before or after the second indication information. Alternatively, the number N of prediction information may be preset by the protocol.

[0159] For example, a time unit can be understood as the time interval between two adjacent moments corresponding to N prediction information moments, or the length of the time period corresponding to each of the N prediction information moments. A moment can be absolute time, a time slot, or a symbol, etc. When the number of moments is N, it's equivalent to a report containing N prediction information moments, with one moment corresponding to one prediction information moment. Similarly, when the number of time periods is N, it's equivalent to a report containing N prediction information moments, with one time period corresponding to one prediction information moment. For example, as... Figure 8 The diagram illustrates a beam prediction scenario. With a time unit of T1 or T2, the number of prediction times N included in a single report is 3. For example, 3 times... Figure 8 (a) shows times t2, t3, and t4, or... Figure 8 (b) shows the times t3, t5, and t7.

[0160] The time period length can be understood as the length of the time window corresponding to a single report from the terminal device. For example, the time window corresponding to a single report is... Figure 8 (a) shows the time period t1 to t4, where the length of the time period is the length between t1 and t4, including 3 time units T1, or the time window corresponding to one report. Figure 8 (b) shows the time period t1 to t7, where the time period length is the length between t1 and t7, including three time units T2. Alternatively, the time period length can be understood as the length of the effective time period corresponding to the prediction information reported by the terminal device in one transmission; for example, the time period is... Figure 8(a) shows the time period t2 to t5, where the length of the time period is the length between t2 and t5, including 3 time units T1, or the time period is... Figure 8 (b) shows the time period t3 to t9, which includes three time units T2. Furthermore, the time period corresponding to each prediction information can be understood as the effective time period corresponding to the prediction information, for example, such as... Figure 8 As shown in (a), the time periods corresponding to the three prediction information are t2~t3, t3~t4, and t4~t5, respectively. For example, the length of the time window corresponding to the prediction information included in a single report is equal to the sum of the time periods corresponding to each prediction information included in the single report. Alternatively, the length of the effective time period corresponding to the prediction information included in a single report is equal to the sum of the lengths of the effective time periods corresponding to each prediction information included in the single report.

[0161] In some embodiments, besides indicating at least two candidate time units or time period lengths in a manner similar to a list or set of time units or a list or set of time period lengths, the second indication information may also indicate a range of at least two candidate time units, including a minimum time unit and a maximum time unit. The terminal device can infer multiple candidate time units based on this time unit range according to a prediction rule. For example, the selectable time units are integer multiples of the minimum time unit and are less than or equal to the maximum time unit. Alternatively, the second indication information may also indicate a range of at least two candidate time period lengths, including a minimum time period length and a maximum time period length. The terminal device can infer multiple candidate time period lengths based on this time period length range according to a prediction rule. For example, the selectable time period lengths are integer multiples of the minimum time period length and are less than or equal to the maximum time period length. This application does not limit the manner in which the second indication information indicates at least two candidate time units or at least two candidate time period lengths.

[0162] Thus, upon receiving the first and second indication information, the terminal device can perform measurement and prediction. For example, refer to... Figure 8 The terminal device can measure the received reference signal at time t1 to obtain measurement information. Furthermore, starting from time t1, the terminal device performs predictions at preset time intervals, obtaining prediction information for multiple time intervals. The length of these time intervals can be understood as being less than or equal to the length of each of at least two candidate time units. This prediction information corresponding to small time intervals is used by the terminal device to determine the selected first time unit or the length of the first time period when it subsequently determines the prediction information to be reported.

[0163] 702. The terminal device determines a first time unit, which is one of at least two candidate time units; and / or, the terminal device determines a first time period length, which is one of at least two candidate time period lengths.

[0164] In some embodiments, the terminal device determines the first time unit and / or the length of the first time period when the number N of corresponding prediction information reported at one time is fixed.

[0165] In some embodiments, the first time unit is determined by the terminal device from at least two candidate time units.

[0166] In some embodiments, the first time unit is determined based on at least two candidate time units and the current signal change rate of the terminal device. The faster the signal change rate, the shorter the duration of the first time unit; or, the slower the signal change rate, the longer the duration of the first time unit.

[0167] For example, in a time-domain beam prediction scenario, the terminal device can determine the current signal change rate (i.e., beam change rate) based on its current moving speed or current environmental changes. For instance, a faster moving speed results in a faster beam change rate, while a slower moving speed results in a slower beam change rate. Alternatively, a faster beam change rate occurs when the current environmental changes indicate a greater number of obstacles in the environment, while a slower rate occurs when the current environmental changes indicate fewer obstacles. Alternatively, the terminal device can determine its beam change rate based on both its current moving speed and current environmental changes.

[0168] For example, in the case where the second indication information is used to indicate at least two candidate time units, the at least two candidate time units include, for instance, Figure 8 The time units shown are {T1, T2}, where T2 > T1. When the terminal device determines that the current beam change rate is relatively fast, for example, when the current beam change rate is greater than or equal to a speed threshold, the terminal device can determine the first time unit as T1; when the terminal device determines that the current beam change rate is relatively slow, for example, when the current beam change rate is less than a speed threshold, the terminal device can determine the first time unit as T2. In this way, the terminal device can flexibly choose an appropriate first time unit for prediction based on the current beam change rate, rather than predicting according to a fixed time unit. When the first time unit selected by the terminal device becomes larger, it is equivalent to reducing the amount of prediction information that the terminal device needs to report within a certain period of time, thus reducing the reporting overhead of the terminal device.

[0169] In some embodiments, the length of the first time period is determined by the terminal device from at least two candidate time period lengths.

[0170] In some embodiments, the length of the first time period is determined based on at least two candidate time period lengths and the current signal change rate of the terminal device. The faster the signal change rate, the shorter the first time period length; or, the slower the signal change rate, the longer the first time period length.

[0171] For example, when the second indication information is used to indicate at least two time period lengths, the at least two time period lengths can also be understood as at least two time window lengths. For instance, in a time-domain beamforming scenario, at least two time period lengths include, for example, Figure 8 The diagram shows {N*T1, N*T2}, where N represents the number of predicted information items (3). The time period represented by N*T2 is longer than the time period represented by N*T1. When the terminal device determines that the current beam change rate is fast, for example, when the current beam change rate is greater than or equal to a speed threshold, the terminal device can determine the first time period length as N*T1; when the terminal device determines that the current beam change rate is slow, for example, when the current beam change rate is less than a speed threshold, the terminal device can determine the first time period length as N*T2. In this way, for the terminal device, given that the number of predicted information items is N, or the number of time instances of predicted information is N, the terminal device can flexibly select an appropriate first time period length for prediction based on the current beam change rate. Optionally, the terminal device determines the first time unit based on the first time period length and N, instead of performing beam prediction according to a fixed time unit; for example, the first time unit could be the first time period length divided by N. When the first time period length selected by the terminal device increases, it is equivalent to reducing the number of predicted information items that the terminal device needs to report within a certain period, thus lowering the reporting overhead of the terminal device.

[0172] Therefore, it can be understood that, for the first time unit, in some embodiments, the time interval between any two adjacent predictions among the N predictions is the first time unit. Alternatively, the length of the time period corresponding to any one of the N predictions is the first time unit. Furthermore, the time periods corresponding to any two adjacent predictions among the N predictions are temporally continuous and do not overlap.

[0173] For example, N pieces of prediction information include Figure 8 (a) shows the prediction information for the three times t2, t3, and t4. Figure 8In (a) above, the time interval between time t2 and time t3 is the first time unit T1, and the time interval between time t3 and time t4 is also the first time unit T1. Alternatively, the length of the time period corresponding to any one of the prediction information at times t2, t3, and t4 is the first time unit T. Here, the length of the time period corresponding to any prediction information represents the effective time period of the prediction information, or in other words, the prediction information at any time within that time period is considered that prediction information. For example, the length of the time period corresponding to time t2 represents the effective time period of the prediction information at time t2 as the length of the time period between times t2 and t3, or in other words, the prediction information at any time between times t2 and t3 is considered the prediction information corresponding to time t2. Furthermore, among the prediction information at times t2, t3, and t4, the time periods corresponding to any two adjacent prediction information are continuous in time and do not overlap. That is, the time period corresponding to the prediction information at time t2 is t2~t3, and the time period corresponding to the prediction information at time t3 is t3~t4. The time period lengths t2~t3 and t3~t4 are continuous and do not overlap.

[0174] Alternatively, for the length of the first time period, the time interval between the earliest and latest prediction information among the N prediction information is less than or equal to the length of the first time period; or, the sum of the lengths of the time periods corresponding to each prediction information among the N prediction information is the length of the first time period, and the time periods corresponding to any two adjacent prediction information among the N prediction information are temporally continuous and do not overlap.

[0175] For example, for the length of the first time period, the time interval between any two adjacent predictions among the N predictions is the same. Figure 8 As shown in (a), the length of the first time period is between t1 and t4. The corresponding prediction information includes three prediction information pieces. The time interval between the earliest prediction information (time t2) and the latest prediction information (time t4) is less than or equal to the length of the first time period. In other words, the sum of the lengths of the time periods corresponding to each of the three prediction information pieces is the length of the first time period. Similarly to the above description, the time periods corresponding to any two adjacent prediction information pieces at times t2, t3, and t4 are temporally continuous and do not overlap.

[0176] In some embodiments, prior to step 702, the method may further include the terminal device sending capability information, the capability information including at least one of the following: supported time units, supported number of prediction information items, and supported time period length. Accordingly, the network device receives the capability information. Thus, the network device can determine at least two candidate time units in the second indication information, or determine the time period lengths of at least two candidates in the second indication information, based on the terminal device's capability information. For example, the network device can select some or all of the supported time units from the supported time units reported by the terminal device as at least two candidate time units, or select some or all of the supported time period lengths from the supported time period lengths reported by the terminal device as at least two candidate time period lengths. The network device can also determine a fixed number of prediction information items N based on the number of prediction information items supported by the terminal device.

[0177] 703. The terminal device determines the number N of prediction information contained in each of the at least one report corresponding to the first prediction task, where N is a positive integer.

[0178] The number N of predicted information can be understood as the number of predicted information items included in a single report, or the number of predicted information items included in a single report. If the first prediction task is a dynamically triggered task, or a non-periodic reporting task, the first prediction task corresponds to only one report, and this report contains N predicted information items. If the first prediction task is a periodic or semi-continuous reporting task, the first prediction task corresponds to multiple reports, with one report for each period, and each of these multiple reports contains N predicted information items.

[0179] In some embodiments, the number N of prediction information may be preset locally on the terminal device, or it may be indicated or configured by the network device, and this application does not limit this. For example, if the number N of prediction information is indicated or configured by the network device, the second indication information includes the number N of prediction information, or the number N of prediction information may also be indicated to the terminal device in other indication information.

[0180] 704. The terminal device determines the first report corresponding to the first prediction task based on at least two of the first time unit, the first time period length, or N. The first report is one of at least one report and includes N prediction information.

[0181] In some embodiments, when the terminal device determines a first time unit, the terminal device can determine the first report corresponding to the first prediction task based on the first time unit and the number N of prediction information. For example, the first time unit determined by the terminal device is... Figure 8 In (a) shown in the diagram, T1 is given, and the number of prediction information N is 3. The terminal device can select... Figure 8 The prediction information corresponding to times t2, t3, and t4 shown in (a) is reported to the network device in the first report. The time unit between times t1 and t2, t2 and t3, and t3 and t4 is T1.

[0182] Once the terminal device has determined the length of the first time period, it can determine the first report corresponding to the first prediction task based on the length of the first time period and the number N of prediction information. For example, the length of the first time period determined by the terminal device is... Figure 8 As shown in (b), N*T2 can be used to determine the prediction time interval T2 based on the length of the first time period and the number of prediction information N. The terminal device can select... Figure 8 The prediction information corresponding to times t3, t5, and t7 shown in (b) is reported to the network device in the first report. The time unit between times t1 and t3, t3 and t5, and t5 and t7 is T2.

[0183] Alternatively, if the terminal device has determined the first time unit and the first time period length, it can determine the first report corresponding to the first prediction task based on the first time unit and the first time period length. For example, the first time unit determined by the terminal device is... Figure 8 In (a) shown in the figure, time t1 is the measurement time, and the time length between time t1 and time t4 is the length of the first time period. When the terminal device selects the prediction information corresponding to time t2, t3 and t4 in the prediction information to report to the network device.

[0184] Alternatively, if the terminal device has determined the first time unit and the first time period length, it can determine the first report corresponding to the first prediction task based on the first time unit, the first time period length, and the number N of prediction information. For example, the first time unit determined by the terminal device is... Figure 8 In (a) shown in the figure, when time t1 is the measurement time and the time length between time t1 and time t4 is the length of the first time period, the terminal device can select three prediction information corresponding to time t2, t3 and t4 in the prediction information to report to the network device.

[0185] 705. The terminal device sends the first report.

[0186] Accordingly, the network device receives the first report.

[0187] In some embodiments, the first report is further used to indicate a first time unit or a first time period length. For example, the first report includes a first time unit or a first time period length, or the first report includes an index of the first time unit or an index of the first time period length. The first time unit can be uniquely determined based on the index of the first time unit, and the first time period length can be uniquely determined based on the index of the first time period length. Optionally, the correspondence between the index of the first time unit and the first time unit can be indicated to the terminal device by the network device, or it can be preset by the protocol. Optionally, the correspondence between the index of the first time period length and the first time period length can be indicated to the terminal device by the network device, or it can be preset by the protocol.

[0188] This can be understood as the first report including indication information for the first time unit and prediction information corresponding to the first time unit; or, the first report including indication information for the length of the first time period and prediction information corresponding to the length of the first time period.

[0189] For example, the first report includes Figure 8 (a) shows the first time unit T1 and the prediction information corresponding to the first time unit T1, and the prediction information corresponding to the first time unit T1 includes the prediction information corresponding to times t2, t3, and t4. Alternatively, the first report includes... Figure 8 (a) shows the first time period length 3*T1 and the prediction information corresponding to the first time period length 3*T1, and the prediction information corresponding to the first time period length 3*T1 includes the prediction information corresponding to times t2, t3 and t4.

[0190] In some embodiments, the number of bits in the first report sent by the terminal device is fixed. For example, the terminal device can report the first report using Part 1 format, meaning the first report only includes a first part. Figure 9 The diagram illustrates a first report format. This first report includes an indication of the time unit selected by the terminal device and N prediction information items. For example, when N is 3, the indication of the selected time unit indicates the first time unit, and the prediction information includes the three selected prediction information items. This fixed-bit-count first report format is chosen because the number N of prediction information items to be reported by the terminal device is fixed, and the network device knows the number N of prediction information items to be reported by the terminal device in advance. Using this fixed-bit-count format (Part 1) for the first report format results in higher efficiency for the network device in parsing the first report.

[0191] In some embodiments, the N prediction information items in the first report reported using the Part1 format are arranged in chronological order, meaning the first prediction information corresponds to the earliest time or time period. This eliminates the overhead of reporting the timestamp for each prediction information item, allowing the network device to know the time or time period corresponding to each prediction information item.

[0192] In some embodiments, the N prediction information in the first report reported in Part1 format is randomly arranged. Therefore, the report also needs to carry the timestamp corresponding to each prediction information so that the network device can know the time or time period corresponding to each prediction information.

[0193] In some embodiments, the first report further includes one or more measurement information. The one or more measurement information is used to predict N prediction information.

[0194] In other words, the terminal device can simultaneously report measurement information and prediction information in the first report. Of course, the measurement information and prediction information can also be reported in different reports; this application does not limit this. For example, the second instruction information is further used to instruct the terminal device to report N+M time instances at a time, where M is the number of measurement information used for prediction, or the number of time instances corresponding to the measurement information, and N is the number of predicted information obtained, or the number of time instances corresponding to the predicted information. These N prediction information are obtained based on the M measurement information.

[0195] For example, when the measurement information is reference signal measurement information, the number of reference signal measurement information is one or more. The reference signal measurement information is used to predict... Figure 8 (a) shows the prediction information corresponding to the first time unit T1. There is one measurement information, namely the measurement information corresponding to time t1, and three prediction information, namely the prediction information corresponding to times t2, t3, and t4.

[0196] Alternatively, the reference signal measurement information can be used to predict the result. Figure 8 (a) shows the prediction information corresponding to the first time period t1 to t4. There is one measurement information, namely the measurement information corresponding to time t1, and three prediction information, namely the prediction information corresponding to times t2, t3 and t4 within the first time period t1 to t4.

[0197] In some embodiments, when the network device receives large time units of instructions from the terminal device for a continuous period, it indicates that the signal change rate of the terminal device is slow over a relatively long period. In this case, the network device can directly adjust the configured reporting period, resource measurement period, minimum selectable time unit, minimum candidate time period length, etc. For example, the network device can increase the reporting period, resource measurement period, minimum selectable time unit, and minimum candidate time period length.

[0198] Therefore, in some embodiments, the method may further include: the terminal device receiving fourth indication information sent by the network device, the fourth indication information being used to update at least one of the following: the period for the terminal device to report prediction information, the period for measurement, the time unit for the smallest candidate for prediction, and the length of the smallest candidate time period. The period for reporting prediction information can be understood as the effective time length corresponding to a single report of prediction information by the terminal device.

[0199] For example, when a network device determines that the signal change rate of a terminal device is slow and below a signal change rate threshold for a relatively long period, the network device can send a fourth indication to the terminal device. This indication specifies a longer prediction information reporting period, a longer measurement period, a longer minimum candidate time unit, and a longer minimum candidate time period. This allows the network device to flexibly adjust at least one of the following: the terminal device's prediction information reporting period, measurement period, minimum candidate time unit for prediction, and minimum candidate time period length.

[0200] Therefore, in the prediction method of this application, in the time domain prediction scenario, the network device can instruct the terminal device to make predictions using the candidate time unit (i.e., the time interval of the time instance) or the candidate time period length. The terminal device can flexibly select the reporting time unit or time period according to the rate of change of the signal. When the time unit or time period increases and the number of prediction information N remains unchanged, the measurement overhead and reporting overhead of the terminal device can be reduced.

[0201] Furthermore, when the terminal device reports the first report using Part 1 format (fixed number of bits), the number of bits in the first report is fixed, based on the specific configuration of the network device, when indicating the corresponding time unit / time period length and the prediction information of N time instances. This reduces the complexity of the network device's detection report. Moreover, the first report does not need to explicitly indicate the timestamp corresponding to the prediction information, which reduces the reporting overhead of the terminal device.

[0202] As explained above, Figure 7The illustrated method embodiments can be applied to aperiodic, periodic, or semi-continuous reporting scenarios. Considering the terminal device's adaptive selection of the corresponding time unit or time period length for reporting, the predicted information for N time instances is fixed for reporting. Figure 7 The illustrated method embodiment is further enhanced for periodic or semi-continuous reporting, with the main difference being the reporting process in step 705.

[0203] This is because when network devices are configured to report periodically or semi-persistently, the information reported in a certain period may already contain the predicted information for the time instance in the next reporting period. For example... Figure 10 The diagram illustrates a periodic / semi-persistent reporting method. Figure 10 As shown, at times t1 and t2, the terminal device selects time unit T1 for reporting, and at time t3, the terminal device switches to time unit T2 for reporting. Under the condition of reporting prediction information for a fixed number of time instances, once the terminal device selects the time unit or time period length of the prediction information and the reporting period is also fixed, the terminal device will include the prediction information for times {t4, t5, t6} in the report reported at time t3.

[0204] Furthermore, according to the current reporting cycle, the terminal device also needs to report at time t5, and the reported information includes the prediction information at times {t6, t7, t8}. However, since the prediction information at time t6 has already been reported at time t3, in order to avoid duplicate reporting and further reduce reporting overhead, this application provides a possible processing solution.

[0205] In some embodiments, the method further includes: if the first prediction task is a periodic task or a semi-persistent task, and each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, and the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report, performing at least one of the following:

[0206] The terminal device ignores sending the report for the Yth period; or,

[0207] The terminal device sends a third indication message, which is used to indicate that the N prediction messages corresponding to the Yth period should be ignored; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

[0208] The time period corresponding to the Yth cycle can be understood as the time period between the start time and the end time of the Yth cycle. The terminal device ignoring the sending of the report for the Yth cycle can also be understood as the terminal device not sending the report for the Yth cycle.

[0209] In some embodiments, the method further includes: if the first prediction task is a periodic task or a semi-persistent task, each report in at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report, and one or more prediction information predicted in the Yth period is the same as the prediction information at the corresponding time in the first report, then at least one of the following is performed:

[0210] The terminal device ignores sending the report for the Yth period; or,

[0211] The terminal device sends a third indication message, which is used to indicate that the N prediction messages corresponding to the Yth period should be ignored; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

[0212] For example, if a network device continuously monitors reports submitted by terminal devices at fixed intervals, that is, if the network device assumes that terminal devices always report at fixed intervals, then... Figure 11 The diagram illustrates a periodic / semi-continuous reporting method. In a single report, the number of predicted information items N is 3, and the number of resources used for measurement in each period M is 1. The fixed detection period of the network device is (3+1)*T1. When the terminal device switches the time unit of the prediction task at time t3 (from time unit T1 to time unit T2), the first report submitted by the terminal device at time t3 is... Figure 11The report for the third reporting cycle (starting at t3 and ending at t5) shown in the diagram includes prediction information for times t4, t5, and t6. That is, the time period corresponding to the three prediction information in the first report is t4 to t7. The fourth reporting cycle following the third reporting cycle corresponds to the time period between t5 and t7. The time period between t5 and t7 is included in the time period corresponding to the prediction information at times t4, t5, and t6. It can be understood that in this case, when the terminal device sends reports according to a fixed cycle, the report submitted by the terminal device at time t5 will include the prediction information for time t6, which has already been reported at time t3. That is, the prediction information submitted at time t5 includes the prediction information for times t6, t7, and t8, and the prediction information for time t6 will be repeatedly reported. In this case, the terminal device can ignore sending the report for the fourth reporting cycle, i.e., not send a report at time t5. Alternatively, the terminal device can send a third indication message to indicate that the prediction information corresponding to the report for the fourth cycle should be ignored. This scenario is equivalent to the terminal device instructing the network device that the prediction information reported at time t5 has not changed compared to the prediction information reported at time t3, and the network device can reuse the prediction information reported at time t3. Alternatively, the terminal device can first determine at time t5 whether the prediction information at time t6 is the same as the prediction information reported at time t3. If they are the same, the terminal device can ignore sending the report for the fourth reporting cycle, i.e., it will not send a report at time t5. Or, the terminal device can send a third indication message, which indicates that the prediction information corresponding to the report for the fourth cycle should be ignored. This scenario is equivalent to the terminal device instructing the network device that the prediction information reported at time t5 has not changed compared to the prediction information reported at time t3, and the network device can reuse the prediction information reported at time t3.

[0213] Accordingly, if the terminal device determines at time t5 that the prediction information for time t6 differs from the prediction information for time t6 reported at time t3, the terminal device can report the prediction information normally at time t5, including the prediction information for times t6, t7, and t8. For the network device, if it does not detect the prediction information for time t6 at time t5, or if it detects the prediction information for time t6 but it is the same as the prediction information for time t6 reported at time t3, the network device can reuse the prediction information for time t6 reported at time t3. If the network device detects the prediction information for time t6 at time t5, it can update the prediction information for time t6 in its report at time t3.

[0214] Therefore, for terminal devices, in scenarios involving periodic or semi-continuous reporting, if the terminal device determines that the prediction information at a certain moment remains unchanged, the terminal device can ignore the reporting or instruct the reuse of the previously reported prediction information at that moment, so as to further reduce the reporting overhead of the terminal device as the time unit increases.

[0215] The above solution avoids the repeated reporting of prediction information from the perspective of the terminal device. In other embodiments, the processing can also be performed from the network device side to avoid the repeated reporting of prediction information.

[0216] In some embodiments, the network device can determine the detection / reporting cycle based on the time unit reported by the terminal device. When the time unit reported by the terminal device changes, the network device can assume that the terminal device will report according to the new reporting cycle for a period of time until the next change in the time unit. Therefore, the network device also adjusts the detection cycle according to the corresponding time unit, and uses this detection cycle until the next change in the time unit reported by the terminal device. Figure 12 The diagram illustrates a report submission process. At time t3, the time unit for reporting by the terminal device changes from T1 to T2. The network device adjusts its detection period from 4*T1 to 4*T2. With the number of predicted information items N fixed at 3, the terminal device does not report predicted information at time t5, and the network device does not detect reports at time t5. In other words, the network device does not expect the terminal device to report at time t5 until the next reporting time t7, at which point the network device checks whether a report has been submitted.

[0217] Optionally, if the network device determines that the time unit has changed, the network device may also adjust the period of the measurement resources. For example, if the network device determines that the time unit has changed, it may adjust the period of the measurement RS resources, meaning that the network device may not send reference signal resources for measurement and prediction at time t5.

[0218] In this way, in predictive scenarios, network devices can adjust the reporting detection cycle and / or measurement resource cycle according to the time unit selected by the terminal device. For network devices, it is not necessary to continuously detect according to the smallest time unit as the cycle. When the detection cycle increases, the receiving complexity of the network device can be reduced. The network device can also schedule uplink resources for times that do not need to be reported to other terminal devices, while also reducing measurement overhead.

[0219] like Figure 13The diagram shows a flowchart of a prediction method. Optionally, the execution subject of this method can be a terminal device, a component or device applied to the terminal device (such as a processor, chip, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device.

[0220] In this method, the terminal device can determine a suitable first time unit based on at least two candidate time units, and / or determine a suitable number of first prediction information based on at least two prediction information numbers, so as to generate a report corresponding to the prediction task based on at least two of the first time unit, the determined first time period, or the number of first prediction information numbers. Figure 13 The illustrated process can be applied to aperiodic, periodic, or semi-persistent reporting types. Typically, Figure 13 The illustrated process is applicable to periodic or semi-continuous reporting types because a report in one period can avoid affecting subsequent periods. For example... Figure 13 As shown, the method includes the following steps.

[0221] 1301. The terminal device receives first instruction information, which is used to instruct the execution of the first prediction task.

[0222] Accordingly, the network device receives the first instruction information.

[0223] For details on how to implement step 1301, please refer to the description of step 701.

[0224] The difference is that in some embodiments, the terminal device receives second indication information, which is used to indicate at least two candidate time units or the number of prediction information for at least two candidates.

[0225] In some embodiments, the second indication information is further used to indicate a first time period. Alternatively, the first time period may be sent to the terminal device by the network device before or after the second indication information. Alternatively, the first time period is preset by the protocol. The first time period can be understood as the time window corresponding to a single report from the terminal device, or as the effective time period corresponding to the prediction information included in a single report from the terminal device.

[0226] In some embodiments, the second indication information is further used to indicate the length of the first time period. Alternatively, the length of the first time period may be sent to the terminal device by the network device before or after the second indication information. Alternatively, the length of the first time period is preset by the protocol. The length of the first time period can be understood as the length of the time window corresponding to a single report by the terminal device, or the length of the effective time period corresponding to the prediction information included in a single report by the terminal device. That is, the length of the first time period is the length of the first time period.

[0227] For example, when the second indication information is used to indicate the number of prediction information from at least two candidates, the second indication information includes the number of prediction information from at least two candidates, and also includes a first time period. The first time period is used to indicate the effective time length or prediction window length corresponding to one report, and may also include the prediction information that needs to be reported by the terminal device at each time point. For example, such as Figure 14 The diagram illustrates a periodic or semi-persistent reporting method. The number of prediction messages for at least two candidates is, for example, [missing information]. Figure 14 (a) shows the number of the three forecast messages reported periodically, or... Figure 14 (b) shows the number of one forecast message that can be periodically reported. The first period corresponds to a first time period of t1 to t5 or t2 to t5, and the second period corresponds to a first time period of t5 to t9 or t6 to t9. The length of the first time period is the length between t1 and t5 or the length between t2 and t5.

[0228] For example, in the case where the second indication information is used to indicate at least two candidate time units, the second indication information includes at least two candidate time units, a first time period, and may also include prediction information that needs to be reported by the terminal device at each time point.

[0229] 1302. The terminal device determines a first time unit, which is one of at least two candidate time units; and / or determines a first number of prediction information, which is one of at least two candidate numbers of prediction information.

[0230] In some embodiments, the terminal device determines the first time unit and / or the number of first prediction information K when the length of the first time period corresponding to each report is fixed. Determining the number of first prediction information K means determining the number of time instances corresponding to each report, where K is a positive integer.

[0231] In some embodiments, the first time unit is determined by the terminal device from at least two candidate time units.

[0232] In some embodiments, the number of first prediction information items is determined by the terminal device from at least two candidate numbers of first prediction information items.

[0233] In some embodiments, similar to step 702, the first time unit is determined based on at least two candidate time units and the current signal change rate of the terminal device. Further, the number of first prediction information items can be determined based on the first time unit and the first time period. For example, the at least two candidate time units indicated in the second indication information include... Figure 14The {T1,T2} shown in the diagram represents the first time period corresponding to the first cycle as t1~t5 or t2~t5, and the first time period corresponding to the second cycle as t5~t9 or t6~t9. The length of the first time period T_valid = 4*T1 = 2*T2, or the length of the first time period T_valid = 3*T1 = 1*T2. When the terminal device determines that the current signal changes rapidly, it can select T1 as the first time unit. In this case, the terminal device can determine that the number of first prediction information is 3. When the terminal device determines that the current signal changes slowly, it can select T2 as the first time unit. In this case, the terminal device can determine that the number of first prediction information N is 1. That is, the number of first prediction information is equal to the value obtained by dividing the length of the first time period by the first time unit and then subtracting the number of measurement information in one cycle, or the number of first prediction information is equal to the value obtained by dividing the length of the first time period by the first time unit.

[0234] In some embodiments, the number of first prediction information items is determined based on the number of prediction information items for at least two candidates and the current signal change rate of the terminal device. Further, a first time unit can be determined based on the number of first prediction information items and a first time period. In other words, the first time unit is determined based on the number of prediction information items for at least two candidates, the current signal change rate of the terminal device, and the first time period. For example, the number of prediction information items for at least two candidates indicated in the second indication information includes... Figure 14 The {3, 1} shown in the diagram represents the first time period corresponding to the first cycle as t1~t5 or t2~t5, and the first time period corresponding to the second cycle as t5~t9 or t6~t9. The length of the first time period T_valid = 4*T1 = 2*T2, or the length of the first time period T_valid = 3*T1 = 1*T2. When the terminal device determines that the current signal changes rapidly, it can select 3 first prediction information items, in which case the terminal device can determine the first time unit as T1; when the terminal device determines that the current signal changes slowly, it can select 1 first prediction information item, in which case the terminal device can determine the first time unit as T2. That is, the first time unit is equal to the length of the first time period divided by (the number of first prediction information items plus the number of measurement information items), or the first time unit is equal to the length of the first time period divided by the number of first prediction information items.

[0235] like Figure 14As shown in (c), the terminal device can also adaptively switch the first time unit and / or the number of first prediction information items. For example, if the signal of the terminal device changes rapidly during the first time period corresponding to the previous report, the terminal device may select the first time unit as T1 or select the number of first prediction information items as 3. If the signal of the terminal device changes slowly during the first time period of the subsequent report, the terminal device may switch the first time unit to T2 at time t5 or select the number of first prediction information items as 1 to reduce the reporting overhead of the terminal device.

[0236] In some embodiments, prior to step 1302, the method may further include: the terminal device sending capability information, the capability information including at least one of the following: supported time units, supported number of prediction information items, and supported time period length. Correspondingly, the network device receives the capability information. Thus, the network device can determine at least two candidate time units in the second indication information, or determine the number of prediction information items in the second indication information, based on the capability information of the terminal device. For example, the network device can select some or all of the supported time units from the supported time units reported by the terminal device as at least two candidate time units, or select some or all of the time periods as at least two candidate prediction information items based on the number of prediction information items reported by the terminal device. The network device can also determine a time period length based on the time period length supported by the terminal device, and then determine a first time period as the effective time length or prediction window length for the prediction task.

[0237] 1303. The terminal device determines the first time period corresponding to the first prediction task.

[0238] In some embodiments, the first time period may be preset locally on the terminal device, or it may be indicated or configured by the network device; this application does not limit this. For example, if the first time period is indicated or configured by the network device, the second indication information includes the first time period, or the first time period may be indicated to the terminal device in other indication information.

[0239] 1304. The terminal device determines the first report corresponding to the first prediction task based on at least two of the first time unit, the number of first prediction information items, or the first time period. The first report includes K prediction information items.

[0240] In some embodiments, similar to step 702, the time interval between any two adjacent first prediction information in the K first prediction information of the first report is the first time unit, or the time period length corresponding to any one of the K prediction information is the first time unit, and the time periods corresponding to any two adjacent prediction information in the K prediction information are continuous in time and do not overlap, as can be seen in the description in step 702.

[0241] Alternatively, K equals the number of the first prediction information items. In some embodiments, the time interval between any two adjacent prediction information items in the K prediction information items is the same. For example, when the number of the first prediction information items is 3, K equals 3, and the prediction information items corresponding to the number of the first prediction information items include 3 prediction information items, such as... Figure 14 As shown in (a), the three prediction information includes prediction information at times t2, t3 and t4.

[0242] In some embodiments, when the terminal device determines a first time unit, the terminal device can determine the first report corresponding to the first prediction task based on the first time unit and a first time period. For example, the first time unit determined by the terminal device is... Figure 14 In (a) shown in the figure, T1 is defined, and the first time period is t1 to t5. Furthermore, the terminal device determines that the number of prediction information to be reported is 3. For example, the terminal device can select... Figure 14 The prediction information corresponding to times t2, t3, and t4 shown in (a) is reported to the network device in the first report. The time unit between times t1 and t2, t2 and t3, and t3 and t4 is T1.

[0243] Once the terminal device has determined the number of first prediction information items, it can determine the first report corresponding to the first prediction task based on the first time period and the number of prediction information items. For example, if the terminal device determines the number of first prediction information items to be 1, and the first time period to be... Figure 14 (b) shows t1 to t5. Further, the terminal device can determine the time unit as T2 based on the first time period and the number N of the first prediction information. The terminal device can select... Figure 14 The prediction information corresponding to time t3 is shown in (b) in the first report and is reported to the network device along with the prediction information corresponding to time t3. The time unit between times t1 and t3 and between times t3 and t5 is T2.

[0244] Alternatively, if the terminal device has determined the first time unit and the number of first prediction information items, the terminal device can determine the first report corresponding to the first prediction task based on the first time unit and the number of first prediction information items. For example, the first time unit determined by the terminal device is... Figure 14 In (a) shown in the figure, time t1 is the measurement time. When the number of first prediction information is 3, the terminal device can select the prediction information corresponding to time t2, t3 and t4 from the prediction information and report it to the network device.

[0245] Alternatively, if the terminal device has determined the first time unit and the number of first prediction information items, it can determine the first report corresponding to the first prediction task based on the first time unit, the number of first prediction information items, and the first time period. For example, the first time unit determined by the terminal device is... Figure 14 In (a) shown in the figure, time t1 is the measurement time. When the number of first prediction information is 3, the first time period is t1 to t5. The terminal device can select the prediction information corresponding to time t2, t3 and t4 from the prediction information and report it to the network device.

[0246] 1305. The terminal device sends the first report.

[0247] Accordingly, the network device receives the first report.

[0248] In some embodiments, the first report is further used to indicate a first time unit and / or, the number of first prediction information items. Exemplarily, the first report includes a first time unit or a number of first prediction information items, or the first report includes an index of the first time unit or an index of the number of first prediction information items. The first time unit can be uniquely determined by the index of the first time unit, and the number of first prediction information items can be uniquely determined by the index of the number of first prediction information items. Optionally, the correspondence between the index of the first time unit and the first time unit can be indicated to the terminal device by the network device, or it can be preset by the protocol. Optionally, the correspondence between the index of the number of first prediction information items and the length of the first time period can be indicated to the terminal device by the network device, or it can be preset by the protocol.

[0249] This can be understood as the first report including the indication information of the first time unit and the prediction information corresponding to the first time unit; or, the first report including the indication information of the number of first prediction information and the prediction information corresponding to the number of first prediction information.

[0250] Here, the time period corresponding to the K predicted information items is the first time period, or, the time period corresponding to each of the K predicted information items is included in the first time period. For example, such as Figure 14 As shown in (a), when the K prediction information corresponds to the prediction information at three times t2, t3, and t4, K = 3, and the time period corresponding to these three prediction information is... Figure 14 The first time period t1 to t5. Alternatively, the time period corresponding to each of these three prediction information is included in the first time period t1 to t5, that is, the time period t2 to t3 corresponding to the prediction information at time t2 is included in the first time period, the time period t3 to t4 corresponding to the prediction information at time t3 is included in the first time period, and the time period t4 to t5 corresponding to the prediction information at time t4 is included in the first time period.

[0251] In some embodiments, the first report includes a first part and a second part.

[0252] The first part indicates the first time unit, and the second part indicates K prediction information; or, the first part indicates the number of first prediction information, and the second part indicates K prediction information. The number of bits included in the second part is determined based on the first part.

[0253] This situation is equivalent to the first report reported using the Part1+Part2 format. The reason why the number of bits in the second part is not fixed is that in this method, the value of K in the K prediction information is optional, and the number of K prediction information determined by the terminal device is variable.

[0254] For example, such as Figure 15 The diagram illustrates a reporting format for a first report. The first part has a fixed bit length and is used to indicate the first time unit selected by the terminal device or to indicate the number K of the first prediction information. The second part has a variable bit length and is used to indicate K prediction information, such as K beam prediction information. For example, when K is 3, this application does not limit the bit positions of the three prediction information indicated in the second part. For instance, the bit position of the prediction information at time t2 may be before or after the bit position of the prediction information at time t3.

[0255] The number of bits included in the second part is determined based on the first part. For example, after receiving the first part, the network device can determine the number of prediction information items contained in the second part, and therefore can determine the number of bits included in the second part.

[0256] In some embodiments, the K prediction information in the second part are arranged in chronological order, that is, the first prediction information corresponds to the earliest time or time period. This eliminates the overhead of reporting the timestamp of each prediction information, and the network device can know the time or time period corresponding to each prediction information.

[0257] In some embodiments, the K prediction information in the second part is randomly arranged, so the report also needs to carry the timestamp corresponding to each prediction information, so that the network device can know the time or time period corresponding to each prediction information.

[0258] In some scenarios, when the first prediction task is a periodic or semi-persistent task, it's possible that the prediction information in the next reporting cycle is the same as the prediction information reported in the previous reporting cycle. To reduce reporting overhead, the terminal device may choose not to report in this situation, or the reported information may not include prediction information from any given time. For network devices, when this situation is identified, they can reuse the prediction information reported at the most recent time.

[0259] Therefore, in some embodiments, the method may further include:

[0260] If the first prediction task is a periodic or semi-persistent task, and the first report is the report for the Xth period, and the prediction information for the Yth period after the Xth period is the same as the latest prediction information among the K prediction information in the first report, then perform at least one of the following:

[0261] Ignore sending the report for the Yth period; or,

[0262] Send a third indication message, which indicates that the number of prediction messages corresponding to the Yth period is 0, or;

[0263] Send a fourth indication message, which is used to indicate that the prediction information corresponding to the Yth period should be ignored.

[0264] X and Y are positive integers.

[0265] For example, such as Figure 16 The diagram illustrates a method of not reporting prediction information. The first time unit is T2, the number of prediction messages K is 1, and the Xth period can be understood as the time interval from time t1 to time t5. The terminal device can send a report at time t1, which includes the prediction information at time t3. The Yth period after the Xth period can be understood as the time interval from time t5 to time t9. Before reporting at time t5, the terminal device can first determine whether the prediction information at time t7 corresponding to the Yth period is the same as the prediction information at time t3 in the first report sent at time t1 in the Xth period. If they are the same, the terminal device can ignore sending the report for the Yth period, or in other words, the terminal device does not report the prediction information at time t7 at time t5. Alternatively, the terminal device can send a third or fourth indication message to the network device at time t5, i.e., still send a report. The fixed-length portion of the report includes the third indication message, the variable-length portion has 0 bits, and the third indication message indicates that the number of prediction messages K is 0. Alternatively, the fixed-length portion of the report may include a fourth indication, which indicates that the number of bits in the variable-length portion of the report is 0, or that the prediction information corresponding to the Yth period should be ignored, or that the network device should reuse the prediction information of the previous most recent time t3 as the prediction information of the current time t7 that was originally to be reported.

[0266] In this case, to avoid the impact of network devices missing prediction information, network devices can also stipulate that terminal devices can only not report prediction information at certain locations, or can only instruct network devices to reuse prediction information at certain locations, or stipulate that terminal devices cannot not report or instruct network devices to reuse prediction information at certain time domain locations.

[0267] Therefore, in some embodiments, the method may further include: the terminal device receiving fifth indication information, the fifth indication information being used to indicate a period in which the transmission of prediction information is allowed to be ignored, or the fifth indication information being used to indicate a period in which the reuse of prediction information corresponding to the previous period is allowed, or the fifth indication information being used to indicate a period in which the transmission of prediction information is not allowed to be ignored, or the fifth indication information being used to indicate a period in which the reuse of prediction information corresponding to the report of the previous period is not allowed.

[0268] For example, the fifth instruction information may include the sequence number of the period in which the prediction information can be ignored, or the fifth instruction information may include the reporting time of the period in which the prediction information can be ignored, or the fifth instruction information may indicate that the prediction information can be ignored when the number of periods is even.

[0269] In this way, if the network device does not detect prediction information during a period in which the terminal device is allowed to ignore the reporting of prediction information or during a period in which the terminal device is allowed to reuse the prediction information from the most recent moment, it is equivalent to instructing the network device to reuse the prediction information from the most recent moment, thereby reducing the reporting overhead of the terminal device.

[0270] As explained above, this application can also be applied to ORAN systems. If applied to an ORAN system, the network devices in the above embodiments can be near real-time RIC / CU / DU / RUs within the ORAN system. That is, near real-time RIC / CU / DU / RUs can be used to execute the processes described above for the network devices.

[0271] In this way, within the ORAN system, terminal devices can flexibly choose the time unit, time period, or number of prediction messages reported at one time. Within the same time period length, increasing the time unit or decreasing the number of prediction messages effectively reduces the amount of prediction information, thereby reducing the bit overhead of the terminal device sending reports. Alternatively, with the number of prediction messages remaining constant, increasing the selected time unit or time period length also effectively reduces the amount of prediction information within the same time window, further reducing the bit overhead of the terminal device sending reports.

[0272] It is understood that, in order to achieve the functions in the above embodiments, the network device and terminal device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0273] Figure 17 and Figure 18 The diagram illustrates the possible structures of communication devices provided in embodiments of this application. These communication devices can be used to implement the functions of terminal devices or network devices in the above method embodiments, and thus also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be as follows: Figure 2 The terminal devices 220 / 230 shown can also be as follows: Figure 2 The network device 210 shown can also be a module (such as a chip) applied to a terminal device or network device.

[0274] like Figure 17 As shown, the communication device 700 includes a processing unit 710 and a transceiver unit 720. The communication device 700 is used to implement the above-mentioned... Figure 7 and / or Figure 13 The methods illustrated in this embodiment demonstrate the functions of the terminal device or network device.

[0275] When the communication device 700 is used to implement Figure 7 In the method embodiment shown, the terminal device functions as follows: the transceiver unit 720 is used to receive first indication information and second indication information, etc.; the processing unit 710 is used to determine a first time unit, a first time period length, the number of prediction information, and to determine a first report corresponding to the first prediction task based on at least two of the first time unit, the first time period length, or N, etc. The transceiver unit 720 is also used to send the first report.

[0276] When the communication device 700 is used to implement Figure 13 In the method embodiment shown, the terminal device functions as follows: the transceiver unit 720 is used to receive first indication information and second indication information, etc.; the processing unit 710 is used to determine a first time unit, determine a first time period, and determine a first report corresponding to the first prediction task based on at least two of the first time unit, the number of first prediction information items, or the first time period. The transceiver unit 720 is also used to send the first report.

[0277] When the communication device 700 is used to implement Figure 7In the method embodiment shown, the network device functions as follows: the transceiver unit 720 is used to send first indication information and second indication information, etc., and to receive third indication information and first report, etc.; the processing unit 710 is used to adjust the detection cycle or reporting cycle, etc.

[0278] When the communication device 700 is used to achieve Figure 13 In the method embodiment shown, the network device functions as follows: the transceiver unit 720 is used to send first indication information and second indication information, and to receive third indication information and first report; the processing unit 710 is used to adjust the configured reporting period, the period of the measurement reference signal, the minimum candidate time unit, etc.

[0279] For a more detailed description of the processing unit 710 and the transceiver unit 720 mentioned above, please refer to [link / reference]. Figure 7 The relevant descriptions in the method embodiments shown.

[0280] Figure 18 A schematic diagram of a possible communication device is shown. It will be understood that the communication device 800 includes means of the necessary form, such as modules, units, elements, circuits, or interfaces, to be appropriately configured together to perform this solution. The communication device 800 may be... Figure 3 The access network nodes, terminals, core network equipment, or other network devices, or components (e.g., chips) within these devices, are used to implement the methods described in the following method embodiments. The communication device 800 includes one or more processors 811. The processor 811 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, while the central processing unit can be used to control the communication device (e.g., RAN nodes, terminals, or chips), execute software programs, and process data from the software programs.

[0281] Optionally, in one design, the processor 811 may include a program 813 (sometimes also referred to as code or instructions), which can be executed on the processor 811 to cause the communication device 800 to perform the methods described in the above embodiments. In yet another possible design, the communication device 800 includes circuitry (…). Figure 18 (Not shown), the circuit is used to implement the functions of the terminal device or network device in the above embodiments.

[0282] Optionally, the communication device 800 may include one or more memories 812 storing a program 814 (sometimes referred to as code or instructions), which can be run on the processor 811 to cause the communication device 800 to perform the methods described in the above method embodiments.

[0283] Optionally, the processor 811 and / or memory 812 may include AI modules 817 and 818, which are used to implement AI-related functions. The AI ​​modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a RIC module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0284] Optionally, the processor 811 and / or memory 812 may also store data. The processor and memory may be configured separately or integrated together.

[0285] Optionally, the communication device 800 may further include a transceiver 815 and / or an antenna 816. The processor 811, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 815, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device through the antenna 816.

[0286] When the aforementioned communication device is a chip applied to a terminal, the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receives information from the base station, which can be understood as the information being first received by other modules in the terminal (such as an RF module or antenna), and then sent to the terminal chip by these modules. The terminal chip sends information to the base station, which can be understood as the information being first sent to other modules in the terminal (such as an RF module or antenna), and then sent to the base station by these modules.

[0287] When the aforementioned communication device is a chip applied to a base station, the base station chip implements the functions of the base station in the above method embodiments. The base station chip receives information from the terminal, which can be understood as the information being first received by other modules in the base station (such as an RF module or antenna), and then sent to the base station chip by these modules. The base station chip sends information to the terminal, which can be understood as the information being sent down to other modules in the base station (such as an RF module or antenna), and then sent to the terminal by these modules.

[0288] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal chip and other modules of the terminal, or between a base station chip and other modules of the base station.

[0289] It is understood that the processor in the embodiments of this application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0290] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. The processor and storage medium can also exist as discrete components in a base station or terminal.

[0291] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0292] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0293] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.

[0294] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

Claims

1. A prediction method, characterized in that, include: Receive a first instruction message, the first instruction message being used to instruct the execution of a first prediction task; Determine a first time unit, which is one of at least two candidate time units; and / or determine a first time period length, which is one of at least two candidate time period lengths; Determine the number N of prediction information contained in each of the at least one reports corresponding to the first prediction task, where N is a positive integer; The first report corresponding to the first prediction task is determined based on at least two of the first time unit, the first time period length, or N, wherein the first report is one of the at least one report and the first report includes N prediction information. Send the first report.

2. The method according to claim 1, characterized in that, The method further includes: Receive second indication information, which is used to indicate the time unit of the at least two candidates or the time period length of the at least two candidates.

3. The method according to claim 1 or 2, characterized in that, The first report is also used to indicate the first time unit and / or the length of the first time period.

4. The method according to claim 3, characterized in that, The time interval between any two adjacent predictions among the N predictions is the first time unit; or, The time period corresponding to any one of the N prediction information is the length of the first time unit, and the time periods corresponding to any two adjacent prediction information among the N prediction information are temporally continuous and do not overlap; or, The time interval between the earliest predicted information and the latest predicted information among the N predicted information is less than or equal to the length of the first time interval; or, The sum of the lengths of the time periods corresponding to each of the N prediction information is the length of the first time period, and the time periods corresponding to any two adjacent prediction information in the N prediction information are temporally continuous and do not overlap.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: If the first prediction task is a periodic task or a semi-persistent task, each report in the at least one report corresponds to one of the Z periods of the first prediction task, the first report is the report of the Xth period, and the time period corresponding to the Yth period after the Xth period is included in the time period corresponding to the N prediction information in the first report, and at least one of the following is performed: Ignore sending the report for the Yth period; or, Send a third indication message, which is used to indicate that the N prediction messages corresponding to the Yth period should be ignored; X and Y are positive integers less than or equal to Z, and Z is a positive integer greater than 1.

6. A prediction method, characterized in that, include: Receive a first instruction message, the first instruction message being used to instruct the execution of a first prediction task; Determine a first time unit, which is one of at least two candidate time units; And / or, determine a first number of prediction information, wherein the first number of prediction information is one of at least two candidate numbers of prediction information; Determine the first time period corresponding to the first prediction task; A first report corresponding to the first prediction task is determined based on at least two of the first time unit, the number of the first prediction information, or the first time period. The first report includes K prediction information, where K is a positive integer. Send the first report.

7. The method according to claim 6, characterized in that, The method further includes: Receive second indication information, which is used to indicate the time unit of the at least two candidates or the number of prediction information of the at least two candidates.

8. The method according to claim 6 or 7, characterized in that, The first report is also used to indicate the first time unit, and / or the number of the first prediction information items.

9. The method according to any one of claims 6-8, characterized in that, The time period corresponding to the K prediction information is the first time period, or the time period corresponding to each of the K prediction information is included in the first time period.

10. The method according to claim 9, characterized in that, The time interval between any two adjacent predictions in the K prediction information is the first time unit; or, The time period corresponding to any one of the K prediction information is the length of the first time unit, and the time periods corresponding to any two adjacent prediction information among the K prediction information are temporally continuous and do not overlap; or, K is equal to the number of the first prediction information items, and K is a positive integer.

11. The method according to any one of claims 6-10, characterized in that, The first report comprises a first part and a second part; The first part is used to indicate the first time unit, and the second part is used to indicate the K prediction information; or, The first part is used to indicate the number of the first prediction information, and the second part is used to indicate the K prediction information; The number of bits included in the second part is determined based on the first part.

12. The method according to any one of claims 6-11, characterized in that, The method further includes: If the first prediction task is a periodic or semi-persistent task, and the first report is the report for the Xth period, and the prediction information corresponding to the Yth period after the Xth period is the same as the latest prediction information among the K prediction information in the first report, then at least one of the following is performed: Ignore sending the report for the Yth period; or, Send a third indication message, which is used to indicate that the number of prediction messages corresponding to the Yth period is 0, or; Send a fourth indication message, which is used to indicate that the prediction information corresponding to the Yth period should be ignored; X and Y are positive integers.

13. The method according to claim 5 or 12, characterized in that, The method further includes: Receive a fifth indication message, which is used to indicate the period in which sending prediction information is allowed to be ignored, or the period in which the prediction information corresponding to the previous period is allowed to be reused, or the period in which sending prediction information is not allowed to be ignored, or the period in which the prediction information corresponding to the report of the previous period is not allowed to be reused.

14. The method according to any one of claims 1-13, characterized in that, Send capability information, which includes at least one of the following: supported time units, supported number of prediction information items, and supported time period length.

15. A communication device, characterized in that, include: A receiving unit is configured to receive first indication information, wherein the first indication information is used to instruct the execution of a first prediction task; The processing unit is configured to determine a first time unit, which is one of at least two candidate time units; and / or determine a first time period length, which is one of at least two candidate time period lengths. The processing unit is further configured to determine the number N of prediction information contained in each of the at least one reports corresponding to the first prediction task, where N is a positive integer; The processing unit is further configured to determine a first report corresponding to the first prediction task based on at least two of the first time unit, the first time period length, or N, wherein the first report is one of the at least one report and the first report includes N prediction information. A sending unit is used to send the first report.

16. A communication device, characterized in that, include: A receiving unit is configured to receive first indication information, wherein the first indication information is used to instruct the execution of a first prediction task; A processing unit is configured to determine a first time unit, wherein the first time unit is one of at least two candidate time units; And / or, determine a first number of prediction information, wherein the first number of prediction information is one of at least two candidate numbers of prediction information; The processing unit is further configured to determine the first time period corresponding to the first prediction task; The processing unit is further configured to determine a first report corresponding to the first prediction task based on at least two of the first time unit, the number of the first prediction information, or the first time period, wherein the first report includes K prediction information, and K is a positive integer; A sending unit is used to send the first report.

17. A communication device, characterized in that, The device includes at least one processor connected to a memory, the at least one processor being configured to read and execute a program stored in the memory, such that the device performs the method as described in any one of claims 1-14.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of claims 1-14.

19. A chip, characterized in that, The chip stores computer execution instructions, and when the computer execution instructions are run, the method described in any one of claims 1-14 is executed.

Images