Communication method and apparatus

Abstract

A communication method and apparatus. In the method, CPU occupancy counts and CPU occupancy time periods that correspond to a first report are determined on the basis of a first rule, wherein a first CPU occupancy count corresponds to a first CPU occupancy time period, a second CPU occupancy count corresponds to a second CPU occupancy time period, the first CPU occupancy count is less than or equal to a CSI computation load corresponding to a simultaneous AI execution process that can be supported by a UE, and the second CPU occupancy count is less than or equal to a CSI computation load corresponding to a simultaneous non-AI execution process that can be supported by the UE. The first report can be completed jointly by processing units corresponding to two CPUs. In this case, the UE and an RAN may determine, on the basis of the first rule, the first CPU occupancy count and the first CPU occupancy time period that correspond to the first report, and the second CPU occupancy count and the second CPU occupancy time period that correspond to the first report, so as to align the CPU occupancy counts and the occupancy time periods, thereby completing a subsequent communication process.

Description

Communication method and apparatus

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202510138805.0, filed on February 7, 2025, and entitled “A Communication Method and Apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] Embodiments of the present application relate to the technical field of wireless communication, and in particular, to a communication method and apparatus. BACKGROUND

[0004] In a communication system (for example, a long term evolution (LTE) communication system or a new radio (NR) communication system, etc.), a network device usually determines the configuration of a downlink data channel of a terminal device based on channel state information (CSI), such as the resource, modulation and coding scheme (MCS), and precoding of the downlink data channel of the terminal device. Specifically, the network device can send a reference signal to the terminal device, the terminal device estimates the channel information according to the known reference signal and the received reference signal, and feeds back the channel information to the network device through a CSI report, and the network device can determine the configuration of the terminal device according to the channel information of the terminal device.

[0005] The terminal device can report the number N of simultaneously processed CSI calculations that can be supported according to its own capability cpu , that is, the terminal device is configured with N cpu CSI processing units (CPUs) for processing CSI reports configured on all component carriers (CCs). As for the CPU, the current communication protocol specifies the number of CPUs occupied by each CSI report (referred to as CPU occupancy number) and the CPU occupancy time period (time-line), so that the network device and the terminal device can align the CPU occupancy when the terminal device processes the CSI report.

[0006] The 3rd generation partnership project (3GPP) proposes to apply artificial intelligence (AI) to NR, to improve network performance and user experience by intelligently collecting and analyzing data. For example, AI-based CSI reporting can include not only measurement information about a channel, but also prediction information about the channel based on AI, etc.

[0007] After the introduction of AI technology, the CPU used to process CSI reporting can be further divided into a first type of CPU and a second type of CPU, where the first type of CPU is used to process AI operations in AI-based CSI reporting, and the second type of CPU is used to process non-AI CSI reporting and non-AI operations in AI-based CSI reporting. In this case, how the network device and the terminal device determine the CPU occupation number and the CPU occupation time period corresponding to the CSI reporting is a problem that needs to be solved at present. SUMMARY

[0008] Embodiments of the present application provide a communication method and device, which are used to provide a new determination method of CPU occupation number and CPU occupation time period.

[0009] In a first aspect, embodiments of the present application provide a communication method, which is applied to a first device, or a communication module / processing module in the first device, or a circuit or chip responsible for communication function in a communication device (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or system in package (SIP) chip containing a modem core), or a circuit or chip responsible for processing function in the first device (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application specific integrated circuit (ASIC)).

[0010] The first device can be a terminal device or a radio access network device.

[0011] Taking the method applied to the first device as an example, in the method, according to the first rule, a channel state information processing unit CPU occupation number and a CPU occupation time period corresponding to the first report are determined; the CPU occupation number includes a first CPU occupation number and a second CPU occupation number, and the CPU occupation time period includes a first CPU occupation time period and a second CPU occupation time period, the first CPU occupation time period corresponds to the first CPU occupation number, and the second CPU occupation time period corresponds to the second CPU occupation number; the first CPU occupation number is less than or equal to a first CPU maximum occupation number, and the first CPU maximum occupation number is a number of channel state information, CSI, calculations that can be supported by the terminal device to simultaneously process an AI execution process; the second CPU occupation number is less than or equal to a second CPU maximum occupation number, and the second CPU maximum occupation number is a number of CSI calculations that can be supported by the terminal device to simultaneously process a non-AI execution process.

[0012] In the above method, the terminal device can execute the AI execution process in the first report through a processing unit corresponding to the first CPU and execute the non-AI execution process in the first report through a processing unit corresponding to the second CPU, that is, the first report can be completed by the processing units corresponding to the two CPUs together, instead of being completed by a processing unit corresponding to one CPU alone. In this case, the terminal device and the radio access network device can determine the first CPU occupation number and the first CPU occupation time period corresponding to the first report according to the first rule, and the second CPU occupation number and the second CPU occupation time period corresponding to the first report, so as to align the CPU occupation number and the CPU occupation time period, and then complete the subsequent communication process.

[0013] In a possible implementation, the first report carries an AI inference result; and the first rule includes that the first CPU occupation number corresponding to the first report is a first value, and the first value corresponds to a first CPU first occupation time period.

[0014] In a possible implementation, a starting time corresponding to the first CPU first occupation time period is at least one of the following times: a time at which CSI calculation of all measurement resources corresponding to the first report is completed, a time at which CSI calculation of a first measurement resource is completed, and a termination time of a last measurement resource; the first measurement resource is an earliest measurement resource in the at least one measurement resource corresponding to the first report, and the last measurement resource is a latest measurement resource in the at least one measurement resource corresponding to the first report; and a termination time corresponding to the first CPU first occupation time period is at least one of the following times: an AI execution process completion time, or a last time unit of an uplink time unit carrying the first report.

[0015] Optionally, the measurement resource can be a resource of a CSI-RS / CSI-IM / SSB. For example, for a prediction report, the measurement resource can be a resource of a CSI-RS / CSI-IM / SSB in a corresponding observation window of the prediction report; for a monitoring report, the measurement resource can be a resource of a CSI-RS / CSI-IM / SSB in a corresponding monitoring window of the monitoring report.

[0016] Optionally, the time when the CSI calculation is completed can be Z' time units after a last symbol of the measurement resource; the Z' is a time unit defined by a protocol, and the Z' includes a time for channel estimation and CSI calculation.

[0017] In a possible implementation, the first CPU first occupation time period includes at least one first time period, and each of the at least one first time period corresponds to at least one measurement resource corresponding to the first report; a starting time corresponding to each of the at least one first time period is at least one of the following: a time when CSI calculation of the at least one measurement resource corresponding to the first report is completed, and a last time unit of the at least one measurement resource corresponding to the first report; and a terminal time corresponding to each of the at least one first time period is X1 time units after the starting time corresponding to the at least one first time period.

[0018] In a possible implementation, the X1 time units correspond to time units corresponding to an AI execution process, or the X1 time units include time units corresponding to the AI execution process.

[0019] In a possible implementation, a starting time corresponding to the first CPU first occupation time period is a first time unit of a first measurement resource, and the first measurement resource is an earliest measurement resource in the at least one measurement resource corresponding to the first report; and a terminal time corresponding to the first CPU first occupation time period is a last time unit of an uplink time unit carrying the first report.

[0020] In the embodiments of the present application, the first time unit can also be replaced by the earliest time unit, and the last time unit can also be replaced by the latest time unit.

[0021] In a possible implementation, the first value is a CPU occupation number of the terminal device for the AI execution process, which is reported or indicated or preset by the terminal device; or the first value is a CPU occupation number of the terminal device for the AI report, which is reported or indicated or preset by the terminal device.

[0022] The first value can be the CPU usage of the terminal device during the AI ​​execution process reported by the terminal device; or, it can be the CPU usage of the terminal device during the AI ​​execution process indicated by the terminal device, for example, the first value is the counting coefficient corresponding to the CPU usage of the terminal device during the AI ​​execution process; or, it can be the CPU usage of the terminal device during the AI ​​execution process preset by the protocol.

[0023] In one possible implementation, the first rule includes: the second CPU usage number corresponding to the first report is a second value, and the second value corresponds to the first CPU usage time period.

[0024] In one possible implementation, the start time corresponding to the first time period occupied by the second CPU is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; the end time corresponding to the first time period occupied by the second CPU is the last time unit of the uplink time unit carrying the first report.

[0025] In one possible implementation, the first time period occupied by the second CPU includes a second time period and a third time period; the start time of the second time period is the first time unit of the first measurement resource, which is the earliest measurement resource among at least one measurement resource corresponding to the first report; the end time of the second time period is the time when the CSI calculation of the last measurement resource is completed, or the time when the processing unit corresponding to the second CPU sends the CSI calculation result of the last measurement resource to the processing unit corresponding to the first CPU, where the last measurement resource is the latest measurement resource among at least one measurement resource corresponding to the first report; the start time of the third time period is the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed; the end time of the third time period is the last time unit of the uplink time unit carrying the first report.

[0026] In one possible implementation, the first CPU occupancy time period includes at least one second time period and one third time period. The at least one second time period corresponds one-to-one with at least one target measurement resource corresponding to the first report. The at least one target measurement resource is the measurement resource other than the latest measurement resource among the plurality of measurement resources corresponding to the first report. The third time period corresponds to the last measurement resource, which is the latest measurement resource among the plurality of measurement resources corresponding to the first report. The start time of each second time period is the first time unit of the corresponding target measurement resource. The end time of each second time period is the time when the CSI calculation of the corresponding target measurement resource is completed. The start time of the third time period is the first time unit of the last measurement resource. The end time of the third time period is the last time unit of the uplink time unit carrying the first report.

[0027] In one possible implementation, the first time period occupied by the second CPU includes at least one second time period and one third time period. The at least one second time period corresponds one-to-one with at least one measurement resource corresponding to the first report. The start time of each second time period is the first time unit of the corresponding measurement resource. The end time of each second time period is the time when the CSI calculation of the corresponding measurement resource is completed. The start time of the third time period is the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed. The end time of the third time period is the last time unit of the uplink time unit carrying the first report.

[0028] In one possible implementation, the second value is the CPU usage count measured by a reference signal reported by the terminal device or preset by the terminal device; or, the second value is the CPU usage count reported by the terminal device, indicated by the terminal device, or preset by the terminal device for non-AI execution processes in the AI ​​report.

[0029] In one possible implementation, the first report carries AI monitoring results; when the terminal device does not obtain the AI ​​execution result required by the first report, the first rule includes: the first CPU usage number corresponding to the first report is a third value, the third value corresponds to a second CPU usage time period; the start time corresponding to the second CPU usage time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result; the end time corresponding to the second CPU usage time period is the time when the AI ​​execution process is completed; the third value is the CPU usage number of the terminal device for the AI ​​execution process reported, indicated, or preset by the terminal device, or the CPU usage number of the terminal device for the AI ​​report reported, indicated, or preset by the terminal device.

[0030] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution results required by the first report, the first rule includes: the first CPU usage corresponding to the first report is 0, and / or, the first report does not occupy the first CPU.

[0031] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the measurement results and AI execution results required by the first report, the first rule includes: the second CPU occupancy number corresponding to the first report is a fourth value, the fourth value corresponds to the second CPU occupancy time period; the fourth value is 1 or a preset fixed value; and / or, the termination time corresponding to the second CPU occupancy time period is the last time unit of the uplink time unit carrying the first report, and the duration of the second CPU occupancy time period is a preset duration.

[0032] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution results required by the first report but has not obtained the measurement results required by the first report, the first rule includes: the second CPU usage number corresponding to the first report is a fifth value, the fifth value corresponds to the second CPU third usage time period; the start time corresponding to the second CPU third usage time period is the first time unit of the first measurement resource, the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; the end time corresponding to the second CPU third usage time period is the time when the first report was generated; the fifth value is the CPU usage number of the terminal device for non-AI execution processes in the AI ​​report, reported, indicated, or preset by the terminal device.

[0033] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution result required by the first report but has not obtained the measurement result required by the first report, the first rule includes: the second CPU usage number corresponding to the first report is a fifth value, the fifth value corresponds to the second CPU third usage time period; the second CPU third usage time period includes at least one fourth time period and one fifth time period, the at least one fourth time period corresponds one-to-one with at least one target measurement resource, the at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report, the fifth time period corresponds to the last measurement resource, the last... The measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report; the start time of each fourth time period in the at least one fourth time period is the first time unit of the corresponding target measurement resource; the end time of each fourth time period in the at least one fourth time period is the time when the CSI calculation of the corresponding target measurement resource is completed; the start time of the fifth time period is the first time unit of the last measurement resource; the end time of the fifth time period is the last time unit of the uplink time unit carrying the first report; the fifth value is the CPU usage of the terminal device for the non-AI execution process in the AI ​​report, as reported, indicated, or preset by the terminal device.

[0034] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the measurement results required by the first report but has not obtained the AI ​​execution results required by the first report, the first rule includes: the second CPU usage number corresponding to the first report is a sixth value, the sixth value corresponds to the fourth CPU usage time period; the end time of the fourth CPU usage time period is the last time unit of the uplink time unit carrying the first report, and the duration of the fourth CPU usage time period is a preset duration; and / or, the sixth value is 1 or a preset fixed value.

[0035] Secondly, embodiments of this application provide a communication method that can be applied to a first device, or a communication module / processing module in the first device, or a circuit or chip in the communication device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or a circuit or chip in the first device responsible for processing functions (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)).

[0036] The first device may be a terminal device or a wireless access network device, and the terminal device includes at least one channel state information processing unit (CPU), each of which is used to execute AI execution processes and non-AI execution processes.

[0037] Taking the application of this method to the first device as an example, in this method, the CPU usage count and CPU usage time period corresponding to the first report are determined according to the second rule.

[0038] In the above method, the terminal device can execute the AI ​​execution process and the non-AI execution process in the first report through the processing unit corresponding to the CPU. However, the CPU usage time period and the corresponding CPU usage number are determined separately for the AI ​​execution process and the non-AI execution process. In this case, the terminal device and the wireless access network device can determine the CPU usage number and CPU usage time period corresponding to the first report according to the second rule, thereby aligning the CPU usage number and CPU usage time period and completing the subsequent communication process.

[0039] In one possible implementation, the second rule includes: the CPU usage corresponding to the first report is a first value, and the first value corresponds to a first CPU usage time period; the start time corresponding to the first CPU usage time period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; the end time corresponding to the CPU usage time period is the last time unit of the uplink time unit carrying the first report; and the first value is the CPU usage of the terminal device for the AI ​​report reported, indicated, or preset by the terminal device.

[0040] In one possible implementation, the second rule includes: the CPU usage count corresponding to the first report includes a first value and a second value; the CPU usage time period corresponding to the first report includes a first time period and a second time period; the first value corresponds to the first time period, and the second value corresponds to the second time period; the first value is the CPU usage count of the terminal device for the AI ​​execution process reported, indicated, or preset by the terminal device, or the CPU usage count of the terminal device for the AI ​​report reported, indicated, or preset by the terminal device; the second value is the CPU usage count measured by a reference signal reported or preset by the terminal device; or the CPU usage count corresponding to a non-AI execution process in the AI ​​report reported, indicated, or preset by the terminal device; the first time period is the time period during which the terminal device executes the AI ​​execution process corresponding to the first report; the second time period is the time period during which the terminal device executes the non-AI execution process corresponding to the first report.

[0041] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution results and measurement results required by the first report, the second rule includes: the CPU usage number corresponding to the first report is a third value, the third value corresponds to the CPU usage time period; the third value is 1 or a preset fixed value; the termination time corresponding to the CPU usage time period is the last time unit of the uplink unit carrying the first report, and the duration of the CPU usage time period is a preset duration.

[0042] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution result required by the first report but has not obtained the measurement result required by the first report, or when it has obtained the measurement result required by the first report but has not obtained the AI ​​execution result required by the first report, or when it has not obtained both the measurement result and the AI ​​execution result required by the first report, the second rule includes: the CPU usage count is a fourth value, the fourth value corresponds to the CPU usage time period; the start time corresponding to the CPU usage time period is the first time unit of the first measurement resource, the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; the end time corresponding to the CPU usage time period is the last time unit of the uplink unit carrying the first report; the fourth value is the CPU usage count of the terminal device reported, indicated, or preset by the terminal device.

[0043] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the AI ​​execution results required by the first report but has not obtained the measurement results required by the first report, the second rule includes: the CPU usage count includes a fourth value and a fifth value, the fourth value corresponds to at least one third time period in the CPU usage time period, and the fifth value corresponds to the fourth time period in the CPU usage time period; the at least one third time period corresponds one-to-one with at least one target measurement resource, the at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report, the fourth time period corresponds to the last measurement resource, and the last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report; the start time corresponding to each of the at least one third time period is the start time of the corresponding target measurement resource. The first time unit; the end time of each of the at least one third time period is the time when the CSI calculation of the corresponding target measurement resource is completed; the start time of the fourth time period is the first time unit of the last measurement resource; the end time of the fourth time period is the last time unit of the uplink time unit carrying the first report; the fourth value is the CPU usage of the terminal device for the AI ​​execution process reported, indicated, or preset by the terminal device, or the CPU usage of the terminal device for the AI ​​report reported, indicated, or preset by the terminal device; the fifth value is the CPU usage of the reference signal measurement reported or preset by the terminal device, or the CPU usage of the terminal device for the non-AI execution process in the AI ​​report reported, indicated, or preset by the terminal device.

[0044] In one possible implementation, the first report carries AI monitoring results; when the terminal device has obtained the measurement results required for the first report but has not obtained the AI ​​execution results required for the first report, the second rule includes: the CPU usage count includes a sixth value and a seventh value, the sixth value corresponds to the fifth time period in the CPU usage time period, and the seventh value corresponds to the sixth time period in the CPU usage time period; the start time corresponding to the fifth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result; the end time corresponding to the fifth time period is the time when the AI ​​execution process is completed; the sixth value is the CPU usage count of the terminal device for the AI ​​execution process reported, indicated, or preset by the terminal device, or the CPU usage count of the terminal device for the AI ​​report reported, indicated, or preset by the terminal device; the end time corresponding to the sixth time period is the last time unit of the uplink time unit carrying the first report, and the duration of the sixth time period is a preset duration; the seventh value is 1 or a preset fixed value.

[0045] In one possible implementation, the first report carries the results of AI monitoring;

[0046] When the terminal device fails to obtain the measurement results required for the first report and the AI ​​execution results required for the first report, the second rule includes: the CPU usage count includes an eighth value, a ninth value, and a tenth value; the eighth value corresponds to the seventh time period in the CPU usage time period; the ninth value corresponds to the eighth time period in the CPU usage time period; and the tenth value corresponds to the ninth time period in the CPU usage time period. The start time corresponding to the seventh time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result. The end time corresponding to the seventh time period is the time when the AI ​​execution process is completed. The eighth value is the value reported or indicated by the terminal device. The eighth time period is defined as either the CPU usage of the terminal device during the AI ​​execution process (preset by the device) or the CPU usage reported, indicated, or preset by the terminal device for the AI ​​report. The start time of the eighth time period is the first time unit of the first measurement resource, where the first measurement resource is the earliest among at least one measurement resource corresponding to the first report. The end time of the eighth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed. The ninth value is either the CPU usage of the reference signal measurement reported by the terminal device or preset by the terminal device; or the CPU usage of the non-AI execution process in the AI ​​report reported, indicated, or preset by the terminal device. The end time of the ninth time period is the last time unit of the uplink time unit carrying the first report, and the duration of the ninth time period is a preset duration. The tenth value is 1 or a preset fixed value.

[0047] In one possible implementation, if the seventh time period and the eighth time period overlap, the CPU usage of the overlapping portion is the sum of the eighth value and the ninth value.

[0048] Thirdly, embodiments of this application provide a communication method that can be applied to a terminal device, or a communication module / processing module in a terminal device, or a circuit or chip in a terminal device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or a circuit or chip in a terminal device responsible for processing functions (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)).

[0049] Taking the application of this method to a terminal device as an example, in this method, the terminal device receives a first beam set (training set A) indication information sent by a wireless access network device, the first beam set indication information being used to indicate the first beam set; the terminal device determines a second beam set (training set B), the second beam set being a subset of the first beam set; the terminal device performs measurements based on the first beam set and the second beam set to obtain measurement information corresponding to the first beam set and the second beam set; or, the terminal device performs measurements based on the first beam set to obtain measurement information corresponding to the first beam set, and determines the measurement information corresponding to the second beam set based on the measurement information corresponding to the first beam set and the mapping relationship between the second beam set and the first beam set; the terminal device performs AI training based on the measurement information corresponding to the first beam set and the measurement information corresponding to the second beam set; the terminal device receives a third beam set (inference set B) indication information, the third beam set indication information being used to indicate the third beam set; the third beam set has the same first feature as the second beam set.

[0050] Optionally, the terminal device performs measurements based on the third beam and performs AI inference based on the measurement information corresponding to the third beam set.

[0051] Optionally, the method further includes: the terminal device determining the range corresponding to the fourth beam set (inference set A); or, the terminal device receiving fourth beam set indication information sent by the radio access network device, the fourth beam set indication information being used to indicate the range of the fourth beam set; the terminal device performing AI inference based on the measurement information corresponding to the third beam set and the range of the fourth beam set. The range of the fourth beam set can be an identifier list of the fourth beam set (e.g., SSB ID List, beam ID List).

[0052] Optionally, the first feature being the same includes the beam mapping corresponding to the third beam set being the same as the beam mapping corresponding to the second beam, or the beam order corresponding to the third beam set being the same as the beam order corresponding to the second beam, or the network-side additional conditions corresponding to the third beam set being the same as the network-side additional conditions corresponding to the second beam.

[0053] Optionally, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set, including: when the associated ID corresponding to the third beam set is the same as the associated ID corresponding to the second beam set, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set.

[0054] Optionally, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set, including: when the associated ID corresponding to the third beam set is the same as the associated ID corresponding to the second beam set, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set.

[0055] Optionally, the terminal device determines the second beam set by: the terminal device receiving second beam set indication information sent by the wireless access network device, the second beam set indication information being used to indicate the second beam set; or, the terminal device determines the second beam set according to the first beam set and a preset rule.

[0056] Optionally, the beam set can be replaced by: measurement resource set, CSI-RS resource set, SSB resource set, etc.

[0057] Fourthly, embodiments of this application provide a communication method that can be applied to a wireless access network device, or a communication module / processing module in a wireless access network device, or a circuit or chip in a wireless access network device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or a circuit or chip in a wireless access network device responsible for processing functions (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)).

[0058] Taking the application of this method to a wireless access network device as an example, in this method, the wireless access network device sends a first beam set indication information to the terminal device, the first beam set indication information being used to indicate a first beam set; and sends a third beam set indication information to the terminal device, the third beam set indication information being used to indicate a third beam set; the third beam set has the same first feature as the second beam set, and the second beam set is a subset of the first beam set.

[0059] Optionally, the wireless access network device may also send fourth beam set indication information to the terminal device, the fourth beam set indication information being used to indicate the range of the fourth beam set. Further, the range of the fourth beam set may be an identifier list of the fourth beam set (e.g., SSB ID List, beam ID List).

[0060] Optionally, the first feature being the same includes the beam mapping corresponding to the third beam set being the same as the beam mapping corresponding to the second beam, or the beam order corresponding to the third beam set being the same as the beam order corresponding to the second beam, or the network-side additional conditions corresponding to the third beam set being the same as the network-side additional conditions corresponding to the second beam.

[0061] Optionally, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set, including: when the associated ID corresponding to the third beam set is the same as the associated ID corresponding to the second beam set, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set.

[0062] Optionally, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set, including: when the associated ID corresponding to the third beam set is the same as the associated ID corresponding to the second beam set, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set.

[0063] Optionally, the terminal device determines the second beam set by: the terminal device receiving second beam set indication information sent by the wireless access network device, the second beam set indication information being used to indicate the second beam set; or, the terminal device determines the second beam set according to the first beam set and a preset rule.

[0064] Optionally, the beam set can be replaced by: measurement resource set, CSI-RS resource set, SSB resource set, etc.

[0065] Fifthly, this application also provides a communication device that has the function of implementing the method in the first aspect or any implementation thereof. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0066] In one possible implementation, the communication device includes a processing module and, optionally, an interface module. These modules can perform the corresponding functions described in the first aspect or any implementation thereof, as detailed in the method examples, which will not be repeated here.

[0067] In one possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions described in the first aspect or any implementation thereof. Optionally, the communication device further includes a communication interface and / or a memory. The communication interface is used for sending and receiving frames, information, or data, and for communicating with other devices in the communication system. The memory is coupled to the processor and stores necessary program instructions and data for the communication device.

[0068] Sixthly, this application also provides a communication device that has the function of implementing the method in the second aspect or any implementation thereof. The function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0069] In one possible implementation, the communication device includes a processing module and, optionally, an interface module. These modules can perform the corresponding functions described in the second aspect or any implementation thereof, as detailed in the method examples, which will not be repeated here.

[0070] In one possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions described in the second aspect or any implementation thereof. Optionally, the communication device further includes a communication interface and / or a memory. The communication interface is used for sending and receiving frames, information, or data, and for communicating with other devices in the communication system. The memory is coupled to the processor and stores necessary program instructions and data for the communication device.

[0071] Seventhly, this application also provides a communication device having the function of implementing the method in the third aspect or any implementation thereof. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0072] In one possible implementation, the communication device includes a processing module and, optionally, an interface module. These modules can perform the corresponding functions described in the third aspect or any implementation thereof, as detailed in the method examples, which will not be repeated here.

[0073] In one possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions described in the third aspect or any implementation thereof. Optionally, the communication device further includes a communication interface and / or a memory. The communication interface is used for sending and receiving frames, information, or data, and for communicating with other devices in the communication system. The memory is coupled to the processor and stores necessary program instructions and data for the communication device.

[0074] Eighthly, this application also provides a communication device having the function of implementing the method in the fourth aspect or any implementation thereof. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0075] In one possible implementation, the communication device includes a processing module and, optionally, an interface module. These modules can perform the corresponding functions described in the fourth aspect or any implementation thereof, as detailed in the method examples, which will not be repeated here.

[0076] In one possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions described in the fourth aspect or any implementation thereof. Optionally, the communication device further includes a communication interface and / or a memory. The communication interface is used for sending and receiving frames, information, or data, and for communicating with other devices in the communication system. The memory is coupled to the processor and stores necessary program instructions and data for the communication device.

[0077] Ninthly, embodiments of this application provide a chip, including: a processor coupled to a memory for storing instructions, wherein when the instructions are executed by the processor, the chip causes the chip to implement the methods described in the first to fourth aspects and any of their implementations.

[0078] In a tenth aspect, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the first to fourth aspects and any of their implementations.

[0079] Eleventhly, embodiments of this application provide a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the first to fourth aspects and any of their implementations. Attached Figure Description

[0080] Figure 1 is a schematic diagram of the PUSCH and PDCCH interval provided in an embodiment of this application;

[0081] Figure 2 is a schematic diagram of the beam management inference process provided in an embodiment of this application;

[0082] Figure 3 is a schematic diagram of the inference process for CSI prediction provided in the embodiments of this application;

[0083] Figure 4 is a schematic diagram of the inference process of CSI compression provided in the embodiment of this application;

[0084] Figure 5 is a schematic diagram of a communication system architecture provided in an embodiment of this application;

[0085] Figure 6 is a schematic diagram of another communication system architecture provided in an embodiment of this application;

[0086] Figure 7 is a schematic diagram of an application framework provided in an embodiment of this application;

[0087] Figure 8 is a schematic diagram of another application framework provided in an embodiment of this application;

[0088] Figure 9 is a block diagram of a terminal device-side chip baseband implementation provided in an embodiment of this application;

[0089] Figure 10 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0090] Figures 11 to 21 are schematic diagrams of CPU usage periods provided in the embodiments of this application;

[0091] Figure 22 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0092] Figure 23 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0093] Figure 24 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0094] Figure 25 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0095] In communication systems (e.g., LTE or NR systems), network devices typically determine the downlink data channel resources, MCS, and precoding configurations of terminal devices based on Channel Information Structure (CSI). CSI is a type of channel information that reflects channel characteristics and quality. For example, CSI can be represented by a channel matrix, such as including the channel matrix itself, or it can include the channel's eigenvectors.

[0096] CSI measurement refers to the process by which the receiver calculates channel information based on a reference signal transmitted by the transmitter, i.e., estimating channel information using channel estimation methods. The propagation of a wireless signal in a channel can be represented as Y = HX + N_noise, where Y represents the signal received by the receiver, H represents CSI, X is the reference signal (X represents information known to both the receiver and transmitter), and N_noise represents noise. After acquiring the received signal Y, the receiver can use channel estimation algorithms, such as least squares or minimum mean square error, to perform channel estimation. For example, the reference signal X may include one or more of the following signals: channel state information reference signal (CSI-RS), synchronizing signal / physical broadcast channel block (SSB), CSI interference measurement (CSI-IM), sounding reference signal (SRS), or demodulation reference signal (DMRS). CSI-RS, SSB, and DMRS can be used to measure downlink CSI; SRS and DMRS can be used to measure uplink CSI.

[0097] Taking a frequency division duplex (FDD) communication scenario as an example, since uplink and downlink channels lack reciprocity, or reciprocity cannot be guaranteed, network devices typically send downlink reference signals to terminal devices. The terminal devices then perform channel and interference measurements based on the received downlink reference signals to estimate the downlink channel identity (CSI). The terminal devices can generate a CSI report according to predefined protocol methods or network device configurations, and feed the CSI report back to the network device. This allows the network device to obtain the downlink CSI and select a more suitable channel identity (MCS) for the terminal device, thus better adapting to changing wireless channels.

[0098] For example, CSI may include at least one of the following: channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), time domain channel properties (TDCP), etc.

[0099] In this context, RI indicates the number of downlink transmission layers recommended by the terminal equipment, CQI indicates the modulation and coding scheme recommended by the terminal equipment, and PMI indicates the precoding recommended by the terminal equipment. The number of precoding layers indicated by PMI corresponds to RI. For example, if RI is n, then PMI indicates n layers of precoding, where n is a positive integer.

[0100] It should be understood that the RI, CQI, and PMI values ​​indicated in the aforementioned CSI report are merely suggested values ​​for the terminal device. The network device may perform downlink transmission according to some or all of the information indicated in the CSI report; alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

[0101] In codebook-based CSI feedback, for some codebooks with high overhead, such as R15 type II, R16 type II, and R17 type II, the CSI report content can include two parts: Part 1 and Part 2. CQI and RI belong to Part 1, while PMI belongs to Part 2. Part 2 is typically transmitted via the Physical Uplink Shared Channel (PUSCH). Since the size of Part 2 is not fixed, and multiple CSI reports may need to be transmitted on the same resource, the size of Part 2 to be transmitted may exceed the channel's capacity. In related schemes, when the number of coded modulation symbols (or modulation symbols) in Part 2 to be transmitted exceeds a set threshold, the terminal device can discard lower-priority content based on the report content's priority until the number of coded modulation symbols in Part 2 to be transmitted does not exceed the set threshold. The number of coded modulation symbols in Part 2 to be transmitted and the set threshold can be calculated using formulas and parameters defined in the protocol.

[0102] Taking the CSI feedback method based on the R16 codebook as an example, part 2 of a CSI report can be divided into three groups. In descending order of priority, these three groups are group 0, group 1, and group 2. Group 0 includes oversampling selection (or phase rotation selection), spatial basis indication, and strongest coefficient indication; group 1 includes frequency basis indication, partial coefficient indication, partial coefficient amplitude, and phase; and group 2 includes remaining partial coefficient indication, remaining partial coefficient amplitude, and phase.

[0103] Terminal devices can report the number N of CSI calculations they can process simultaneously, based on their capabilities. cpu That is, the terminal device is configured with N cpu Each CSI processing unit (CPU) is used to process CSI reports configured on all CCs. The CPU usage of the terminal device when processing CSI reports can be categorized into two aspects: the number of CPUs used and the time period during which CPU usage occurs.

[0104] Regarding CPU usage, you can refer to the following settings:

[0105] At a given symbol, if the computation reported by the CSI uses L CPUs, then the terminal device has N CPUs. cpu -L unused CPUs. If a symbol still has N... cpu-L CPUs are not currently occupied, and there are N CSI reports that need to be processed. The CPU usage for each CSI report is... That is, it needs to occupy If there are N CPUs, then the terminal device can process the M highest priority CSI reports out of these N CSI reports, and will not update the NM lowest priority CSI reports, where M is the maximum value that satisfies the following constraint:

[0106] When there is not enough idle CPU, the terminal device may not update the CSI report, but it does not mean that it does not need to provide a CSI report. The terminal device can provide a previously cached CSI report, or it can provide other information according to the settings.

[0107] CPU usage may vary depending on the type of CSI report. For example:

[0108] When performing time-frequency tracking of the phase reference signal (TRS), i.e., when the configuration parameter "reportQuantity" is configured to 'none' and the configuration parameter "CSI-RS-ResourceSet" contains the higher-level parameter "trs-Info", no CPU is used, i.e., CPU usage is 0. cpu =0.

[0109] When measuring the received power of the layer 1 reference signal (L1-RSRP), i.e., when the configuration parameter "reportQuantity" is configured as 'cri-RSRP', 'ssb-Index-RSRP', or 'none' (and the configuration parameter "CSI-RS-ResourceSet" does not contain the higher-layer parameter "trs-Info"), the CPU usage is 1, i.e., the CPU usage is 0. cpu =1.

[0110] When the parameter "reportQuantity" in the configuration parameter "CSI-ReportConfig" is configured as 'tdcp', for CSI reports with latency Y configured by the higher-level parameter Y, the CPU utilization O cpu = (Y+1)÷X, where the value of X is determined based on the capability information reported by the terminal device.

[0111] When the configuration parameter "reportQuantity" is configured as 'cri-RI-PMI-CQI', 'cri-RI-i1', 'cri-RI-i1-CQI', 'cri-RI-CQI', or 'cri-RI-LI-PMI-CQI', the CPU usage is O. cpu =K s , where K s This indicates the number of non-zero power (NZP) CSI-RS resources in the channel measurement resource (CMR).

[0112] When an AP CSI report is triggered, with no PUSCH sent and no CPU occupied, and the AP CSI report is wideband, using a type I codebook or without PMI feedback, and the CMR only has CSI-RS resources on ports 4 or less, it occupies all CPU, i.e., 0. cpu =N cpu .

[0113] For each CSI report processed, the CPU will continuously occupy a certain number of symbols, i.e., the CPU usage time period. The protocol specifies that when the reporting type parameter "reportConfigType" is not set to 'none', the CPU usage time period can be set as follows:

[0114] The CPU usage period for periodic or semi-persistent CSI reports (excluding the initial semi-persistent CSI report on the PUSCH after a physical downlink control channel (PDCCH) trigger report) is from the first orthogonal frequency division multiplexing (OFDM) symbol of the earliest of the latest CSI-RS / CSI-IM / SSB transmission occasions for channel or interference measurements that precedes the CSI reference resource, until the last symbol of the PUSCH / PUCCH carrying the CSI report.

[0115] The CPU usage period for non-periodic CSI reports is from the first symbol after the PDCCH that triggered the CSI report to the last symbol of the PUSCH that carries the report.

[0116] The CPU usage period for the initial semi-persistent CSI report on the PUSCH after PDCCH triggering is from the first symbol after PDCCH to the last symbol of the PUSCH carrying the report.

[0117] A semi-static CSI report on PUSCH configured with an R18 Doppler codebook has a CPU usage time period starting from the latest consecutive K earlier than the CSI reference resource. P The transmission timing of a periodic CSI-RS (P CSI-RS) or semi-persistent CSI-RS (SP CSI-RS) begins with the first symbol and ends with the last symbol of the PUSCH carrying the report. Wherein, K... P ∈{1,2,4}, indicated by the terminal device according to its own capabilities, can be understood as the observation window supported by the terminal device.

[0118] The NR protocol also specifies the CSI calculation time. When triggering a CSI report, network devices can allocate sufficient time for terminal devices to perform CSI calculations according to the specified CSI calculation time. For CSI reports on the PUSCH triggered by downlink control information (DCI), the terminal device will only report a valid CSI report if the following two conditions are met:

[0119] Condition 1: The first uplink symbol carrying the corresponding CSI report (including the impact of timing advance) must begin no earlier than symbol Z. ref .

[0120] Condition 2: The first uplink symbol carrying the nth CSI report (including the effects of timing advance) must start no earlier than symbol Z′. ref (n).

[0121] Among them, Z ref An uplink symbol is defined as the earliest uplink symbol that satisfies the following condition: the interval between the start time of its cyclic prefix (CP) and the end time of the last symbol of the PDCCH that triggered the CSI report is greater than or equal to T. proc,CSI =(Z)(2048+144)·κ2 -μ ·T C When aperiodic CSI-RS is used for channel measurements in the nth triggered CSI report, Z′ ref(n) is defined as an uplink symbol that is the earliest uplink symbol that satisfies the following condition: the interval between the start time of its CP and the end time of the last symbol of the resource that ended the latest is greater than or equal to T′. proc,CSI =(Z′)(2048+144)·κ2 -μ ·T C .

[0122] The above provision can be understood as follows: the time interval between the first symbol of the PUSCH carrying the CSI report and the end time of the last symbol of the PDCCH that triggers the CSI report is greater than or equal to the specified time parameter T. proc,CSI Furthermore, the time interval between the first symbol of the PUSCH carrying the CSI report and the end time of the reference resource used for channel measurements must be greater than or equal to the specified time parameter T′. proc,CSI As shown in Figure 1. When the above conditions are not met, the terminal device does not need to update the reported CSI. The values ​​of Z and Z′ in the above formula can be determined according to the tables and principles given by the protocol. In addition, for non-DCI-triggered reporting (such as periodic reporting, semi-persistent reporting, etc.), the protocol limits the CSI calculation time by defining CSI reference resources to ensure that the terminal device only needs to update the reported CSI when it has sufficient calculation time. The CSI reference resource is defined as a time-frequency resource; in the frequency domain, the CSI reference resource is defined by a set of downlink physical resource blocks corresponding to the frequency band related to the CSI calculation; in the time domain, the CSI reference resource is defined as a valid time slot located before the uplink time slot of the CSI report, and the number of symbols between the time slot where the CSI reference resource is located and the CSI reporting time slot needs to be greater than the value given by the protocol. The CSI-RS used to calculate the CSI report cannot be later than the CSI reference resource. If there is no valid downlink time slot corresponding to a certain CSI reporting configuration, the terminal device may not report the CSI. The above provision can be understood as the time interval between the CSI-RS used to calculate the CSI report and the CSI reporting time slot being greater than or equal to the specified time parameter.

[0123] NR specifies the rules for CSI-RS port and resource activation and counting. In any time slot, the number of CSI-RS ports or resources activated by a terminal device in the active bandwidth part (BWP) shall not exceed the number of CSI-RS ports and resources reported by the terminal device in its capability report.

[0124] NZP CSI-RS resources are active for the duration defined below:

[0125] For AP CSI-RS: It starts from the end time of the PDCCH containing the request and ends at the end time of the scheduling PUSCH containing the report associated with that AP CSI-RS.

[0126] For SP CSI-RS: The period begins from the end time of issuing the activation command and ends at the end time of issuing the deactivation command.

[0127] For P CSI-RS: It starts when the higher-level signaling configuration period CSI-RS is configured and ends when the period CSI-RS configuration is released.

[0128] If a CSI-RS resource is referenced N times by one or more CSI reporting settings without the higher-level parameter "csi-ReportSubConfigToAddModList" configured, the CSI-RS resource and the CSI-RS ports within that resource are counted N times. For periodic or semi-static CSI-RS resources in a set of channel measurement CSI-RS resources linked to a CSI-ReportConfig configuration where the higher-level parameter "codebookType" is configured as 'typeII-Doppler-r18' or 'typeII-Doppler-PortSelection-r18', the CSI-RS resource and the CSI-RS ports within that resource are counted K times. P Next, among which, K P ∈{1,2,4}, as indicated by the terminal device based on its own capabilities.

[0129] With the development of AI technology, it can be applied to more and more scenarios. 3GPP has proposed using AI in NR to improve network performance and user experience through intelligent data collection and analysis.

[0130] Currently, 3GPP has designed multiple application scenarios for AI on the RAN side from working groups such as Radio Access Network (RAN) 3 and RAN1. RAN1 includes CSI-RS feedback enhancement, beam scanning enhancement, and positioning enhancement. These scenarios can be further subdivided into different sub-scenarios, which will be introduced separately below.

[0131] 1. Beam management enhancement

[0132] AI-based beam management enhancements can include sub-scenarios such as beam scanning matrix prediction and optimal beam prediction. Sparse beam prediction based on AI and machine learning (ML) can be used to improve prediction accuracy. A possible AI / ML-based coefficient beam prediction process may include:

[0133] 1) Generation of the initial model: The network device trains a sparse scanning matrix based on the reporting results of the full beam scanning of the SSB by a certain number of terminal devices. This matrix is ​​usually unique to each cell.

[0134] 2) The network device sends the sparse model to the terminal device (e.g., via SIB messages), and the terminal device performs sparse scanning based on this matrix, i.e., beam scanning in the P1 stage.

[0135] 3) Based on the sparse scanning results of the terminal devices, the network devices infer the optimal CSI-RS beam and perform P2 phase scanning. The terminal devices then provide feedback on the optimal CSI-RS beam ID.

[0136] According to the discussion in the 3GPP RAN1 task force, beam management use cases can be divided into beam management use case 1 (BM case 1) and beam management use case 2 (BM case 2). Figure 2 provides an example of the reasoning process for BM case 1 and BM case 2. The model in BM case 1 is a one-side model, meaning the model is deployed on the network (NW) side or the terminal device side. For BM case 1 and BM case 2, the terminal device can report the prediction results to the NW side based on the output of the terminal device-side model, or the NW side can predict the optimal beam (Top-1 / N beams) based on the reports for the set B of models on the NW side.

[0137] BM case 1: Predicting downlink beams for set A (set A) based on measurement results from set B. A possible procedure for BM case 1 might include:

[0138] 1) The base station scans the set B beam, and the base station or terminal equipment obtains the measurement results of set B;

[0139] 2) The AI ​​model of the base station or terminal equipment uses the measurement results of set B as the model input to predict the K best beams (top K beams) on set A.

[0140] BM case 2: Predicting the downlink beam for future set A based on historical measurements of set B. A possible procedure for BM case 2 might include:

[0141] 1) The base station scans the set B beam, and the base station or terminal equipment obtains the measurement results of set B;

[0142] 2) The AI ​​model of the base station or terminal equipment uses the measurement results of set B as the model input to predict the K best beams (top K beams) on set A at future time.

[0143] For models on the terminal device side, model monitoring methods can be categorized as follows:

[0144] Type 1, Network-side monitoring. Furthermore, Type 1 can include: Option 1, where the terminal device reports tags (such as measurement results) and inference results to the network side so that the network side can perform metric calculations; Option 2, where the terminal device reports performance metrics or events based on performance metrics to the network side.

[0145] Type 2: UE-side monitoring. Specifically, the terminal device can report monitoring decisions (such as model selection / activation / deactivation / switching / fallback, etc.) to the network device.

[0146] The performance metric mentioned above may include one or more of the following:

[0147] Key performance indicators (KPIs) related to beam prediction accuracy, such as Top-K / 1 beam prediction accuracy.

[0148] Link quality-related KPIs include throughput, layer 1 reference signal received power (L1-RSRP), layer 1 signal to interference plus noise ratio (L1-SINR), and assumed block error rate (BLER).

[0149] Performance metrics for AI / ML-based input / output data distribution.

[0150] The difference between the measured RSRP and the predicted RSRP is the difference between L1-RSRP.

[0151] For data collection in beam management use cases, information such as L1-RSRPs and / or beam IDs can be collected during training; predicted L1-RSRPs and / or beam IDs can be collected during inference; and L1-RSRPs and / or beam IDs, as well as calculated performance metrics, can be collected during monitoring.

[0152] 2. Positioning accuracy enhancements

[0153] AI-based location enhancement can be used to improve location accuracy. A possible AI-based location enhancement process may include:

[0154] 1) Collect raw data using operator-controlled reference UE (User Equipment);

[0155] 2) The location management function (LMF) and the base station can be trained separately. The LMF model can be used to infer the final positioning (such as latitude and longitude), while the base station model can be used to infer line-of-sight (LOS) / non-line-of-sight (NLOS) positioning.

[0156] 3. CSI-RS feedback enhancement

[0157] AI-based CSI-RS feedback enhancement use cases can include the following two sub-use cases, briefly described below:

[0158] 1) CSI prediction: Time-domain CSI prediction based on terminal device side model.

[0159] Figure 3 provides an example of the inference process for CSI prediction. The AI / ML-based CSI prediction model is used to predict future CSI based on historical CSI. The input / output CSI types can be: original channel matrix, precoding matrix, etc. Preprocessing of the measured channels may be necessary to generate the input to the CSI prediction model; further processing may also be required for the output of the CSI prediction model.

[0160] For model training, training data can be generated by the terminal device. For model inference on the terminal device side, input data is available within the terminal device. For network-side performance monitoring, the calculated performance metrics or the data required for performance metric calculation can be generated by the terminal device and sent to the network side.

[0161] For data collection of CSI prediction use cases, during training, target CSIs within the observation window / prediction window can be collected; during inference, predicted CSIs can be collected; and during monitoring, correctly labeled CSIs (ground truth CSIs), calculated performance metrics, performance monitoring outputs, etc., can be collected.

[0162] 2) CSI compression: Spatial frequency domain / spatial time frequency domain CSI compression based on a two-sided model.

[0163] Figure 4 provides an example of the inference process for CSI compression. The AI / ML-based CSI generation part generates CSI feedback information on the terminal device side; the AI / ML-based CSI reconstruction part reconstructs the CSI on the base station side based on the received CSI feedback information. The AI / ML model input (for the CSI generation part) / output (for the CSI reconstruction part) types can be: original channel matrix or precoding matrix. Preprocessing of the measured channel may be required to generate the input to the CSI generation model; further processing may also be needed for the output of the CSI reconstruction model.

[0164] For the network-side inference portion of a two-sided model, input data can be generated by the terminal device and sent to the network side. For the terminal device-side inference portion of a two-sided model, input data is available within the terminal device. For model training, training data can be generated by the terminal device and / or the network side. For the network-side performance monitoring portion, calculated performance metrics or data used for performance metric calculation can be generated by the terminal device and sent to the network side. To select a CSI generation model compatible with the CSI reconstruction model used by the network side, pairing information can be established based on model identification.

[0165] For CSI feedback enhancement use cases, monitoring methods may include:

[0166] 1) Network-side monitoring, such as estimating AI model / AI performance based on the target CSI (actual channel estimate associated with the CSI report) reported by the terminal device, and further generating monitoring decisions.

[0167] 2) Terminal device-side monitoring: Monitoring can be performed based on the output of the CSI reconstruction model indicated by the network side (the terminal device can be associated with the CSI report in an aligned format), or based on the output of the CSI reconstruction model of the agent on the terminal device side, or by directly estimating intermediate KPIs, or by estimating the monitoring output. The network side can configure thresholds to instruct the terminal device to perform monitoring.

[0168] For data collection of CSI compression test cases, during training, target CSI, CSI feedback information, gradients of CSI feedback information, etc. can be collected; during inference, CSI feedback information, etc. can be collected; during monitoring, target CSI, calculated performance metrics, etc. can be collected.

[0169] In AI-based CSI use cases, the CPUs used to process CSI reports can be further divided into Type I CPUs and Type II CPUs. Type I CPUs handle AI operations within the AI-based CSI reports, such as CSI prediction. Type II CPUs handle non-AI CSI reports, as well as non-AI operations within AI-based CSI reports, such as RS measurement, CSI calculation, AI performance metric calculation, and PUSCH generation. In this context, how network devices and terminal devices determine the CPU usage and CPU usage time periods corresponding to CSI reports is a problem that needs to be solved.

[0170] In view of this, embodiments of this application provide a communication method for determining a new way of measuring CPU usage and CPU usage time periods.

[0171] The communication method provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, Internet of Things (IoT) communication systems, satellite communication systems, future communication systems such as 6th generation (6G) mobile communication systems, or integrated systems of multiple systems. The communication method 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.

[0172] In a communication system, a network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. A network element can also be replaced by an entity, network entity, device, communication device, 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 application embodiment 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 in this application embodiment.

[0173] Figure 5 provides an exemplary system architecture diagram applicable to an embodiment of this application. As shown in Figure 5, the communication system 100 may include at least one network device 110; the communication system 100 may also include at least one terminal device 120, and further, may include a terminal device 130. The network device 110 and the terminal device 120 can communicate via a wireless link. The communication devices in this communication system, for example, the network device 110 and the terminal device 120, can communicate via multi-antenna technology.

[0174] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. 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, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and supporting beam management, network energy saving has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (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.

[0175] Figure 6 is a schematic diagram of another communication system applicable to the communication method of this application embodiment. Compared with the communication system 100 shown in Figure 5, the communication system 200 shown in Figure 6 may further include an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building a training dataset or training an AI model.

[0176] In one possible implementation, network device 110 can send data related to the training of the AI ​​model to AI network element 140, 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 terminal devices. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal devices. 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 110, and another portion on terminal devices 120 / 130. Alternatively, the trained AI model may be deployed on network device 110; or, the trained AI model may be deployed on terminal devices 120 / 130.

[0177] It should be understood that Figure 6 is only used as an example of AI network element 140 being directly connected to network device 110. In other scenarios, AI network element 140 can also be connected to terminal devices 120 / 130. Alternatively, AI network element 140 can be connected to both network device 110 and terminal devices 120 / 130 simultaneously. Alternatively, AI network element 140 can also be connected to network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between AI network element 140 and other network elements.

[0178] In addition, the AI ​​network element 140 can also be set as a module in network device 110 and / or terminal devices 120, 130.

[0179] It should be noted that Figures 5 and 6 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as core network devices, wireless relay devices, wireless backhaul devices, etc., which are not shown in Figures 5 and 6. In practical applications, the communication system may include multiple network devices or multiple terminal devices. The embodiments of this application do not limit the number of network devices and terminal devices included in the communication system.

[0180] 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 apparatus.

[0181] 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 vehicles, 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.

[0182] 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 a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0183] 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.

[0184] The network device in this application embodiment can be a device used to communicate 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 vehicle-to-everything (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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. DU is configured to implement one or more functions preceding layer mapping (such as coding, rate matching, scrambling, modulation, and one or more of layer mapping functions), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT), or adding a cyclic prefix (CP)) are moved to RU. For uplink transmission, de-RE mapping is used as the dividing line. DU is configured to implement one or more functions preceding de-mapping (such as decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and one or more of de-RE mapping functions), while other functions following de-mapping (e.g., digital BF or fast Fourier transform (FFT), or removing CP) are moved to RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0190] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] AI nodes can be AI network elements or AI modules.

[0198] Figure 7 illustrates a possible application framework in a communication system. As shown in Figure 7, network elements in the communication system are connected via interfaces (e.g., NG interfaces, Xn interfaces) or air interfaces. These network element nodes, such as core network equipment, access network nodes (i.e., the aforementioned network equipment, such as RAN nodes), terminal equipment, or one or more devices in OAM, are equipped with one or more AI modules (only one is shown in Figure 7). Access network equipment can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. One or more AI modules can also be set in CU and / or DU. Optionally, CU can also be split into CU-CP and CU-UP. One or more AI models can also be set in CU-CP and / or CU-UP.

[0199] 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.

[0200] 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.

[0201] Network devices can be those equipped with one or more AI modules. For example, an AI module can be a RAN intelligent controller (RIC) as shown in Figure 8, such as a near-real-time RIC or a non-real-time RIC. For instance, a near-real-time RIC can be located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC can be located in an OAM, a cloud server, a core network device, or other network devices. The RIC can obtain subsets from multiple terminal devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset, and then train based on the training dataset. Exemplarily, near-real-time and non-real-time RICs can also be configured as separate network elements; the network device can be either a near-real-time RIC or a non-real-time RIC.

[0202] Figure 8 illustrates another possible application framework in a communication system. As shown in Figure 8, the communication system includes a RAN intelligent controller (RIC). The RIC can be used to implement AI-related functions. RICs can include near-real-time (near-RT) RICs and non-real-time (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.

[0203] The near real-time RIC can be used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from access network 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 the inference results to the access network 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 the inference results to the DU, and the DU sends them to the RU.

[0204] The 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.

[0205] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and 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 CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0206] Figure 9 is a block diagram of a terminal device-side chip baseband implementation provided in an embodiment of this application. As shown in Figure 9, the terminal device chip baseband can be implemented using a processing system of one or more processors. The processor may include a microprocessor (e.g., x86, ARM), a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), a GPU, a programmable logic device (PLD), a state machine, gated logic, discrete hardware circuits, and other suitable hardware configured to various functions. That is, the processor used in the baseband can be used to implement the processes described below and any one or more of those processes.

[0207] A processing system can be implemented using a bus architecture, typically represented by a bus. A bus can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the processing system. The bus communicatively couples various circuits together, including one or more processors (typically represented by a processor), memory, and computer-readable media (typically represented by a computer-readable media). The bus can also link various other circuits, such as timing sources, peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further. The bus interface provides the interface between the bus and transceivers, and between the bus and the interface.

[0208] A transceiver provides a communication interface or means for communicating with various other devices via a wireless transmission medium. The transceiver may be coupled to an antenna array, and the transceiver and antenna array may be used together for communication with a corresponding network type. At least one interface (e.g., a network interface and / or a user interface) provides a communication interface or means for communication via an internal bus or via an external transmission medium.

[0209] The processor is responsible for managing the bus and general processing, including executing software stored on a computer-readable medium. When the processor executes the software, the software causes the processing system to perform the various functions described below for any particular device.

[0210] The functions that can be implemented by the processor, memory, and computer-readable medium may include: encoding, decoding, rate matching, rate dematching, scrambling, descrambling, modulation, demodulation, layer mapping, FFT, IFFT, IDFT, precoding, RE mapping, channel equalization, RE mapping, digital BF, adding CP, removing CP, etc.

[0211] The communication method provided in this application embodiment can be applied to the above-described communication system / framework. As shown in Figure 10, the communication method may include the following steps:

[0212] Step 101: The first device determines the CPU usage count and CPU usage time period corresponding to the first report according to the first rule.

[0213] The first device can be a network device, or a communication module / processing module within a network device, or a circuit or chip within a network device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), or a circuit or chip within a network device responsible for processing functions (such as a graphics processing unit (GPU), an AI processor, or an application-specific integrated circuit (ASIC)). In other words, the communication method provided in the embodiments of this application can be implemented by a network device.

[0214] Alternatively, the first device may also be a terminal device, or a communication module / processing module in the terminal device, or a circuit or chip in the terminal device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip in the terminal device responsible for processing functions (such as a GPU, AI processor, or ASIC)). In other words, the communication method provided in the embodiments of this application can be implemented by a terminal device.

[0215] The aforementioned first report is an AI-based report. For example, the first report can be a CSI report corresponding to the AI ​​inference result, or a CSI report carrying the AI ​​inference result, or a UE report corresponding to the AI ​​inference result, or a UE report carrying the AI ​​inference result, etc.

[0216] The first rule mentioned above can be pre-configured. For example, the first rule can be set in the communication protocol and pre-configured in the network device and / or terminal device, so that the network device and / or terminal device can determine the CPU usage and CPU usage time period corresponding to the first report according to the first rule.

[0217] The CPU usage count mentioned above includes the first CPU usage count and the second CPU usage count. The CPU usage time period includes the first CPU usage time period and the second CPU usage time period. The first CPU usage time period corresponds to the first CPU usage count, and the second CPU usage time period corresponds to the second CPU usage count.

[0218] Specifically, the first CPU utilization is less than or equal to the first maximum CPU utilization, which is the number of CSI calculations corresponding to AI execution processes that the terminal device can support processing simultaneously. The second CPU utilization is less than or equal to the second maximum CPU utilization, which is the number of CSI calculations corresponding to non-AI execution processes that the terminal device can support processing simultaneously.

[0219] Step 102: The first device communicates with the second device based on the CPU usage count and CPU usage time period.

[0220] When the first device is a network device or a device in a network device, the second device may be a terminal device, or a communication module / processing module in the terminal device, or a circuit or chip in the terminal device that is responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip in the terminal device that is responsible for processing functions (such as a GPU, AI processor, or ASIC).

[0221] When the first device is a terminal device or a device in a terminal device, the second device may be a network device, or a communication module / processing module in a network device, or a circuit or chip in a network device that is responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip in a network device that is responsible for processing functions (such as a GPU, AI processor, or ASIC).

[0222] In one possible implementation, the second device also determines the CPU usage count and CPU usage time period corresponding to the first report according to the first rule, thereby enabling the first device and the second device to align the CPU usage count and CPU usage time period.

[0223] The first and second devices can transmit the first report based on the CPU usage and CPU usage time period corresponding to the first report. For example, when the network device schedules the terminal device to send back the first report, it reserves computing time for the terminal device based on the CPU usage and CPU usage time period. If the terminal device needs to send back multiple reports on the resource for which the first report is sent, but it is determined based on the CPU usage and CPU usage time period that the terminal device cannot send back multiple reports on the corresponding resource in time, then the network device and the terminal device can determine which reports the terminal device will not update based on the priority of each report.

[0224] In one possible implementation, the first communication device may determine the number of CPUs occupied and the time period occupied by the first CPU according to the first rule, and / or determine the number of CPUs occupied and the time period occupied by the second CPU according to the first rule.

[0225] The first CPU is used to process the AI-based execution process in the first report, such as the AI ​​model's inference process, the AI ​​model's training process, and AI-related processing processes.

[0226] The second CPU is used to handle non-AI execution processes in the first report, such as RS measurement, CSI calculation, AI performance metric calculation, PUSCH generation, etc.

[0227] For example, the first report is a CSI inference report, used to report the terminal device's prediction information for future CSI. The terminal device needs to measure the received reference signal (RS), calculate the CSI, predict the CSI (inputting the calculated CSI into the AI ​​model to obtain the predicted CSI information), and finally generate the first report based on the predicted CSI information. In this process, the measurement of RS, the calculation of CSI, and the generation of the first report are executed by the second CPU, while the CSI prediction process is executed by the first CPU.

[0228] For example, the first report is a CSI monitoring report, used to report the CSI predicted by the terminal device at time t1 and the actual CSI at time t1. The terminal device needs to measure the RS received at time t0 and calculate the CSI, as shown in Figure 11. It then predicts the CSI at time t1 based on the CSI at time t0; next, it measures and calculates the CSI on the RS received at time t1; and finally, it generates the first report based on the predicted CSI at time t1 and the CSI calculated at time t1. In this process, the measurement and CSI calculation of RS at time t0, the measurement and CSI calculation of RS at time t1, and the generation of the first report are executed by the second CPU; the prediction of the CSI at time t1 is executed by the first CPU.

[0229] In one possible implementation, the first rule mentioned above includes a first CPU usage number corresponding to the first report as a first value, and the first value corresponds to a first CPU usage time period.

[0230] The determination of the first CPU occupancy period can include the following three methods:

[0231] Method 1

[0232] The start time of the first CPU occupancy period is at least one of the following times: the time when the CSI calculation of all measurement resources corresponding to the first report is completed, the time when the CSI calculation of the first measurement resource is completed, and the end time of the last measurement resource.

[0233] The first measurement resource mentioned above is the earliest measurement resource among at least one measurement resources corresponding to the first report; the last measurement resource mentioned above is the latest measurement resource among at least one measurement resources corresponding to the first report.

[0234] In the embodiments of this application, the measurement resources may include one or more of the following resources: CSI-RS resources, CSI-IM resources, and SSB resources. For example, when the first report is a CSI inference report, the measurement resources may be CSI-RS / CSI-IM / SSB resources within the observation window corresponding to the first report; when the first report is a CSI monitoring report, the measurement resources may be CSI-RS / CSI-IM / SSB resources within the monitoring window corresponding to the first report.

[0235] In this embodiment, the time when the CSI calculation is completed can be Z' time units after the last time unit of the measurement resource; where Z' can be a time unit specified by the protocol, and the Z' time units can include the time for channel estimation and CSI calculation. In this embodiment, the time unit can be replaced by a time-domain symbol (such as an OFDM symbol), a time slot, etc.

[0236] In the embodiments of this application, the termination time of the measurement resource may refer to the last time unit of the measurement resource, for example, the last symbol of the measurement resource.

[0237] For example, as shown in Figure 12, the measurement resources corresponding to the first report include the resources corresponding to the first reference signal (RS) and the second RS. The resources corresponding to the RS can be understood as the resources corresponding to the occasion of CSI-RS / CSI-IM / SSB. For example, the resources corresponding to the first RS can be understood as the resources corresponding to the occasion of the first CSI-RS / CSI-IM / SSB, and the resources corresponding to the second RS can be understood as the resources corresponding to the occasion of the second CSI-RS / CSI-IM / SSB. The terminal device measures the first RS and the second RS, calculates the CSI, and predicts the CSI corresponding to the third RS and the fourth RS. In the above process, the last symbol carrying the first RS corresponds to time t1, and the terminal device completes the CSI calculation for the first RS at time t2. The last symbol carrying the second RS corresponds to time t3, and the terminal device completes the CSI calculation for the second RS at time t4. Therefore, the start time of the first CPU occupancy period can be time t2, time t3, or time t4.

[0238] The termination time corresponding to the first CPU occupancy period is at least one of the following: the time when the AI ​​execution process is completed, or the last time unit (such as a symbol) of the uplink time unit carrying the first report.

[0239] Taking Figure 12 as an example, the terminal device completes the CSI prediction for the third and fourth RS at time t5 and sends the first report to the network device. The last symbol carrying the first report corresponds to time t6. Therefore, the end time of the first CPU occupancy period can be either time t5 or time t6.

[0240] Method 2

[0241] The first CPU occupancy period may include at least one first time period, with each first time period corresponding one-to-one with at least one measurement resource corresponding to the first report. For example, in the example shown in Figure 12, the first report corresponds to the resource corresponding to the first RS and the resource corresponding to the second RS. Therefore, the first CPU occupancy period may include two first time periods, corresponding to the resources corresponding to the first RS and the second RS, respectively. The processing unit corresponding to the first CPU of the terminal device performs an AI execution process based on the CSI calculation result of the corresponding RS within each first time period, such as performing CSI prediction based on the CSI calculation result of the corresponding RS.

[0242] The start time for each first time period can be at least one of the following: the time when the CSI calculation of the measurement resource corresponding to the first time period is completed, or the last time unit (such as a symbol) of the measurement resource corresponding to the first time period.

[0243] The end time for each first time period can be X1 time units (such as symbols) following the start time of that first time period. These X1 time units correspond to the time units corresponding to the AI ​​execution process, or they can include the time units corresponding to the AI ​​execution process.

[0244] For example, as shown in Figure 13, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS. Therefore, the first CPU occupancy time period includes two first time periods: first time period 1 and first time period 2. First time period 1 corresponds to the resources corresponding to the first RS, and first time period 2 corresponds to the resources corresponding to the second RS. The last symbol corresponding to the first RS is symbol A. After Y symbols, the terminal device completes the CSI calculation for the first RS, and after X1-Y symbols, it completes the AI ​​execution process, i.e., inference and prediction based on the CSI of the first RS. The last symbol corresponding to the second RS is symbol B. After Y symbols, the terminal device completes the CSI calculation for the second RS, and after X1-Y symbols, it completes the AI ​​execution process. Therefore, the start time of first time period 1 can be symbol A or symbol A+Y; the end time of first time period 1 can be symbol A+X1. The start time of first time period 2 can be symbol B or symbol B+Y; the end time of first time period 2 can be symbol B+X1.

[0245] Method 3

[0246] The start time corresponding to the first CPU occupancy time period is the start time of the first measurement resource, which is the first time unit (such as a symbol) of the first measurement resource. The first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report.

[0247] The termination time corresponding to the first CPU occupancy period is the last time unit (such as a symbol) of the uplink time unit carrying the first report.

[0248] The first time unit can be replaced with the earliest time unit, and the last time unit can be replaced with the latest time unit.

[0249] For example, as shown in Figure 14, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS. The first symbol corresponding to the first RS is symbol A; the last symbol carrying the first report is symbol B. Then, the start time of the first CPU occupancy time period can be symbol A, and the end time can be symbol B.

[0250] The first device and the second device can determine the first CPU occupancy time period using any of the three methods described above. The first CPU occupancy number corresponding to each time period in the first CPU occupancy time period can be the CPU occupancy number of the terminal device for the AI ​​execution process reported by the terminal device, or it can be the CPU occupancy number of the terminal device for the AI ​​execution process indicated by the terminal device, or it can be a preset CPU occupancy number of the terminal device for the AI ​​execution process.

[0251] Terminal devices can report their initial CPU usage for one or more AI execution processes to the network device. For example, a terminal device can report its initial CPU usage during CSI model training, CSI inference, and other model training and inference. Alternatively, the terminal device can send parameters determining the initial CPU usage to the network device, instructing the network device to determine the initial CPU usage based on the parameters reported by the terminal device. Alternatively, the initial CPU usage for one or more AI execution processes can be pre-configured for the terminal device, for example, by pre-setting it in the communication protocol, allowing the network device and the terminal device to determine the initial CPU usage according to the communication protocol.

[0252] In one possible implementation, the first rule mentioned above includes the second CPU usage number corresponding to the first report being a second value, and the second value corresponding to the first CPU usage time period.

[0253] The determination of the first time period occupied by the second CPU can include the following four methods:

[0254] Method 1

[0255] The start time corresponding to the first time period occupied by the second CPU is the start time of the first measurement resource, that is, the first time unit (such as a symbol) of the first measurement resource. The first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report.

[0256] The termination time corresponding to the first occupied time period of the second CPU is the last time unit (such as a symbol) of the uplink time unit carrying the first report.

[0257] Taking Figure 14 as an example, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS. The first symbol corresponding to the first RS is symbol A; the last symbol carrying the first report is symbol B. Therefore, the start time of the first time period occupied by the second CPU can be symbol A, and the end time can be symbol B.

[0258] Method 2

[0259] The first time period occupied by the second CPU may include a second time period and a third time period. During the second time period, the processing unit corresponding to the second CPU of the terminal device performs CSI calculation on at least one measurement resource corresponding to the first report; during the third time period, it generates the first report based on the AI ​​execution result sent by the processing unit corresponding to the first CPU.

[0260] The start time corresponding to the second time period can be the start time of the first measurement resource, that is, the first time unit of the first measurement resource (such as a symbol). The first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report.

[0261] The termination time corresponding to the second time period can be the time when the CSI calculation of the last measurement resource is completed, or the time when the processing unit corresponding to the second CPU sends the CSI calculation result of the last measurement resource to the processing unit corresponding to the first CPU; the last measurement resource is the latest measurement resource among at least one measurement resource corresponding to the first report.

[0262] The start time of the third time period can be the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed.

[0263] The termination time corresponding to the third time period can be the last time unit (such as a symbol) of the uplink time unit that carries the first report.

[0264] For example, as shown in Figure 15, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the second RS. The first symbol corresponding to the first RS is symbol A. The processing unit corresponding to the second CPU completes the CSI calculation for the first RS and the second RS at symbol B, and sends the CSI calculation results of the first RS and the second RS to the processing unit corresponding to the first CPU at symbol C. The processing unit corresponding to the first CPU performs AI prediction based on the CSI calculation results of the first RS and the second RS, obtains the AI ​​execution result at symbol D, and sends the AI ​​execution result to the CPU processing unit corresponding to the second CPU at symbol E. The last symbol carrying the first report is symbol F.

[0265] Then, the start time of the second period in the first occupied time period of the second CPU can be symbol A, and the end time of the second period can be symbol B or symbol C; the start time of the third period in the first occupied time period of the second CPU can be symbol D or symbol E, and the end time of the third period can be symbol F.

[0266] Method 3

[0267] The first CPU occupancy period may include at least one second period and one third period. The at least one second period corresponds one-to-one with at least one target measurement resource, which is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report; the third period corresponds to the last measurement resource, which is the latest measurement resource among the multiple measurement resources corresponding to the first report.

[0268] For example, if the first report corresponds to two RSs, then the first time period occupied by the second CPU can include a second time period and a third time period; then the second time period corresponds to the first RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation of the first RS in the second time period; the third time period corresponds to the second RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation of the second RS in the third time period, and generates the first report based on the AI ​​execution result.

[0269] For example, if the first report corresponds to three RSs, then the first time period occupied by the second CPU can include second time period 1, second time period 2, and third time period. Specifically, second time period 1 corresponds to the first RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the first RS during second time period 1; second time period 2 corresponds to the second RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the second RS during second time period 2; third time period corresponds to the third RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the third RS during third time period, and generates the first report based on the AI ​​execution results.

[0270] The start time corresponding to each second time period can be the start time of the corresponding target measurement resource, that is, the first time unit of the corresponding target measurement resource (such as a symbol).

[0271] The end time for each second time period can be the time when the CSI calculation for the corresponding target measurement resource is completed.

[0272] The start time corresponding to the third time period can be the start time of the last measurement resource, that is, the first time unit of the last measurement resource (such as a symbol).

[0273] The termination time corresponding to the third time period can be the last time unit (such as a symbol) of the uplink time unit that carries the first report.

[0274] For example, as shown in Figure 16, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS. The first symbol corresponding to the first RS is symbol A. The processing unit corresponding to the second CPU completes the CSI calculation for the first RS at symbol B. The first symbol corresponding to the second RS is C. The processing unit corresponding to the second CPU completes the CSI calculation for the second RS at symbol D. The last symbol carrying the first report is symbol E. Therefore, the start time of the second period within the first occupied time period of the second CPU can be symbol A, and the end time of the second period can be symbol B; the start time of the third period within the first occupied time period of the second CPU can be symbol C, and the end time of the third period can be symbol E.

[0275] Method 4

[0276] The first time period occupied by the second CPU may include at least one second time period and one third time period, with at least one second time period corresponding one-to-one with at least one measurement resource corresponding to the first report. The processing unit corresponding to the second CPU of the terminal device performs CSI calculation on the RS on the corresponding measurement resource during each second time period, and generates the first report based on the AI ​​execution result obtained by the processing unit corresponding to the first CPU during the third time period.

[0277] The start time of each second time period can be the start time of the corresponding measurement resource, i.e., the first time unit of the corresponding measurement resource (such as a symbol). The end time of each second time period can be the time when the CSI calculation of the corresponding measurement resource is completed.

[0278] The start time of the third time period can be the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed. The end time of the third time period can be the last time unit (such as a symbol) of the uplink time unit carrying the first report.

[0279] For example, as shown in Figure 17, the measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS. The first symbol corresponding to the first RS is symbol A. The processing unit corresponding to the second CPU completes the CSI calculation for the first RS at symbol B. The first symbol corresponding to the second RS is C. The processing unit corresponding to the second CPU completes the CSI calculation for the second RS at symbol D. The processing unit corresponding to the first CPU obtains the AI ​​execution result at symbol E and sends the AI ​​execution result to the CPU processing unit corresponding to the second CPU at symbol F. The last symbol carrying the first report is symbol G.

[0280] Then, the start time of the second period 1 in the first time period of the second CPU is symbol A, and the end time is symbol B; the start time of the second period 2 is symbol C, and the end time is symbol D; the start time of the third period is symbol E or symbol F, and the end time of the third period is symbol G.

[0281] The first and second devices can determine the second CPU's occupancy period using any of the four methods described above. The second CPU occupancy count corresponding to each period in the first occupancy period, i.e., the second value, can be the CPU occupancy count measured by the reference signal reported by the terminal device, or the CPU occupancy count measured by the reference signal preset by the terminal device, or the CPU occupancy count reported by the terminal device for non-AI execution processes in the AI ​​report, or the CPU occupancy count indicated by the terminal device for non-AI execution processes in the AI ​​report, or a preset (as specified in the protocol) CPU occupancy count for non-AI execution processes in the AI ​​report.

[0282] Terminal devices can report their second CPU usage for non-AI execution processes within one or more AI reports to the network device. For example, a terminal device can report its second CPU usage for processes such as RS measurement, CSI calculation, metric calculation, and PUSCH generation. Alternatively, the terminal device can send parameters for determining the second CPU usage to the network device, instructing the network device to determine the second CPU usage based on the parameters reported by the terminal device. Alternatively, the second CPU usage for one or more non-AI execution processes can be pre-configured for the terminal device, for example, by pre-setting it in the communication protocol, allowing the network device and the terminal device to determine the second CPU usage according to the communication protocol.

[0283] Optionally, the method in the foregoing embodiments of determining the first CPU usage as a first value and the first value corresponding to a first CPU usage time period according to the first rule can be applied to AI-based inference reports, i.e., the first report carries AI inference results. Similarly, the method in the foregoing embodiments of determining the second CPU usage as a second value and the second value corresponding to a first CPU usage time period according to the first rule can also be applied to AI-based CSI inference reports.

[0284] Optionally, when the first report carries AI monitoring results, the first device and the second device may also determine the first CPU usage count and the first CPU usage time period corresponding to the first report according to the first rule, and / or determine the second CPU usage count and the second CPU usage time period corresponding to the first report according to the first rule.

[0285] Since the first report contains AI monitoring results, and the generation of AI monitoring results requires both measurement results and AI execution results (i.e., AI inference results), there are four possible scenarios when the terminal device determines that it needs to generate and feed back the first report:

[0286] Scenario 1: The measurement results and AI execution results required for the first report have been obtained.

[0287] In this situation, since the terminal device has already obtained the AI ​​execution result required for the first report, the first CPU does not need to perform the AI ​​execution process again. Therefore, the first CPU usage for the first report is 0, meaning it does not occupy the first CPU.

[0288] The second CPU no longer needs to perform RS measurement and CSI calculation. It can perform metric calculation and PUSCH generation based on the obtained measurement results and AI execution results.

[0289] In case 1, the first rule could include: the second CPU usage number corresponding to the first report is the fourth value, and the fourth value corresponds to the second CPU usage time period.

[0290] The fourth value is either 1 or a preset fixed value, which is the second CPU usage number when performing metric calculation and PUSCH generation.

[0291] The termination time corresponding to the second CPU occupancy period is the last time unit (such as a symbol) of the uplink time unit carrying the first report. The duration of the second CPU occupancy period can be a preset duration. Since the time for the second CPU to perform metric calculation and PUSCH generation can be a preset duration, the occupancy period of the second CPU is the preset duration before the last time unit carrying the first report, as shown in Figure 18.

[0292] Scenario 2: The AI ​​execution results required for the first report have been obtained, but the measurement results required for the first report have not been obtained.

[0293] In this situation, since the terminal device has already obtained the AI ​​execution result required for the first report, the first CPU does not need to perform the AI ​​execution process again. Therefore, the first CPU usage for the first report is 0, meaning it does not occupy the first CPU.

[0294] In case 2, the first rule may also include the second CPU usage number corresponding to the first report being the fifth value, and the fifth value corresponding to the third CPU usage time period.

[0295] The determination of the third time period occupied by the second CPU can include the following two methods:

[0296] Method 1

[0297] The start time corresponding to the third occupancy period of the second CPU can be the start time of the first measurement resource, that is, the first time unit (such as a symbol) of the first measurement resource. The first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report. For example, if all measurement resources corresponding to the first report include the resources corresponding to the first RS and the resources corresponding to the second RS, then the start time of the third occupancy period of the second CPU can be the first time unit corresponding to the first RS.

[0298] The termination time corresponding to the third occupancy period of the second CPU can be the time when the first report was generated, or it can be the last time unit (such as a symbol) of the uplink time unit carrying the first report. For example, if the second CPU of the terminal device generates the first report on symbol A and completes the transmission of the first report on symbol B, that is, the last symbol carrying the first report is symbol B, then the termination time of the third occupancy period of the second CPU can be either symbol A or symbol B.

[0299] The fifth value mentioned above can be the CPU usage of the terminal device in the AI ​​report for non-AI execution processes reported by the terminal device, or it can be the CPU usage of the terminal device in the AI ​​report for non-AI execution processes indicated by the terminal device, or it can be a preset CPU usage of the terminal device in the AI ​​report for non-AI execution processes.

[0300] Method 2

[0301] The second CPU third occupancy time period includes at least one fourth time period and one fifth time period. At least one fourth time period corresponds one-to-one with at least one target measurement resource. The at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report. The fifth time period corresponds to the last measurement resource. The last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report.

[0302] For example, if the first report corresponds to two measured RSs, then the third time period occupied by the second CPU may include a fourth time period and a fifth time period; wherein, the fourth time period corresponds to the first RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation of the first RS in the fourth time period; the fifth time period corresponds to the second RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation of the second RS in the fifth time period, as well as performs metric calculation and generates the first report based on the AI ​​execution results.

[0303] For example, if the first report corresponds to three measured RSs, then the third time period occupied by the second CPU can include the fourth time period 1, the fourth time period 2, and the fifth time period. Specifically, the fourth time period 1 corresponds to the first RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the first RS during the fourth time period 1; the fourth time period 2 corresponds to the second RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the second RS during the fourth time period 2; the fifth time period corresponds to the third RS, and the processing unit corresponding to the second CPU of the terminal device completes the CSI calculation for the third RS during the fifth time period, as well as performing metric calculations based on the AI ​​execution results and generating the first report.

[0304] The start time corresponding to each fourth time period is the start time of the corresponding target measurement resource, that is, the first time unit of the corresponding target measurement resource (such as a symbol).

[0305] The end time for each fourth time period is the time when the CSI calculation for the corresponding target measurement resource is completed.

[0306] The starting time corresponding to the fifth time period is the starting time of the last measurement resource, that is, the first time unit of the last measurement resource (such as a symbol).

[0307] The termination time corresponding to the fifth time period is the last time unit (such as a symbol) of the uplink time unit that carries the first report;

[0308] The fifth value corresponding to each fourth and fifth time period can be the CPU usage count reported by the terminal device or measured by the reference signal preset by the terminal device, or the CPU usage count measured by the reference signal preset by the terminal device, or the CPU usage count of the terminal device for non-AI execution processes in the AI ​​report reported by the terminal device, or the CPU usage count of the terminal device for non-AI execution processes in the AI ​​report indicated by the terminal device, or the preset CPU usage count of the terminal device for non-AI execution processes in the AI ​​report.

[0309] Scenario 3: The measurement results required for the first report have been obtained, but the AI ​​execution results required for the first report have not been obtained.

[0310] In this situation, since the terminal device has obtained the measurement results required for the first report, but not the AI ​​execution results required for the first report, the terminal device needs to perform the AI ​​execution process based on the first CPU to obtain the AI ​​execution results; there is no need to perform RS measurement and CSI calculation based on the second CPU. The terminal device can perform metric calculation, PUSCH generation, and other operations based on the obtained measurement results and the AI ​​execution results obtained by the first CPU.

[0311] In case 3, the first rule could include: the first CPU usage number corresponding to the first report is the third value, and the third value corresponds to the second CPU usage time period.

[0312] The determination of the first CPU second occupancy time period is similar to that in the aforementioned embodiments, and may also include the following three methods:

[0313] Method 1

[0314] The start time of the second CPU occupancy period is at least one of the following: the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result in the first report is completed; the time when the CSI calculation of the first measurement resource corresponding to the AI ​​execution result in the first report is completed; and the end time of the last measurement resource corresponding to the AI ​​execution result in the first report. For example, as shown in Figure 19, the AI ​​execution result in the first report corresponds to the CSI prediction results of the third RS and the fourth RS. The CSI prediction results of the third and fourth RS are determined based on the measurement results of the first RS and the second RS. Therefore, the start time of the second CPU occupancy period can be the time when the CSI calculation of the first RS and the second RS is completed, i.e., symbol C; it can also be the time when the CSI calculation of the first RS is completed, i.e., symbol A; or it can be the end time of the second RS, i.e., symbol B.

[0315] The termination time corresponding to the second occupancy period of the first CPU can be at least one of the following: the time when the AI ​​execution process is completed, or the last time unit (such as symbol) of the uplink time unit carrying the first report. Taking Figure 19 as an example, the processing unit corresponding to the first CPU of the terminal device completes the CSI prediction of the third RS and the fourth RS at symbol D, and completes the sending of the first report to the network device at symbol E. Then, the termination time of the second occupancy period of the first CPU can be either symbol D or symbol E.

[0316] Method 2

[0317] The first CPU second occupancy time period may include at least one sixth time period, and at least one sixth time period corresponds one-to-one with at least one measurement resource corresponding to the AI ​​execution result in the first report. For example, in the example shown in Figure 20, the AI ​​execution result in the first report corresponds to the CSI prediction result of the third RS and the CSI prediction result of the fourth RS. The CSI prediction results of the third and fourth RS are determined based on the measurement results of the first RS and the second RS. Therefore, the first CPU second occupancy time period may include two sixth time periods, corresponding to the resources corresponding to the first RS and the second RS, respectively. The processing unit corresponding to the first CPU of the terminal device performs the AI ​​execution process based on the CSI calculation result of the corresponding RS in each sixth time period, such as performing CSI prediction based on the CSI calculation result of the corresponding RS.

[0318] The start time for each sixth time period can be at least one of the following: the time when the CSI calculation for the measurement resource corresponding to the sixth time period is completed, or the last time unit (e.g., symbol) of the measurement resource corresponding to the sixth time period.

[0319] The end time for each sixth time period can be X1 time units (such as symbols) following the start time of that sixth time period. These X1 symbols correspond to the time units corresponding to the AI ​​execution process, or they can include the time units corresponding to the AI ​​execution process.

[0320] For example, as shown in Figure 20, the AI ​​execution result in the first report corresponds to the CSI prediction results of the third RS and the fourth RS. The CSI prediction results of the third and fourth RS are determined based on the measurement results of the first and second RS. Therefore, the second CPU occupancy time period can include the sixth time period 1 and the sixth time period 2. The sixth time period 1 corresponds to the resources corresponding to the first RS, and the sixth time period 2 corresponds to the resources corresponding to the second RS. The last symbol of the first RS is symbol A. After Y symbols, the terminal device completes the CSI calculation for the first RS, and after X1-Y symbols, the AI ​​execution process is completed, i.e., inference prediction is performed based on the CSI of the first RS. The last symbol corresponding to the second RS is symbol B. After Y symbols, the terminal device completes the CSI calculation for the second RS, and after X1-Y symbols, the AI ​​execution process is completed. Therefore, the start time of the sixth time period 1 can be symbol A or symbol A+Y, and the end time of the sixth time period 1 can be A+X1. The start time of the sixth time period 2 can be symbol B or symbol B+Y; the end time of the sixth time period 2 can be symbol B+X1.

[0321] Method 3

[0322] The start time corresponding to the second CPU occupancy period is the start time of the first measurement resource corresponding to the AI ​​execution result in the first report. The first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the AI ​​execution result in the first report.

[0323] The termination time corresponding to the second CPU occupancy period is the last time unit (such as a symbol) of the uplink time unit carrying the first report.

[0324] For example, as shown in Figure 21, the AI ​​execution result in the first report corresponds to the CSI prediction result of the third RS and the CSI prediction result of the fourth RS. The CSI prediction results of the third and fourth RS are determined based on the measurement results of the first RS and the second RS. The first symbol corresponding to the first RS is symbol A; the last symbol carrying the first report is symbol B. Therefore, the start time of the second time period occupied by the first CPU can be symbol A, and the end time can be symbol B.

[0325] The first device and the second device can determine the first CPU second occupancy time period using any of the three methods described above. The first CPU occupancy number corresponding to each time period in the first CPU second occupancy time period, i.e., the third value, can be the CPU occupancy number of the terminal device for the AI ​​execution process reported by the terminal device, or it can be the CPU occupancy number of the terminal device for the AI ​​execution process indicated by the terminal device, or it can be a preset CPU occupancy number of the terminal device for the AI ​​execution process.

[0326] In case 3, the first rule may also include: the second CPU usage number corresponding to the first report is the sixth value, and the sixth value corresponds to the fourth time period of second CPU usage.

[0327] The end time of the fourth time period occupied by the second CPU is the last time unit (such as a symbol) of the uplink time unit carrying the first report, and the duration of the fourth time period occupied by the second CPU is a preset duration. Since the time for the second CPU to perform metric calculation and PUSCH generation can be a preset duration, the time period occupied by the second CPU is the preset duration before the last time unit carrying the first report, as shown in Figure 18.

[0328] The sixth value mentioned above can be 1 or a preset fixed value, which is the second CPU usage number when performing metric calculation and PUSCH generation.

[0329] Scenario 4: The measurement results and AI execution results required for the first report were not obtained.

[0330] Since the AI ​​execution result required for the first report was not obtained, the processing unit corresponding to the first CPU of the terminal device needs to calculate the AI ​​execution result required for the first report. Specifically, the time period and number of CPUs occupied by the first CPU can be determined according to various methods in scenario 3. Further details are omitted here.

[0331] Since the measurement results required for the first report were not obtained, the processing unit corresponding to the second CPU of the terminal device needs to calculate the measurement results required for the first report. Specifically, the time period and number of second CPU occupancy can be determined according to various methods in scenario 2. Further details are omitted here.

[0332] In the aforementioned communication method, the terminal device uses different CPUs to process the AI ​​execution process and the non-AI execution process.

[0333] This application embodiment also provides a communication method, which differs from the aforementioned communication method in that the terminal device uses the same CPU for processing the AI ​​execution process and the non-AI execution process, but determines the CPU usage number and CPU usage time period for the AI ​​execution process and the non-AI execution process respectively.

[0334] As shown in Figure 22, the communication method may include the following steps:

[0335] Step 201: The first device determines the CPU usage count and CPU usage time period corresponding to the first report according to the second rule.

[0336] Optionally, the CPU usage count may include a first CPU usage count and a second CPU usage count, and the CPU usage time period may include a first CPU usage time period and a second CPU usage time period.

[0337] The aforementioned first CPU utilization is less than or equal to the first maximum CPU utilization, which is the number of CSI calculations corresponding to AI execution processes that the terminal device can support processing simultaneously. The aforementioned second CPU utilization is less than or equal to the second maximum CPU utilization, which is the number of CSI calculations corresponding to non-AI execution processes that the terminal device can support processing simultaneously.

[0338] The first device mentioned above can be a network device or a device within a network device; or, the first device can also be a terminal device or a device within a terminal device.

[0339] Step 202: The first device communicates with the second device based on the CPU usage count and CPU usage time period.

[0340] When the first device is a network device or a device within a network device, the second device may be a terminal device or a device within a terminal device.

[0341] When the first device is a terminal device or a device within a terminal device, the second device can be a network device or a device within a network device.

[0342] In one possible implementation, the second device also determines the CPU usage count and CPU usage time period corresponding to the first report according to the second rule, thereby enabling the first device and the second device to align the CPU usage count and CPU usage time period.

[0343] The first and second devices can transmit the first report based on the CPU usage and CPU usage time period corresponding to the first report. For example, when the network device schedules the terminal device to send back the first report, it reserves computing time for the terminal device based on the CPU usage and CPU usage time period. If the terminal device needs to send back multiple reports on the resource for which the first report is sent, but it is determined based on the CPU usage and CPU usage time that the terminal device cannot send back multiple reports on the corresponding resource in time, then the network device and the terminal device can determine which reports the terminal device will not update based on the priority of each report.

[0344] In one possible implementation, the second rule mentioned above may include a first value for the first CPU occupancy number corresponding to the first report, and the first value corresponds to a first CPU occupancy time period.

[0345] The start time corresponding to the first CPU occupancy period can be the start time of the first measurement resource (i.e., the first time unit of the first measurement resource (such as a symbol, etc.), and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report).

[0346] The termination time corresponding to the CPU occupancy period can be the last time unit (such as a symbol) of the uplink time unit that carries the first report.

[0347] The first value can be the CPU usage of the terminal device in response to the AI ​​report, either reported, indicated, or preset by the terminal device.

[0348] In another possible implementation, the second rule mentioned above may include: the CPU usage number corresponding to the first report includes a first value and a second value, the CPU usage time period corresponding to the first report includes a first time period and a second time period, the first value corresponds to the first time period, and the second value corresponds to the second time period.

[0349] The aforementioned first time period refers to the time period during which the terminal device executes the AI ​​execution process corresponding to the first report.

[0350] The aforementioned first value is either the CPU usage of the terminal device during the AI ​​execution process, as reported, indicated, or preset by the terminal device, or the CPU usage reported, indicated, or preset by the terminal device during the AI ​​execution process.

[0351] The aforementioned second time period refers to the period during which the terminal device executes the non-AI execution process corresponding to the first report.

[0352] The aforementioned second value is the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device; or, it is the CPU usage count reported by the terminal device, indicated by the terminal device, or preset by the terminal device for non-AI execution processes in the AI ​​report.

[0353] Optionally, the aforementioned first report may contain AI monitoring results. Since the first report contains AI monitoring results, and the generation of these results requires both measurement results and AI execution results (i.e., AI inference results), there are four possible scenarios when the terminal device determines that it needs to generate and feed back the first report:

[0354] Scenario 1: The measurement results and AI execution results required for the first report have been obtained.

[0355] Scenario 2: The AI ​​execution results required for the first report have been obtained, but the measurement results required for the first report have not been obtained.

[0356] Scenario 3: The measurement results required for the first report have been obtained, but the AI ​​execution results required for the first report have not been obtained.

[0357] Scenario 4: The measurement results and AI execution results required for the first report were not obtained.

[0358] For situation 1 above, the second rule may include: the CPU usage number corresponding to the first report is a third value, and the third value corresponds to the CPU usage time period.

[0359] The third value is either 1 or a preset fixed value.

[0360] The termination time corresponding to the CPU occupancy period is the last time unit (such as a symbol) of the uplink unit carrying the first report, and the duration of the CPU occupancy period is a preset duration.

[0361] For scenarios 2, 3, and 4, the second rule mentioned above may include: the CPU usage count is a fourth value, and the fourth value corresponds to the CPU usage time period.

[0362] The start time corresponding to the CPU usage period is the start time of the first measurement resource, which is the earliest measurement resource among at least one measurement resource corresponding to the first report.

[0363] The termination time corresponding to the CPU occupancy time is the last time unit (such as a symbol) of the uplink unit carrying the first report.

[0364] The fourth value is the CPU usage of the terminal device as reported, indicated, or preset by the terminal device.

[0365] Regarding scenario 2 above, another possible design is that the second rule includes: the CPU usage count includes a fourth value and a fifth value, the fourth value corresponds to at least one third time period in the CPU usage time period, and the fifth value corresponds to the fourth time period in the CPU usage time period.

[0366] In this context, at least one third time period corresponds one-to-one with at least one target measurement resource, and the at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report. The fourth time period corresponds to the last measurement resource, and the last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report.

[0367] The start time corresponding to each of the at least one third time period is the start time of the corresponding target measurement resource.

[0368] The end time of each of the at least one third time period is the time when the CSI calculation for the corresponding target measurement resource is completed.

[0369] The fourth value is either the CPU usage of the terminal device during the AI ​​execution process, as reported, indicated, or preset by the terminal device, or the CPU usage reported, indicated, or preset by the terminal device during the AI ​​report.

[0370] The start time corresponding to the fourth time period is the start time of the last measurement resource.

[0371] The termination time corresponding to the fourth time period is the last time unit (such as a symbol) of the uplink time unit that carries the first report.

[0372] The fifth value is either the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device, or the CPU usage count reported, indicated, or preset by the terminal device for non-AI execution processes in the AI ​​report.

[0373] Regarding scenario 3 above, another possible design is that the second rule includes: the CPU usage count includes a sixth value and a seventh value, the sixth value corresponds to the fifth time period in the CPU usage time period, and the seventh value corresponds to the sixth time period in the CPU usage time period.

[0374] The start time corresponding to the fifth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result.

[0375] The termination time corresponding to the fifth time period is the time when the AI ​​execution process is completed.

[0376] The sixth value is the CPU usage of the terminal device for the AI ​​execution process, as reported, indicated, or preset by the terminal device; or, it is the CPU usage of the terminal device for the AI ​​report, as reported, indicated, or preset by the terminal device.

[0377] The termination time corresponding to the sixth time period is the last time unit (such as a symbol) of the uplink time unit carrying the first report, and the duration of the sixth time period is a preset duration.

[0378] The seventh value is 1 or a preset fixed value.

[0379] Regarding scenario 4 above, another possible design is that the second rule includes: the CPU usage count includes an eighth value, a ninth value, and a tenth value, the eighth value corresponds to the seventh time period in the CPU usage time period, the ninth value corresponds to the eighth time period in the CPU usage time period, and the tenth value corresponds to the ninth time period in the CPU usage time period.

[0380] The start time corresponding to the seventh time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result.

[0381] The termination time corresponding to the seventh time period is the time when the AI ​​execution process is completed.

[0382] The eighth value is either the CPU usage of the terminal device during the AI ​​execution process, as reported, indicated, or preset by the terminal device, or the CPU usage reported, indicated, or preset by the terminal device for the AI.

[0383] The start time corresponding to the eighth time period is the start time of the first measurement resource, which is the earliest measurement resource among at least one measurement resource corresponding to the first report.

[0384] The termination time corresponding to the eighth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed.

[0385] The ninth value is the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device; or, it is the CPU usage count reported by the terminal device, indicated by the terminal device, or preset by the terminal device for non-AI execution processes in the AI ​​report.

[0386] The termination time corresponding to the ninth time period is the last time unit (such as a symbol) of the uplink time unit carrying the first report, and the duration of the ninth time period is a preset duration.

[0387] The tenth value is 1 or a preset fixed value.

[0388] In the above design, there may be overlap between the seventh and eighth time periods. The CPU usage of the overlapping period can be the sum of the eighth and ninth values.

[0389] This application also provides a communication method that can be applied to use cases for beam management enhancement to improve the accuracy of beam inference.

[0390] During beam training, network devices can indicate training beam set A (training set A) and training beam set B (training set B) to terminal devices, where set B is a subset of set A, meaning the resource identifiers (RS IDs) of set B are a subset of the RS IDs in set A. Terminal devices can perform measurements based on set A and set B, using the measurement results as training data to train an AI model for beam inference. This AI model can be used to infer the results of set A based on the measurement results of set B. Furthermore, it can infer the optimal beam (Top-1 beam) or a relatively good N beams (Top-N beams).

[0391] During beam inference, the network device can indicate the inference beam set B (inference set B) to the terminal device. The terminal device can perform measurements based on inference set B, use the measurement results as input data for the AI ​​model, thereby obtaining the result of inference set A, and select the Top-1 / Top-N beams based on the result of inference set A.

[0392] Beam mapping is the process of mapping a signal to a specified beam direction. By modulating the phase and amplitude of an antenna array, the signal can be focused in a specified direction. However, if the beam mapping corresponding to the training set B used during the training phase is inconsistent with the beam mapping corresponding to the inference set B used during the inference phase, beam inference based on the inference set B may lead to reduced inference accuracy, or even model inference failure.

[0393] To address the aforementioned problems, the communication method provided in this application embodiment, as shown in Figure 23, includes the following steps:

[0394] Step 301: The network device sends a first beam set indication information, which is used to indicate the first beam set.

[0395] The first beam set is the aforementioned training set A, which includes multiple beams and can be used for AI training on terminal devices.

[0396] The first beam set indication information may include the identifiers corresponding to each beam in training set A, such as RS ID. Optionally, the first beam set indication information may also include information such as the angle and codebook corresponding to each beam.

[0397] In addition, network devices can also indicate the associated ID corresponding to the first beam set through the first beam set indication information or other indication information. The associated ID can be used to indicate changes in network-side additional conditions, such as whether one or more of the following information has changed: beam angle, codebook, beam order, beam mapping, etc.

[0398] Step 302: The terminal device determines the second beam set, which is a subset of the first beam set.

[0399] The second beam set, namely training set B mentioned above, can also be used for AI training. For example, the terminal device performs measurements based on training set A and training set B, and performs AI training based on the measurement results of training set A and training set B. This enables the trained AI model to predict the results of inference set A based on the measurement results of inference set B.

[0400] Optionally, the network device can send second beam set indication information to the terminal device. This second beam set indication information indicates a second beam set; the terminal device can then determine the second beam set based on this information. The second beam set indication information can directly indicate the beams included in the second beam set, or it can indicate the mapping relationship between the second beam set and the first beam set, allowing the terminal device to determine the second beam set based on the first beam set and the mapping relationship.

[0401] Alternatively, the network device may not send the second beam set indication information; instead, the terminal device may determine the second beam set itself. For example, the first beam set indicated by the network device (training set A) includes beam 0, beam 1, beam 2, ..., beam 7, beam 8; the terminal device may then determine beam 0, beam 3, and beam 6 as the second beam set (training set B) based on the parameters of the model it is training.

[0402] Step 303: The terminal device performs AI training based on the measurement information corresponding to the first beam set and the measurement information corresponding to the second beam set.

[0403] The terminal device can perform measurements based on a first beam set and a second beam set to obtain measurement information corresponding to the first beam set and the second beam set. Alternatively, the terminal device can perform measurements based on the first beam set to obtain measurement information corresponding to the first beam set; then, based on the measurement information corresponding to the first beam set and the mapping relationship between the second beam set and the first beam set, determine the measurement information corresponding to the second beam set.

[0404] Step 304: The network device sends third beam indication information. The third beam indication information is used to indicate the third beam set. The third beam set is a subset of the first beam set, and the third beam set has the same first feature as the second beam set.

[0405] The third beam set is the aforementioned inference set B, which can be used for AI inference on terminal devices.

[0406] The same first feature can include one or more of the following:

[0407] Case 1: The beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam.

[0408] Furthermore, the beam mapping being the same can include situations where the associated ID corresponding to the third beam set is the same as the associated ID corresponding to the second beam set, in which case the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set.

[0409] Case 2: The beam order of the third beam set is the same as that of the second beam set.

[0410] Furthermore, when the associated ID of the third beam set is the same as the associated ID of the second beam set, the beam order of the third beam set is the same as the beam order of the second beam set.

[0411] Case 3: The network-side additional conditions corresponding to the third beam set are the same as those corresponding to the second beam set.

[0412] Step 305: The terminal device performs measurements based on the third beam set and performs AI inference based on the measurement information corresponding to the third beam set.

[0413] This can be understood as the terminal device obtaining the result of inference set A based on the measurement information of inference set B and the AI ​​model trained in step 303.

[0414] Furthermore, the terminal device can also determine the range corresponding to the fourth beam set (i.e., inference set A), that is, the terminal device performs inference / prediction on the beams in the fourth beam set based on the measurement information of the third beam set. Optionally, the network device can send fourth beam set indication information to the terminal device, and the terminal device can determine the range corresponding to the fourth beam set based on the fourth beam set indication information. The range of the fourth beam set may include an identifier list of the fourth beam set (e.g., SSB ID List, beam ID List, etc.). Alternatively, the terminal device can also determine the range corresponding to the fourth beam set itself according to preset rules.

[0415] Alternatively, the above beam set can be replaced with: measurement resource set, CSI-RS resource set, SSB resource set, etc.

[0416] In one specific embodiment, the RAN sends indication information for training set A and training set B to the UE based on NW additional condition 1, where training set B is a subset of training set A. The UE performs AI training based on the measurement information of the resources corresponding to training set A and training set B to obtain an AI model for beam prediction. The RAN sends indication information for inference set B to the UE based on NW additional condition 1. Since the NW additional conditions corresponding to training set B and inference set B are the same, it means that the beam mapping and beam order corresponding to training set B and inference set B are the same. Therefore, when the RAN sends a reference signal to the UE based on inference set B, the UE can perform beam prediction based on the measurement information corresponding to the reference signal and the trained AI model. If the RAN sends indication information for inference set B to the UE based on NW additional condition 2, since the NW additional conditions corresponding to training set B and inference set B are different, it means that the beam mapping or beam order corresponding to training set B and inference set B may be different. Therefore, when the RAN sends a reference signal to the UE based on inference set B, and the UE performs beam prediction based on the received data, it will be difficult to guarantee the accuracy of the prediction.

[0417] Figure 24 is a schematic diagram of a communication device according to an embodiment of this application. The communication device includes a processing module 2401 for processing data. Optionally, the communication device may further include an interface module 2402 for receiving content from other units or network elements, or sending content from other units or network elements. It should be understood that the processing module 2401 in the embodiments of this application may be implemented by a processor or processor-related circuit components (or, referred to as processing circuitry), and the interface module 2402 may be implemented by a receiver / transmitter or receiver / transmitter-related circuit components.

[0418] For example, the communication device may be a communication device equipment, or it may be a chip or other combination device or component that has the functions of the aforementioned communication device equipment applied in the communication device equipment.

[0419] The communication can be the terminal device or network device shown in the embodiments of Figures 10 to 21. The processing module 2401 is then used to: determine the CPU usage count and CPU usage time period of the channel state information processing unit corresponding to the first report according to a first rule; the CPU usage count includes a first CPU usage count and a second CPU usage count, and the CPU usage time period includes a first CPU usage time period and a second CPU usage time period, the first CPU usage time period corresponding to the first CPU usage count, and the second CPU usage time period corresponding to the second CPU usage count; the first CPU usage count is less than or equal to a first maximum CPU usage count, which is the number of Channel State Information (CSI) calculations corresponding to AI execution processes that can be simultaneously processed as indicated by the UE; the second CPU usage count is less than or equal to a second maximum CPU usage count, which is the number of CSI calculations corresponding to non-AI execution processes that can be simultaneously processed as indicated by the UE.

[0420] In addition, the above modules can also be used to support other processes performed by the network devices or terminal devices in the embodiments shown in Figures 10 to 21.

[0421] The communication can be a terminal device or a network device as shown in the embodiment of Figure 22. The processing module 2401 is then used to: determine the CPU usage count and CPU usage time period of the channel state information processing unit corresponding to the first report according to the second rule.

[0422] In addition, the above modules can also be used to support other processes performed by the network device or terminal device in the embodiment shown in FIG22.

[0423] This communication can be the terminal device shown in the embodiment of Figure 23. The processing module 2401 is then configured to: receive first beam set indication information sent by the network device via the interface module 2402, the first beam set indication information indicating a first beam set; perform measurements based on the first beam set and the second beam set via the interface module 2402, and perform AI training based on the measurement information corresponding to the first beam set and the measurement information corresponding to the third beam set; receive third beam set indication information sent by the network device via the interface module 2402, the third beam set indication information indicating a third beam set, the third beam set being a subset of the first beam set, and the third beam set having the same beam mapping as the first beam set, or the third beam set having the same beam order as the first beam set. The third beam set is identical to the network-side additional conditions corresponding to the first beam set, or the third beam set is identical to the first indication information corresponding to the first beam set, wherein the first indication information is used to indicate the network-side additional conditions; measurements are performed based on the third beam set, and AI inference is performed based on the measurement information corresponding to the third beam set.

[0424] In addition, the above modules can also be used to support other processes executed by the terminal device in the embodiment shown in FIG23.

[0425] This communication can be the network device in the embodiment shown in Figure 23. The processing module 2401 is then used to: send first beam set indication information through interface module 2402, the first beam set indication information indicating a first beam set; send third beam set indication information through interface module 2402, the third beam set indication information indicating a third beam set, the third beam set being a subset of the first beam set, and the third beam set having the same beam mapping as the first beam set, or the third beam set having the same beam order as the first beam set, or the third beam set having the same network-side additional conditions as the first beam set, or the third beam set having the same first indication information as the first beam set, the first indication information indicating the network-side additional conditions.

[0426] In addition, the above modules can also be used to support other processes performed by the network device in the embodiment shown in FIG23.

[0427] Figure 25 is a schematic diagram of another communication device according to an embodiment of this application. The communication device includes a processor 2501, a communication interface 2502, and may further include a memory 2503 and a bus 2504. The processor 2501, communication interface 2502, and memory 2503 can be interconnected via the bus 2504. The bus 2504 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 2504 can be divided into an address bus, a data bus, and a control bus, etc. For ease of illustration, only one line is used in Figure 25, but this does not indicate that there is only one bus or one type of bus.

[0428] Processor 2501 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The processor may further include hardware chips. These hardware chips may be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. Memory 2503 may be volatile memory or non-volatile memory, or may include both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache.

[0429] The processor 2501 is used to implement the data processing operation of the communication device, and the communication interface 2502 is used to implement the receiving and sending operations of the communication device.

[0430] The communication can be the terminal device or network device shown in the embodiments of Figures 10 to 21. The processor 2501 is then configured to: determine the CPU usage count and CPU usage time period of the channel state information processing unit corresponding to the first report according to a first rule; the CPU usage count includes a first CPU usage count and a second CPU usage count, and the CPU usage time period includes a first CPU usage time period and a second CPU usage time period, the first CPU usage time period corresponding to the first CPU usage count, and the second CPU usage time period corresponding to the second CPU usage count; the first CPU usage count is less than or equal to a first maximum CPU usage count, which is the number of Channel State Information (CSI) calculations corresponding to AI execution processes that can be simultaneously processed as indicated by the UE; the second CPU usage count is less than or equal to a second maximum CPU usage count, which is the number of CSI calculations corresponding to non-AI execution processes that can be simultaneously processed as indicated by the UE.

[0431] In addition, the above modules can also be used to support other processes performed by the network devices or terminal devices in the embodiments shown in Figures 10 to 21.

[0432] This communication can be a terminal device or a network device as shown in the embodiment of Figure 22. The processor 2501 is then used to: determine the CPU usage count and CPU usage time period of the channel state information processing unit corresponding to the first report according to the second rule.

[0433] In addition, the above modules can also be used to support other processes performed by the network device or terminal device in the embodiment shown in FIG22.

[0434] This communication can be the terminal device shown in the embodiment of Figure 23. The processor 2501 is then configured to: receive first beam set indication information sent by a network device via communication interface 2502, the first beam set indication information indicating a first beam set; perform measurements based on the first beam set and the second beam set via communication interface 2502, and perform AI training based on the measurement information corresponding to the first beam set and the measurement information corresponding to the third beam set; and receive third beam set indication information sent by the network device via communication interface 2502, the third beam set indicating a third beam set, the third beam set being a subset of the first beam set, and the third beam set having the same beam mapping as the first beam set, or the third beam set having the same beam order as the first beam set. The third beam set is identical to the network-side additional conditions corresponding to the first beam set, or the third beam set is identical to the first indication information corresponding to the first beam set, wherein the first indication information is used to indicate the network-side additional conditions; measurements are performed based on the third beam set, and AI inference is performed based on the measurement information corresponding to the third beam set.

[0435] In addition, the above modules can also be used to support other processes executed by the terminal device in the embodiment shown in FIG23.

[0436] This communication can be a network device as shown in the embodiment of Figure 23. The processor 2501 is then configured to: send a first beam set indication information via communication interface 2502, the first beam set indication information indicating a first beam set; send a third beam set indication information via communication interface 2502, the third beam set indication information indicating a third beam set, the third beam set being a subset of the first beam set, and the third beam set having the same beam mapping as the first beam set, or the third beam set having the same beam order as the first beam set, or the third beam set having the same network-side additional conditions as the first beam set, or the third beam set having the same first indication information as the first beam set, the first indication information indicating the network-side additional conditions.

[0437] In addition, the above modules can also be used to support other processes performed by the network device in the embodiment shown in FIG23.

[0438] Based on the same technical concept, embodiments of this application provide a chip, including: a processor coupled to a memory for storing instructions, wherein when the instructions are executed by the processor, the chip enables the chip to implement the method described in any of the above implementation methods.

[0439] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing computer-readable instructions, which, when executed on a computer, cause the above-described method embodiments to be performed.

[0440] Based on the same technical concept, this application also provides a computer program product containing instructions that, when run on a computer, cause the above-described method embodiments to be executed.

[0441] It should be understood that in the description of this application, terms such as "first" and "second" are used only for distinguishing purposes and should not be construed as indicating or implying relative importance or order. References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in still other embodiments" appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0442] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0443] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0444] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0445] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0446] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0447] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A communication method, characterized in that, The method includes: The CPU usage count and CPU usage time period of the channel state information processing unit corresponding to the first report are determined according to the first rule. The CPU usage count includes a first CPU usage count and a second CPU usage count, and the CPU usage time period includes a first CPU usage time period and a second CPU usage time period. The first CPU usage time period corresponds to the first CPU usage count, and the second CPU usage time period corresponds to the second CPU usage count. The first CPU usage count is less than or equal to the first CPU maximum usage count, where the first CPU maximum usage count is the number of Channel State Information (CSI) calculations corresponding to the AI ​​execution process that the terminal device can support simultaneously processing. The second CPU utilization is less than or equal to the second maximum CPU utilization, which is the number of CSI calculations corresponding to non-AI execution processes that the terminal device can support processing simultaneously, as indicated by the terminal device.

2. The method according to claim 1, characterized in that, The first report contains the results of AI reasoning; The first rule includes: the first CPU usage number corresponding to the first report is a first value, and the first value corresponds to the first CPU usage time period.

3. The method according to claim 2, characterized in that, The start time corresponding to the first CPU occupancy period is at least one of the following times: the time when the CSI calculation of all measurement resources corresponding to the first report is completed, the time when the CSI calculation of the first measurement resource is completed, and the end time of the last measurement resource. The first measurement resource is the earliest measurement resource among at least one measurement resources corresponding to the first report, and the last measurement resource is the latest measurement resource among at least one measurement resources corresponding to the first report; The termination time corresponding to the first CPU occupancy period is at least one of the following: the time when the AI ​​execution process is completed, or the last time unit of the uplink time unit carrying the first report.

4. The method according to claim 2, characterized in that, The first CPU first occupancy period includes at least one first time period, and the at least one first time period corresponds one-to-one with at least one measurement resource corresponding to the first report; The start time corresponding to each of the at least one first time period is at least one of the following times: the time when the CSI calculation of at least one measurement resource corresponding to the first report is completed, and the last time unit of the at least one measurement resource corresponding to the first report; The end time corresponding to each of the at least one first time period is X1 time units after the start time corresponding to the at least one first time period.

5. The method according to claim 4, characterized in that, The X1 time units correspond to the time units corresponding to the AI ​​execution process, or the X1 time units include the time units corresponding to the AI ​​execution process.

6. The method according to claim 2, characterized in that, The start time corresponding to the first CPU occupancy period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the first CPU occupancy period is the last time unit of the uplink time unit carrying the first report.

7. The method according to any one of claims 2-5, characterized in that, The first value is the CPU usage of the terminal device during the AI ​​execution process, as reported, indicated, or preset by the terminal device; or, The first value is the CPU usage of the terminal device in response to the AI ​​report, as reported, indicated, or preset by the terminal device.

8. The method according to any one of claims 1-7, characterized in that, The first rule includes: the second CPU usage number corresponding to the first report is a second value, and the second value corresponds to the first time period of second CPU usage.

9. The method according to claim 8, characterized in that, The start time corresponding to the first time period occupied by the second CPU is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the first occupied time period of the second CPU is the last time unit of the uplink time unit that carries the first report.

10. The method according to claim 8, characterized in that, The second CPU's first occupancy period includes a second period and a third period; The start time corresponding to the second time period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the second time period is the time when the CSI calculation of the last measurement resource is completed, or the time when the processing unit corresponding to the second CPU sends the CSI calculation result of the last measurement resource to the processing unit corresponding to the first CPU. The last measurement resource is the latest measurement resource among at least one measurement resource corresponding to the first report. The start time corresponding to the third time period is the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed. The termination time corresponding to the third time period is the last time unit of the uplink time unit that carries the first report.

11. The method according to claim 8, characterized in that, The first CPU occupancy period includes at least one second period and one third period. The at least one second period corresponds one-to-one with at least one target measurement resource corresponding to the first report. The at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report. The third period corresponds to the last measurement resource. The last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report. The start time corresponding to each of the at least one second time period is the first time unit of the corresponding target measurement resource. The termination time corresponding to each of the at least one second time period is the time when the CSI calculation of the corresponding target measurement resource is completed; The start time corresponding to the third time period is the first time unit of the last measurement resource; The termination time corresponding to the third time period is the last time unit of the uplink time unit that carries the first report.

12. The method according to claim 8, characterized in that, The second CPU first occupancy period includes at least one second period and one third period, wherein the at least one second period corresponds one-to-one with at least one measurement resource corresponding to the first report; The start time corresponding to each of the at least one second time period is the first time unit of the corresponding measurement resource. The termination time corresponding to each of the at least one second time period is the time when the CSI calculation of the corresponding measurement resource is completed; The start time corresponding to the third time period is the time when the processing unit corresponding to the second CPU receives the AI ​​execution result sent by the processing unit corresponding to the first CPU, or the time when the AI ​​execution process is completed. The termination time corresponding to the third time period is the last time unit of the uplink time unit that carries the first report.

13. The method according to any one of claims 8-12, characterized in that, The second value is the CPU usage count reported by the terminal device or measured by a preset reference signal of the terminal device; or, The second value is the CPU usage of the terminal device for non-AI execution processes in the AI ​​report, as reported, indicated, or preset by the terminal device.

14. The method according to any one of claims 1-13, characterized in that, The first report contains the results of AI monitoring; When the terminal device does not obtain the AI ​​execution result required by the first report, the first rule includes: the first CPU usage number corresponding to the first report is a third value, and the third value corresponds to the second CPU usage time period; The start time corresponding to the second CPU occupancy period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result. The termination time corresponding to the second CPU occupancy period is the time when the AI ​​execution process is completed; The third value is either the CPU usage of the terminal device during the AI ​​execution process, as reported, indicated, or preset by the terminal device, or the CPU usage reported, indicated, or preset by the terminal device during the AI ​​report.

15. The method according to any one of claims 1-14, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution result required by the first report, the first rule includes: the first CPU usage corresponding to the first report is 0, and / or the first report does not occupy the first CPU.

16. The method according to any one of claims 1-15, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the measurement results and AI execution results required for the first report, the first rule includes: the second CPU usage number corresponding to the first report is a fourth value, and the fourth value corresponds to the second CPU usage time period; The fourth value is 1 or a preset fixed value; and / or The termination time corresponding to the second CPU second occupancy period is the last time unit of the uplink time unit carrying the first report, and the duration of the second CPU second occupancy period is a preset duration.

17. The method according to any one of claims 1-16, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution result required for the first report but has not obtained the measurement result required for the first report, the first rule includes: the second CPU usage number corresponding to the first report is a fifth value, and the fifth value corresponds to the third usage time period of the second CPU; The start time corresponding to the third time period of the second CPU occupancy is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the third CPU occupancy period is the time when the first report was generated. The fifth value is the CPU usage of the terminal device corresponding to the non-AI execution process in the AI ​​report, as reported, indicated, or preset by the terminal device.

18. The method according to any one of claims 1-16, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution result required for the first report but has not obtained the measurement result required for the first report, the first rule includes: the second CPU usage number corresponding to the first report is a fifth value, and the fifth value corresponds to the third usage time period of the second CPU; The second CPU third occupancy time period includes at least one fourth time period and one fifth time period. The at least one fourth time period corresponds one-to-one with at least one target measurement resource. The at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report. The fifth time period corresponds to the last measurement resource. The last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report. The start time corresponding to each of the at least one fourth time period is the first time unit of the corresponding target measurement resource. The termination time corresponding to each of the at least one fourth time period is the time when the CSI calculation of the corresponding target measurement resource is completed; The starting time corresponding to the fifth time period is the first time unit of the last measurement resource; The termination time corresponding to the fifth time period is the last time unit of the uplink time unit that carries the first report; The fifth value is the CPU usage of the terminal device corresponding to the non-AI execution process in the AI ​​report, as reported, indicated, or preset by the terminal device.

19. The method according to any one of claims 1-18, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the measurement results required for the first report but has not obtained the AI ​​execution results required for the first report, the first rule includes: the second CPU usage number corresponding to the first report is the sixth value, and the sixth value corresponds to the fourth usage time period of the second CPU; The end time of the fourth CPU occupancy period is the last time unit of the uplink time unit carrying the first report, and the duration of the fourth CPU occupancy period is a preset duration; and / or The sixth value is 1 or a preset fixed value.

20. A communication method, characterized in that, The terminal device includes at least one channel state information processing unit (CPU), each CPU being used to execute AI execution processes and non-AI execution processes, the method comprising: The CPU usage and CPU usage time period corresponding to the first report are determined according to the second rule.

21. The method according to claim 20, characterized in that, The second rule includes: the CPU usage number corresponding to the first report is a first value, and the first value corresponds to a first CPU usage time period; The start time corresponding to the first CPU occupancy time period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the CPU occupancy period is the last time unit of the uplink time unit that carries the first report; The first value is the CPU usage of the terminal device in response to the AI ​​report, as reported, indicated, or preset by the terminal device.

22. The method according to claim 20, characterized in that, The second rule includes: the CPU usage corresponding to the first report includes a first value and a second value; the CPU usage time period corresponding to the first report includes a first time period and a second time period; the first value corresponds to the first time period; and the second value corresponds to the second time period. The first value is the CPU usage of the terminal device for the AI ​​execution process, as reported, indicated, or preset by the terminal device; or, it is the CPU usage of the terminal device for the AI ​​report, indicated, or preset by the terminal device. The second value is the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device; or, it is the CPU usage count reported by the terminal device, indicated by the terminal device, or preset by the terminal device for non-AI execution processes in the AI ​​report. The first time period is the period during which the terminal device executes the AI ​​execution process corresponding to the first report; The second time period is the period during which the terminal device executes the non-AI execution process corresponding to the first report.

23. The method according to any one of claims 20-22, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution results and measurement results required for the first report, the second rule includes: the CPU usage number corresponding to the first report is a third value, and the third value corresponds to the CPU usage time period; The third value is 1 or a preset fixed value; The termination time corresponding to the CPU occupancy period is the last time unit of the uplink unit carrying the first report, and the duration of the CPU occupancy period is a preset duration.

24. The method according to any one of claims 20-23, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution result required for the first report but has not obtained the measurement result required for the first report, or when it has obtained the measurement result required for the first report but has not obtained the AI ​​execution result required for the first report, or when it has not obtained both the measurement result and the AI ​​execution result required for the first report, the second rule includes: the CPU usage count is a fourth value, and the fourth value corresponds to the CPU usage time period; The start time corresponding to the CPU occupancy period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the CPU occupancy time is the last time unit of the uplink unit carrying the first report; The fourth value is the CPU usage of the terminal device as reported, indicated, or preset by the terminal device.

25. The method according to any one of claims 20-23, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the AI ​​execution result required for the first report but has not obtained the measurement result required for the first report, the second rule includes: the CPU usage count includes a fourth value and a fifth value, the fourth value corresponds to at least one third time period in the CPU usage time period, and the fifth value corresponds to the fourth time period in the CPU usage time period; The at least one third time period corresponds one-to-one with at least one target measurement resource. The at least one target measurement resource is the measurement resource other than the latest measurement resource among the multiple measurement resources corresponding to the first report. The fourth time period corresponds to the last measurement resource. The last measurement resource is the latest measurement resource among the multiple measurement resources corresponding to the first report. The start time corresponding to each of the at least one third time period is the first time unit of the corresponding target measurement resource; The end time of each of the at least one third time period is the time when the CSI calculation of the corresponding target measurement resource is completed; The start time corresponding to the fourth time period is the first time unit of the last measurement resource; The termination time corresponding to the fourth time period is the last time unit of the uplink time unit that carries the first report; The fourth value is the CPU usage of the terminal device for the AI ​​execution process, as reported, indicated, or preset by the terminal device; or, it is the CPU usage of the terminal device for the AI ​​report, indicated, or preset by the terminal device. The fifth value is either the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device, or the CPU usage count reported, indicated, or preset by the terminal device for non-AI execution processes in the AI ​​report.

26. The method according to any one of claims 20-23 or 25, characterized in that, The first report contains the results of AI monitoring; When the terminal device has obtained the measurement results required for the first report but has not obtained the AI ​​execution results required for the first report, the second rule includes: the CPU usage count includes a sixth value and a seventh value, the sixth value corresponds to the fifth time period in the CPU usage time period, and the seventh value corresponds to the sixth time period in the CPU usage time period; The start time corresponding to the fifth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result. The termination time corresponding to the fifth time period is the time when the AI ​​execution process is completed; The sixth value is the CPU usage of the terminal device for the AI ​​execution process, as reported, indicated, or preset by the terminal device; or, it is the CPU usage of the terminal device for the AI ​​report, as reported, indicated, or preset by the terminal device. The termination time corresponding to the sixth time period is the last time unit of the uplink time unit that carries the first report, and the duration of the sixth time period is a preset duration. The seventh value is 1 or a preset fixed value.

27. The method according to any one of claims 20-23 and 25-26, characterized in that, The first report contains the results of AI monitoring; When the terminal device fails to obtain the measurement results required for the first report and the AI ​​execution results required for the first report, the second rule includes: the CPU usage count includes an eighth value, a ninth value, and a tenth value, the eighth value corresponds to the seventh time period in the CPU usage time period, the ninth value corresponds to the eighth time period in the CPU usage time period, and the tenth value corresponds to the ninth time period in the CPU usage time period; The start time corresponding to the seventh time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed, or the end time of the last measurement resource corresponding to the AI ​​execution result. The termination time corresponding to the seventh time period is the time when the AI ​​execution process is completed; The eighth value is the CPU usage of the terminal device for the AI ​​execution process, which is reported, indicated, or preset by the terminal device; or, it is the CPU usage of the terminal device for the AI ​​report, which is reported, indicated, or preset by the terminal device. The start time corresponding to the eighth time period is the first time unit of the first measurement resource, and the first measurement resource is the earliest measurement resource among at least one measurement resource corresponding to the first report; The termination time corresponding to the eighth time period is the time when the CSI calculation of all measurement resources corresponding to the AI ​​execution result is completed; The ninth value is the CPU usage count reported by the terminal device or measured by a reference signal preset by the terminal device; or, it is the CPU usage count reported by the terminal device, indicated by the terminal device, or preset by the terminal device for non-AI execution processes in the AI ​​report. The termination time corresponding to the ninth time period is the last time unit of the uplink time unit that carries the first report, and the duration of the ninth time period is a preset duration. The tenth value is 1 or a preset fixed value.

28. The method according to claim 27, characterized in that, If the seventh time period and the eighth time period overlap, the CPU usage of the overlapping portion is the sum of the eighth value and the ninth value.

29. A communication method, characterized in that, The method includes: Receive first beam set indication information sent by a wireless access network device, wherein the first beam set indication information is used to indicate the first beam set; Determine a second beam set, which is a subset of the first beam set; Measurements are performed based on the first beam set and the second beam set to obtain measurement information corresponding to the first beam set and the second beam set; or, measurements are performed based on the first beam set to obtain measurement information corresponding to the first beam set, and measurement information corresponding to the second beam set is determined based on the measurement information corresponding to the first beam set and the mapping relationship between the second beam set and the first beam set. Training is performed based on the measurement information corresponding to the first beam set and the measurement information corresponding to the second beam set; Receive third beam set indication information, the third beam set indication information is used to indicate a third beam set, the third beam set has the same first feature as the second beam set; Measurements are performed based on the third beam, and inferences are made based on the measurement information corresponding to the third beam set.

30. The method according to claim 29, characterized in that, The method further includes: Determine the range corresponding to the fourth beam set; or, receive the fourth beam set indication information sent by the wireless access network device, the fourth beam set indication information being used to indicate the range of the fourth beam set; The reasoning based on the measurement information corresponding to the third beam set includes: Inference is made based on the measurement information corresponding to the third beam set and the range of the fourth beam set.

31. The method according to claim 30, characterized in that, The scope of the fourth beam set is the list of identifiers for the fourth beam set.

32. The method according to any one of claims 29-31, characterized in that, The first feature is the same, including the beam mapping corresponding to the third beam set being the same as the beam mapping corresponding to the second beam, or the beam order corresponding to the third beam set being the same as the beam order corresponding to the second beam, or the network-side additional conditions corresponding to the third beam set being the same as the network-side additional conditions corresponding to the second beam.

33. The method according to claim 32, characterized in that, The beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set, including: when the association identifier corresponding to the third beam set is the same as the association identifier corresponding to the second beam set, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set.

34. The method according to claim 32 or 33, characterized in that, The beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set, including: when the association identifier corresponding to the third beam set is the same as the association identifier corresponding to the second beam set, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set.

35. The method according to any one of claims 29-34, characterized in that, The determination of the second beam set includes: The system receives a second beam set indication information sent by a wireless access network device, the second beam set indication information being used to indicate a second beam set; or, the system determines the second beam set according to a first beam set and a preset rule.

36. A communication method, characterized in that, The method includes: Send first beam set indication information to the terminal device, wherein the first beam set indication information is used to indicate the first beam set; Send third beam set indication information to the terminal device, wherein the third beam set indication information is used to indicate the third beam set; The second beam set is a subset of the first beam set, and the third beam set has the same first feature as the second beam set. The first beam set and the second beam set are used for training, and the third beam set is used for inference.

37. The method according to claim 36, characterized in that, The method further includes: Send fourth beam set indication information to the terminal device, the fourth beam set indication information being used to indicate the range of the fourth beam set.

38. The method according to claim 37, characterized in that, The scope of the fourth beam set is the list of identifiers for the fourth beam set.

39. The method according to any one of claims 36-38, characterized in that, The first feature is the same, including the beam mapping corresponding to the third beam set being the same as the beam mapping corresponding to the second beam, or the beam order corresponding to the third beam set being the same as the beam order corresponding to the second beam, or the network-side additional conditions corresponding to the third beam set being the same as the network-side additional conditions corresponding to the second beam.

40. The method according to claim 39, characterized in that, The beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set, including: when the association identifier corresponding to the third beam set is the same as the association identifier corresponding to the second beam set, the beam mapping corresponding to the third beam set is the same as the beam mapping corresponding to the second beam set.

41. The method according to claim 39 or 40, characterized in that, The beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set, including: when the association identifier corresponding to the third beam set is the same as the association identifier corresponding to the second beam set, the beam order corresponding to the third beam set is the same as the beam order corresponding to the second beam set.

42. The method according to any one of claims 36-41, characterized in that, The method further includes: Send a second beam set indication information to the terminal device, the second beam set indication information being used to indicate the second beam set.

43. A communication device, characterized in that, include: A processor coupled to a memory for storing programs or instructions that, when executed by the processor, cause the apparatus to perform the method as described in any one of claims 1-42.

44. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-42.

45. A communication device, characterized in that, Includes modules or means for implementing the method as described in any one of claims 1-42.

46. ​​A communication system, characterized in that, It includes one or more of the following: means for implementing the method as described in any one of claims 1-19, means for implementing the method as described in any one of claims 20-28, means for implementing the method as described in any one of claims 29-35, or means for implementing the method as described in any one of claims 36-42.

Images