Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus. The method comprises: on the basis of a first duration, determining one or more of the following: an interval between an end time of a first downlink channel and a transmission start time of a first CSI report, an interval between a first reference signal transmission occasion and the transmission start time of the first CSI report, and a CSI reference resource corresponding to the first CSI report, wherein the first duration corresponds to an execution duration of a first task, the first task comprises an AI-based first prediction task and an AI-based first compression task, input data of the first compression task is determined on the basis of output data of the first prediction task, and the first CSI report, the first downlink channel and the first reference signal transmission occasion correspond to the first task. On the basis of the present application, it is beneficial for a network device to acquire accurate CSI reports.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202510285379.3, filed on March 10, 2025, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication, and more particularly to a communication method and a communication device. Background Technology

[0003] Currently, artificial intelligence (AI) has been introduced into wireless communication networks and has been widely applied in many application scenarios of air interface technology, such as AI-based channel state information (CSI) prediction, AI-based beam management, and AI-based CSI feedback, playing an increasingly important role.

[0004] Therefore, it is necessary to focus on the issue of how to obtain accurate CSI based on AI. Summary of the Invention

[0005] This application provides a communication method and a communication device that, in scenarios where channel state information reference signal (CSI-RS) feedback enhancement is based on AI, enables terminal devices and network devices to align the CSI processing unit (CPU) occupancy mode corresponding to AI-related CSI reports. This helps network devices determine whether any CSI report reported at a specific time has not been updated due to insufficient CPU resources, thereby helping network devices obtain accurate CSI reports.

[0006] In a first aspect, a communication method is provided, the method comprising: determining one or more of the following based on a first duration: a first CSI duration, a second CSI duration, and a CSI reference resource corresponding to a first CSI report; the first CSI duration corresponds to the interval between the end time of a first downlink channel and the start time of transmission of a first CSI report, the second CSI duration corresponds to the interval between the transmission timing of a first reference signal and the transmission start time of a first CSI report; the first duration corresponds to the execution duration of a first task, the first task including an AI-based first prediction task and an AI-based first compression task, the input data of the first compression task being determined based on the output data of the first prediction task, and the first CSI report, the first downlink channel, and the transmission timing of the first reference signal corresponding to the first task.

[0007] The method can be executed by a first device, which can be replaced by a device on the terminal device side, a device on the network device side, or a device on the core network element side.

[0008] The equipment on the terminal device side can include the terminal device itself, the communication module within the terminal device, or the circuits or chips within the 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, etc.). Alternatively, the equipment on the terminal device side can include AI entities on the terminal device side. AI entities on the terminal device side can be the terminal device itself, or AI entities serving the terminal device, such as servers, such as over-the-top (OTT) servers or cloud servers.

[0009] Network-side devices can include the network device itself, communication modules within the network device, or circuits or chips responsible for communication functions within the network device (such as modem chips, also known as baseband chips, or system-on-a-chip (SoC) chips or SIP chips containing modem cores, etc.). Alternatively, network-side devices can include AI entities on the network device side. These AI entities can be the network device itself or AI entities serving the network device, such as radio access network (RAN) intelligent controllers (RICs), operation administration and maintenance (OAM) systems, or servers, such as OTT servers or cloud servers.

[0010] The equipment on the core network element side can include the core network element itself, functional modules within the core network element, or circuits or chips within the core network element. Alternatively, the equipment on the core network element side can include AI entities on the core network element side. These AI entities can be the core network element itself or AI entities serving the core network element, such as servers, like OTT servers or cloud servers.

[0011] Based on the above technical solution, by defining one or more of the first CSI duration, second CSI duration, and CSI reference resources as related to the first duration, it is beneficial for terminal devices and network devices to determine the same first CSI duration, second CSI duration, or CSI reference resources. This facilitates the alignment of the CPU time periods occupied by the first CSI report between the terminal devices and network devices. When the CPU time periods occupied by the first CSI report are aligned between the terminal devices and network devices, it is beneficial for the network devices to determine, based on the CPU usage of the terminal devices at various times, whether any CSI reports submitted by the terminal devices at a specific time have not been updated due to insufficient CPU resources. In other words, it helps the network devices obtain accurate CSI reports.

[0012] For example, the transmission start time of the first CSI report can be replaced by the uplink transmission unit of the first CSI report, the start time of the uplink transmission unit (or uplink channel) of the first CSI report, or the first symbol of the uplink transmission unit of the first CSI report, or the first symbol of the uplink transmission unit used to carry the first CSI report.

[0013] For example, the first reference signal transmission occasion can correspond to the latest reference signal transmission occasion within the observation window corresponding to the first task, or it can be the latest time-domain unit (such as a time slot or symbol) within the latest reference signal transmission occasion within the observation window corresponding to the first task. The reference signal transmission occasion can correspond to the transmission time / opportunity of the reference signal, or the start time of reference signal transmission, or the reception time / opportunity of the reference signal, or the end time of reference signal transmission. The reference signal transmission occasion can be a CSI-RS transmission occasion.

[0014] For example, the end time of the first downlink channel can be replaced with the last symbol of the first downlink channel. The first downlink channel is used to trigger the first CSI report.

[0015] For example, the first task can be replaced by: the network instructing / requesting the terminal device to send a first CSI report carrying data related to the first task. In other words, the first CSI report is used to carry data related to the first task. For example, the first CSI report can carry inference information related to the first task, such as compressed predicted CSI obtained by compressing the predicted CSI. As another example, the first CSI report can carry monitoring information related to the first task, such as one or more of the following: monitoring information related to the first prediction task (such as the square generalized cosine similarity (SGCS) or normalized mean square error (NMSE) corresponding to the predicted CSI, the measured CSI corresponding to the prediction window, the measured CSI corresponding to the observation window), and monitoring information related to the first compression task (such as the predicted CSI, the SGCS or NMSE corresponding to the compressed predicted CSI (obtained by compressing the predicted CSI). For example, the first CSI report may carry training information related to the first task, such as one or more of the following: training information related to the first prediction task (such as the measured CSI corresponding to the prediction window, the measured CSI corresponding to the observation window), and training information related to the first compression task (such as the predicted CSI or the measured CSI, the compressed predicted CSI, and the gradient of the compressed predicted CSI).

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the first CSI duration is determined based on the first duration, including: determining the first CSI duration based on the first duration and the duration of the first observation window corresponding to the first task.

[0017] For example, the duration of the first CSI is not less than the sum of the first duration, the duration of the first observation window, and the second duration predefined by the protocol.

[0018] For example, the duration of the first observation window corresponds to the duration of the K observation resources included in the first observation window. The value of K is configured by the network and / or indicated by the capabilities of the terminal device.

[0019] The second duration is either the minimum time interval #1 or the minimum time interval #2 between the downlink channel used to trigger the CSI report and the CSI reporting time slot. Minimum time interval #1 corresponds to the non-AI mode, and minimum time interval #2 corresponds to the AI ​​mode. The non-AI mode means that AI is not used during the CSI reporting process, while the AI ​​mode means that AI is used during the CSI reporting process.

[0020] For example, the second CSI duration is not less than the sum of the first duration and the third duration predefined by the protocol.

[0021] The third duration is the minimum time interval #3 or minimum time interval #4 between the CSI-RS used for CSI reporting and the CSI reporting time slot. Minimum time interval #3 corresponds to the non-AI mode, and minimum time interval #4 corresponds to the AI ​​mode.

[0022] For example, the interval between the CSI reference resource and the transmission start time of the first CSI report is greater than or equal to the minimum of the fourth duration, which is the sum of the first duration and the fifth duration predefined by the protocol.

[0023] The fifth duration is the minimum time interval #5 or minimum time interval #6 between the CSI reference resource and the CSI reporting time slot. Minimum time interval #5 corresponds to the non-AI mode, and minimum time interval #6 corresponds to the AI ​​mode.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the first duration is a predefined value; or, the first duration is related to a first value of at least one first inference parameter and / or a second value of at least one second inference parameter, wherein the first value of at least one first inference parameter is used for a first prediction task and the second value of at least one second inference parameter is used for a first compression task.

[0025] Based on the above technical solution, if the first duration is a predefined value, it helps reduce the processing complexity of the first device. If the first duration is related to the value of the inference parameters, it helps the first device determine a first duration that is closer to the execution duration of the first task based on the value of the inference parameters, thereby improving the transmission efficiency of the communication system and / or reducing resource consumption. For example, if the first device determines a first duration that is closer to the execution duration of the first task, it helps the first device determine a more accurate CPU usage method for the first CSI report based on one or more of the first CSI duration, the second CSI duration, or CSI reference resources, thereby avoiding resource waste caused by reserving a longer CPU time for the first CSI report.

[0026] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset identifier, association identifier, or function identifier.

[0027] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, the first duration is greater than or equal to the sum of the sixth duration and the seventh duration, the sixth duration corresponds to the execution duration of the first prediction task, and the seventh duration corresponds to the execution duration of the first compression task.

[0029] For example, the sixth duration is a predefined value; or, the sixth duration is associated with a first value of at least one first inference parameter, the first value of which is used for the first prediction task.

[0030] For example, the seventh duration is a predefined value; or, the seventh duration is associated with a second value of at least one second inference parameter, the second value of which is used for the first compression task.

[0031] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a count value of CPU occupied by the first CSI report based on one or more of the following: a first quantity, a second quantity, a first value of at least one first inference parameter, and a second value of at least one second inference parameter; wherein the first quantity is the number of CPUs required to execute the first prediction task, the second quantity is the number of CPUs required to execute the first compression task, the first value of at least one first inference parameter is used for the first prediction task, and the second value of at least one second inference parameter is used for the first compression task.

[0032] Based on the above technical solution, defining the method for determining the CPU usage count of the first CSI report facilitates the alignment of the CPU usage count of the first CSI report between the terminal device and the network device. When the terminal device and the network device align the CPU usage count of the first CSI report, the network device can determine whether any CSI reports submitted by the terminal device at a specific time were not updated due to insufficient CPU resources, based on the CPU usage of the terminal device at various times. In other words, it helps the network device obtain accurate CSI reports.

[0033] For example, the first quantity is a predefined value; or, the first quantity is associated with a first value of at least one first inference parameter.

[0034] For example, the second quantity is a predefined value; or, the second quantity is associated with a second value of at least one second inference parameter.

[0035] In conjunction with the first aspect, in certain implementations of the first aspect, during the time period in which the first CSI report occupies the CPU, the count value of the CPU occupied by the first CSI report is: the maximum value between a first quantity and a second quantity; or, a weighted sum of the first quantity and the second quantity; or, a count value determined based on a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0036] Based on the above technical solution, the first device can determine a more accurate count of CPU usage for the first CSI report through different methods, thereby avoiding the terminal device being unable to report the first CSI report due to insufficient CPU usage for the first CSI report, or avoiding the waste of resources caused by allocating too many CPUs to the first CSI report.

[0037] For example, the start time of the CPU-occupied time period of the first CSI report is no later than the start time of the second reference signal transmission timing. The second reference signal transmission timing may correspond to the earliest reference signal transmission timing within the observation window corresponding to the first task, or it may be the earliest time-domain unit (such as a time slot or symbol) within the earliest reference signal transmission timing within the observation window corresponding to the first task. Further description of the reference signal transmission timing can be found above.

[0038] In conjunction with the first aspect, in some implementations of the first aspect, the count value of CPU usage by the first CSI report is a weighted sum of a first quantity and a second quantity. The method further includes: sending or receiving first indication information, the first indication information being used to indicate a first weighting coefficient corresponding to the first quantity and / or a second weighting coefficient corresponding to the second quantity, the first weighting coefficient and the second weighting coefficient being used to determine the count value of CPU usage by the first CSI report.

[0039] In conjunction with the first aspect, in some implementations of the first aspect, from the start of the time period during which the first CSI report occupies the CPU to the first time period, the count value of the first CSI report occupying the CPU is a first quantity; from the first time period to the end of the time period during which the first CSI report occupies the CPU, the count value of the first CSI report occupying the CPU is a second quantity.

[0040] Based on the above technical solution, when the first task includes a first prediction task and a first compression task, determining the CPU usage count of the first CSI report in different time periods during the time period it occupies CPU is beneficial for rationally configuring CPU usage, thereby facilitating full CPU utilization and avoiding CPU waste. For example, if the first count is greater than the second count, and the CPU usage count of the first CSI report remains at the first count throughout the entire time period during which the first CSI report occupies CPU, then during the time period of executing the first compression task included in the first task, there may be a problem of excessive CPU usage by the first CSI report, leading to resource waste.

[0041] For example, the first moment is a predefined moment; or, the first moment is before the CSI reference resource, and the interval between the first moment and the CSI reference resource is an eighth duration; or, the first moment is after the first reference signal transmission timing, and the interval between the first reference signal transmission timing and the first moment is related to the execution duration of the first prediction task.

[0042] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: sending or receiving second indication information, the second indication information indicating the first moment.

[0043] In conjunction with the first aspect, in some implementations of the first aspect, the first device is a terminal device, and the method further includes: receiving first information, the first information including at least one third value of each of at least one first inference parameter, and / or including at least one fourth value of each of at least one second inference parameter; the first inference parameters are used for a prediction task, and the second inference parameters are used for a compression task; sending second information, the second information including at least one set of inference parameters, each of the at least one set of inference parameters including at least one first inference parameter and at least one second inference parameter, a fifth value of the first inference parameter included in each of the at least one set of inference parameters belonging to at least one third value, and / or a sixth value of the second inference parameter included belonging to at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; receiving third information, the third information including a first set of inference parameters, the first set of inference parameters belonging to at least one set of inference parameters, the first set of inference parameters being used for the first task.

[0044] Based on the above technical solution, the terminal device can combine the values ​​of the inference parameters configured by the network device for the prediction task and the values ​​of the inference parameters configured for the compression task to obtain at least one set of inference parameters for the second task, and send at least one set of inference parameters to the network device. This allows the network device to accurately issue inference parameter configurations that meet the model deployment requirements of the terminal device based on at least one set of inference parameters reported by the terminal device, without having to send too many combinations of inference parameter values ​​to the terminal device, thus saving signaling overhead.

[0045] Furthermore, when the set of inference parameters for the second task is determined by the terminal device, the terminal device can combine the values ​​of the inference parameters configured by the network device for the prediction task and the inference parameters for the compression task according to the maximum value of the inference parameters for the second task supported by the terminal device, thereby avoiding the network device configuring inference parameter values ​​for the terminal device that exceed the terminal device's capabilities.

[0046] In conjunction with the first aspect, in some implementations of the first aspect, before receiving the first information, the method further includes: receiving fourth information, the fourth information being used to request the value of a first inference parameter supported by the first device, and / or, to request the value of a second inference parameter supported by the first device; and sending fifth information, the fifth information including the value of the first inference parameter supported by the first device, and / or including the value of the second inference parameter supported by the first device.

[0047] In a second aspect, a communication method is provided, the method comprising: determining a count value of CPU usage of a first CSI report based on one or more of the following: a first quantity, a second quantity, a first value of at least one first inference parameter, and a second value of at least one second inference parameter; wherein the first quantity is the number of CPUs required to execute a first prediction task, the second quantity is the number of CPUs required to execute a first compression task, the first value of at least one first inference parameter is used for the first prediction task, and the second value of at least one second inference parameter is used for the first compression task.

[0048] The first CSI report corresponds to the first task, which includes an AI-based first prediction task and an AI-based first compression task. The input data for the first compression task is determined based on the output data of the first prediction task.

[0049] This method can be performed by a first device, and further description of the first device can be found in the first aspect above.

[0050] Based on the above technical solution, defining the method for determining the CPU usage count of the first CSI report facilitates the alignment of the CPU usage count of the first CSI report between the terminal device and the network device. When the terminal device and the network device align the CPU usage count of the first CSI report, the network device can determine whether any CSI reports submitted by the terminal device at a specific time were not updated due to insufficient CPU resources, based on the CPU usage of the terminal device at various times. In other words, it helps the network device obtain accurate CSI reports.

[0051] For example, the first quantity is a predefined value; or, the first quantity is associated with a first value of at least one first inference parameter.

[0052] For example, the second quantity is a predefined value; or, the second quantity is associated with a second value of at least one second inference parameter.

[0053] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset identifier, association identifier, or function identifier.

[0054] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0055] In conjunction with the second aspect, in some implementations of the second aspect, during the time period in which the first CSI report occupies the CPU, the count value of the CPU occupied by the first CSI report is: the maximum value between a first quantity and a second quantity; or, a weighted sum of the first quantity and the second quantity; or, a count value determined based on a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0056] Based on the above technical solution, the first device can determine a more accurate count of CPU usage for the first CSI report through different methods, thereby avoiding the terminal device being unable to report the first CSI report due to insufficient CPU usage for the first CSI report, or avoiding the waste of resources caused by allocating too many CPUs to the first CSI report.

[0057] For example, the start time of the CPU-occupied time period of the first CSI report is no later than the start time of the second reference signal transmission timing. The second reference signal transmission timing may correspond to the earliest reference signal transmission timing within the observation window corresponding to the first task, or it may be the earliest time-domain unit (such as a time slot or symbol) among the earliest reference signal transmission timings within the observation window corresponding to the first task. Further description of the reference signal transmission timing can be found in the first aspect above.

[0058] In conjunction with the second aspect, in some implementations of the second aspect, the count value of the CPU occupied by the first CSI report is a weighted sum of a first quantity and a second quantity. The method further includes: sending or receiving first indication information, the first indication information being used to indicate a first weighting coefficient corresponding to the first quantity and / or a second weighting coefficient corresponding to the second quantity, the first weighting coefficient and the second weighting coefficient being used to determine the count value of the CPU occupied by the first CSI report.

[0059] In conjunction with the second aspect, in some implementations of the second aspect, from the start of the time period during which the first CSI report occupies the CPU to the first time period, the count value of the first CSI report occupying the CPU is a first quantity; from the first time period to the end of the time period during which the first CSI report occupies the CPU, the count value of the first CSI report occupying the CPU is a second quantity.

[0060] Based on the above technical solution, when the first task includes a first prediction task and a first compression task, by determining the CPU usage count of the first CSI report in different time periods during which the CPU is occupied by the first CSI report, it is beneficial to rationally configure the CPU usage, thereby making full use of the CPU and avoiding CPU waste.

[0061] For example, the first moment is a predefined moment; or, the first moment is before the CSI reference resource, and the interval between the first moment and the CSI reference resource is an eighth duration; or, the first moment is after the first reference signal transmission timing, and the interval between the first reference signal transmission timing and the first moment is related to the execution duration of the first prediction task.

[0062] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending or receiving second indication information, the second indication information indicating the first moment.

[0063] Thirdly, a communication method is provided, comprising: determining one or more of the following based on a sixth duration: a third CSI duration, a fourth CSI duration, and a CSI reference resource corresponding to a second CSI report; the third CSI duration corresponds to the interval between the end time of the second downlink channel and the start time of the transmission of the second CSI report, the fourth CSI duration corresponds to the interval between the transmission timing of the third reference signal and the transmission start time of the second CSI report; the sixth duration corresponds to the execution duration of an AI-based first prediction task, and the second CSI report, the second downlink channel, and the transmission timing of the third reference signal correspond to the first prediction task.

[0064] This method can be performed by a first device, and further description of the first device can be found in the first aspect above.

[0065] Based on the above technical solution, by defining one or more of the third CSI duration, fourth CSI duration, and CSI reference resources as related to the sixth duration, it is beneficial for terminal devices and network devices to determine the same third CSI duration, fourth CSI duration, or CSI reference resources. This facilitates the alignment of the CPU usage time periods of the second CSI report between the terminal devices and network devices. When the CPU usage time periods of the second CSI report are aligned between the terminal devices and network devices, it is beneficial for the network devices to determine whether any CSI reports submitted by the terminal devices at a specific time have not been updated due to insufficient CPU resources, based on the CPU usage of the terminal devices at various times. In other words, it helps the network devices obtain accurate CSI reports.

[0066] For example, the transmission start time of the second CSI report can be replaced by the uplink transmission unit of the second CSI report, the start time of the uplink transmission unit (or uplink channel) of the second CSI report, or the first symbol of the uplink transmission unit of the second CSI report, or the first symbol of the uplink transmission unit used to carry the second CSI report.

[0067] For example, the third reference signal transmission timing may correspond to the latest reference signal transmission timing within the observation window corresponding to the first prediction task, or it may be the latest time-domain unit (such as a time slot or symbol) within the latest reference signal transmission timing within the observation window corresponding to the first prediction task. Further description of the reference signal transmission timing can be found in the first aspect above.

[0068] For example, the end time of the second downlink channel can be replaced with the last symbol of the second downlink channel. The second downlink channel is used to trigger the second CSI report.

[0069] For example, the first prediction task can be replaced by: the network instructing / requesting the terminal device to send a second CSI report carrying data related to the first prediction task. In other words, the second CSI report is used to carry data related to the first prediction task. For example, the second CSI report can carry inference information related to the first prediction task, such as the predicted CSI. As another example, the second CSI report can carry monitoring information related to the first prediction task, such as one or more of the following: the SGCS or NMSE corresponding to the predicted CSI, the measured CSI corresponding to the prediction window, and the measured CSI corresponding to the observation window. As yet another example, the second CSI report can carry training information related to the first prediction task, such as one or more of the following: the measured CSI corresponding to the prediction window and the measured CSI corresponding to the observation window.

[0070] In conjunction with the third aspect, in some implementations of the third aspect, the third CSI duration is determined based on the sixth duration, including: determining the third CSI duration based on the sixth duration and the duration of the observation window corresponding to the first prediction task.

[0071] For example, the duration of the third CSI is not less than the sum of the sixth duration, the duration of the observation window corresponding to the first prediction task, and the second duration predefined by the protocol. The second duration can be referred to the description in the first aspect above.

[0072] For example, the duration of the second observation window corresponding to the first prediction task corresponds to the duration of the K observation resources included in the second observation window. The value of K is configured by the network and / or indicated by the capabilities of the terminal device.

[0073] For example, the duration of the fourth CSI is not less than the sum of the sixth duration and the third duration predefined by the protocol. The third duration can be referred to the description in the first aspect above.

[0074] For example, the interval between the CSI reference resource and the start time of the transmission of the second CSI report is greater than or equal to the minimum of the fourth duration #a, where the fourth duration #a is the sum of the sixth duration and the fifth duration predefined by the protocol. The fifth duration can be referred to the description in the first aspect above.

[0075] For example, the sixth duration is a predefined value; or, the sixth duration is associated with a first value of at least one first inference parameter, the first value of which is used for the first prediction task.

[0076] Based on the above technical solution, if the sixth duration is a predefined value, it helps reduce the processing complexity of the first device. If the sixth duration is related to the value of the first inference parameter, it helps the first device determine a sixth duration that is closer to the execution duration of the first prediction task based on the value of the first inference parameter, thereby improving the transmission efficiency of the communication system and / or reducing resource consumption. For example, if the first device determines a sixth duration that is closer to the execution duration of the first prediction task, it helps the first device determine a more accurate CPU usage method for the second CSI report based on one or more of the third CSI duration, the fourth CSI duration, or CSI reference resources, thereby avoiding resource waste caused by reserving a longer CPU time for the second CSI report.

[0077] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset identifier, association identifier, or function identifier.

[0078] Fourthly, a communication method is provided, the method comprising: determining one or more of the following based on a seventh duration: a fifth CSI duration, a sixth CSI duration, and a CSI reference resource corresponding to a third CSI report; the fifth CSI duration corresponds to the interval between the end time of the third downlink channel and the start time of the transmission of the third CSI report, the sixth CSI duration corresponds to the interval between the transmission timing of the fifth reference signal and the transmission start time of the third CSI report; the seventh duration corresponds to the execution duration of an AI-based first compression task, and the third CSI report, the third downlink channel, and the transmission timing of the fifth reference signal correspond to the first compression task.

[0079] This method can be performed by a first device, and further description of the first device can be found in the first aspect above.

[0080] Based on the above technical solution, by defining one or more of the fifth CSI duration, sixth CSI duration, and CSI reference resources as related to the seventh duration, it is beneficial for terminal devices and network devices to determine the same fifth CSI duration, sixth CSI duration, or CSI reference resources. This, in turn, helps terminal devices and network devices align the CPU usage time of the third CSI report. When terminal devices and network devices align the CPU usage time of the third CSI report, it is beneficial for network devices to determine whether any CSI reports submitted by the terminal device at a specific time were not updated due to insufficient CPU resources, based on the CPU usage of the terminal device at various times. In other words, it helps network devices obtain accurate CSI reports.

[0081] For example, the transmission start time of the third CSI report can be replaced by the uplink transmission unit of the third CSI report, the start time of the uplink transmission unit (or uplink channel) of the third CSI report, or the first symbol of the uplink transmission unit of the third CSI report, or the first symbol of the uplink transmission unit used to carry the third CSI report.

[0082] For example, the fifth reference signal transmission timing may correspond to the latest reference signal transmission timing within the observation window corresponding to the first compression task, or it may be the latest time-domain unit (such as a time slot or symbol) within the latest reference signal transmission timing within the observation window corresponding to the first compression task. Further description of the reference signal transmission timing can be found in the first aspect above.

[0083] For example, the end time of the third downlink channel can be replaced with the last symbol of the third downlink channel. The third downlink channel is used to trigger the third CSI report.

[0084] For example, the first compression task can be replaced by: the network instructing / requesting the terminal device to send a third CSI report carrying data related to the first compression task. In other words, the third CSI report is used to carry data related to the first compression task. For example, the third CSI report can carry inference information related to the first compression task, such as compressed CSI obtained by compressing the measured CSI. As another example, the third CSI report can carry monitoring information related to the first compression task, such as one or more of the following: the measured CSI, the SGCS or NMSE corresponding to the compressed CSI (obtained by compressing the measured CSI). As yet another example, the third CSI report can carry training information related to the first compression task, such as one or more of the following: the measured CSI, the compressed CSI, and the gradient of the compressed CSI.

[0085] For example, the duration of the fifth CSI is not less than the sum of the seventh duration and the second duration predefined by the protocol. The second duration can be referred to the description in the first aspect above.

[0086] For example, the duration of the sixth CSI is not less than the sum of the seventh duration and the third duration predefined by the protocol. The third duration can be referred to the description in the first aspect above.

[0087] For example, the interval between the CSI reference resource and the start time of the transmission of the third CSI report is greater than or equal to the minimum of the fourth duration #b, where the fourth duration #b is the sum of the seventh duration and the fifth duration predefined by the protocol. The fifth duration can be referred to the description in the first aspect above.

[0088] For example, the seventh duration is a predefined value; or, the seventh duration is associated with a second value of at least one second inference parameter, the second value of which is used for the first compression task.

[0089] Based on the above technical solution, if the seventh duration is a predefined value, it helps reduce the processing complexity of the first device. If the seventh duration is related to the value of the second inference parameter, it helps the first device determine a seventh duration that is closer to the execution duration of the first compression task based on the value of the second inference parameter, thereby improving the transmission efficiency of the communication system and / or reducing resource consumption. For example, if the first device determines a seventh duration that is closer to the execution duration of the first compression task, it helps the first device determine a more accurate CPU usage method for the third CSI report based on one or more of the fifth CSI duration, the sixth CSI duration, or CSI reference resources, thereby avoiding resource waste caused by reserving a longer CPU time for the third CSI report.

[0090] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0091] Fifthly, a communication method is provided, the method comprising: receiving first information, the first information including at least one third value of each of at least one first inference parameter, and / or including at least one fourth value of each of at least one second inference parameter; the first inference parameters being used for a prediction task, and the second inference parameters being used for a compression task; sending second information, the second information including at least one set of inference parameters, each of the at least one set of inference parameters including at least one first inference parameter and at least one second inference parameter, wherein a fifth value of the first inference parameter included in each of the at least one set of inference parameters belongs to at least one third value, and / or a sixth value of the second inference parameter included belongs to at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; and receiving third information, the third information including the first set of inference parameters, the first set of inference parameters belonging to at least one set of inference parameters, the first set of inference parameters being used for the first task.

[0092] This method can be executed by a device on the terminal side. For more details on the device on the terminal side, please refer to the first aspect above.

[0093] Based on the above technical solution, the terminal device can combine the values ​​of the inference parameters configured by the network device for the prediction task and the values ​​of the inference parameters configured for the compression task to obtain at least one set of inference parameters for the second task, and send at least one set of inference parameters to the network device. This allows the network device to accurately issue inference parameter configurations that meet the model deployment requirements of the terminal device based on at least one set of inference parameters reported by the terminal device, without having to send too many combinations of inference parameter values ​​to the terminal device, thus saving signaling overhead.

[0094] Furthermore, when the set of inference parameters for the second task is determined by the terminal device, the terminal device can combine the values ​​of the inference parameters configured by the network device for the prediction task and the inference parameters for the compression task according to the maximum value of the inference parameters for the second task supported by the terminal device, thereby avoiding the network device configuring inference parameter values ​​for the terminal device that exceed the terminal device's capabilities.

[0095] In conjunction with the fifth aspect, in some implementations of the fifth aspect, before receiving the first information, the method further includes: receiving fourth information, the fourth information being used to request the value of a first inference parameter supported by the first device, and / or, to request the value of a second inference parameter supported by the first device; and sending fifth information, the fifth information including the value of the first inference parameter supported by the first device, and / or including the value of the second inference parameter supported by the first device.

[0096] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset identifier, association identifier, or function identifier.

[0097] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0098] A sixth aspect provides a communication method, the method comprising: sending first information, the first information including at least one third value of each of at least one first inference parameter, and / or including at least one fourth value of each of at least one second inference parameter; the first inference parameters being used for a prediction task, and the second inference parameters being used for a compression task; receiving second information, the second information including at least one set of inference parameters, each of the at least one set of inference parameters including at least one first inference parameter and at least one second inference parameter, a fifth value of the first inference parameter included in each of the at least one set of inference parameters belonging to at least one third value, and / or a sixth value of the second inference parameter included belonging to at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; and sending third information, the third information including the first set of inference parameters, the first set of inference parameters belonging to at least one set of inference parameters, the first set of inference parameters being used for the first task.

[0099] This method can be executed by devices on the network device side. For more details on network device side devices, please refer to the first aspect above.

[0100] The beneficial effects of the sixth aspect can be referenced in the fifth aspect above.

[0101] In conjunction with the sixth aspect, in some implementations of the sixth aspect, before sending the first information, the method further includes: sending a fourth information, the fourth information being used to request the value of a first inference parameter supported by the first device, and / or, to request the value of a second inference parameter supported by the first device; and receiving a fifth information, the fifth information including the value of the first inference parameter supported by the first device, and / or including the value of the second inference parameter supported by the first device.

[0102] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset identifier, association identifier, or function identifier.

[0103] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0104] A seventh aspect provides an apparatus. This apparatus may include functional modules corresponding to each of the methods / operations / steps / actions described in any possible implementation of the first aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the second, third, fourth, fifth, or sixth aspects. The module may be a hardware circuit, software, or a combination of hardware circuitry and software implementation.

[0105] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the first device in the methods described in any one of the first to fourth aspects above, while the processing module is used to perform processing-related actions performed by the first device in the methods described in any one of the first to fourth aspects above.

[0106] In one design, the device can be a terminal device, or a device, module, circuit, or chip configured in the terminal device, or a device that can be used in conjunction with network devices, such as an OTT host or cloud server.

[0107] In one design, the device can be a network device, or a device, module, circuit, or chip configured in the network device, or a device that can be used in conjunction with the network device, such as a smart network element with RIC deployed.

[0108] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the terminal device in the method described in the fifth aspect above, while the processing module is used to perform processing-related actions performed by the terminal device in the method described in the fifth aspect above.

[0109] In one design, the terminal device can be the terminal device itself, or a device, module, circuit or chip configured in the terminal device, or a device that can be used with network equipment, such as an OTT host or cloud server.

[0110] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the network device in the method described in the sixth aspect above, while the processing module is used to perform processing-related actions performed by the network device in the method described in the sixth aspect above.

[0111] In one design, the network device can be the network device itself, or a device, module, circuit or chip configured in the network device, or a device that can be used in conjunction with the network device, such as a smart network element with RIC deployed.

[0112] Eighthly, an apparatus is provided, comprising a processor and a storage medium storing instructions which, when executed by the processor, cause a method as described in the first aspect or any possible implementation thereof to be implemented, or cause a method as described in the second aspect or any possible implementation thereof to be implemented, or cause a method as described in the third aspect or any possible implementation thereof to be implemented, or cause a method as described in the fourth aspect or any possible implementation thereof to be implemented, or cause a method as described in the fifth aspect or any possible implementation thereof to be implemented, or cause a method as described in the sixth aspect or any possible implementation thereof to be implemented.

[0113] A ninth aspect provides an apparatus comprising a processing circuit for processing data and / or information such that a method as in the first aspect or any possible implementation thereof is implemented, or a method as in the second aspect or any possible implementation thereof is implemented, or a method as in the third aspect or any possible implementation thereof is implemented, or a method as in the fourth aspect or any possible implementation thereof is implemented, or a method as in the fifth aspect or any possible implementation thereof is implemented, or a method as in the sixth aspect or any possible implementation thereof is implemented.

[0114] The processing circuit may include one or more processors, or all or part of the circuitry in one or more processors used for control or processing functions.

[0115] Optionally, the apparatus may further include a memory for storing a program or instructions, and the processor for executing the program or instructions to implement the method as described in the first aspect or any possible implementation thereof, or to implement the method as described in the second aspect or any possible implementation thereof, or to implement the method as described in the third aspect or any possible implementation thereof, or to implement the method as described in the fourth aspect or any possible implementation thereof, or to implement the method as described in the fifth aspect or any possible implementation thereof, or to implement the method as described in the sixth aspect or any possible implementation thereof.

[0116] Optionally, the device may also include the transceiver circuit, or an input / output interface.

[0117] In a tenth aspect, a chip is provided, including processing circuitry, the processing circuitry being configured to execute a program or instructions to cause the method as described in the first aspect or any possible implementation thereof to be implemented, or to cause the method as described in the second aspect or any possible implementation thereof to be implemented, or to cause the method as described in the third aspect or any possible implementation thereof to be implemented, or to cause the method as described in the fourth aspect or any possible implementation thereof to be implemented, or to cause the method as described in the fifth aspect or any possible implementation thereof to be implemented, or to cause the method as described in the sixth aspect or any possible implementation thereof to be implemented.

[0118] Optionally, the chip may further include a memory for storing programs or instructions.

[0119] Optionally, the chip may also include transceiver circuitry, or input / output interfaces.

[0120] Eleventhly, a computer-readable storage medium is provided, the computer-readable storage medium including instructions that, when executed by a processor, cause the method as in the first aspect or any possible implementation of the first aspect to be implemented, or cause the method as in the second aspect or any possible implementation of the second aspect to be implemented, or cause the method as in the third aspect or any possible implementation of the third aspect to be implemented, or cause the method as in the fourth aspect or any possible implementation of the fourth aspect to be implemented, or cause the method as in the fifth aspect or any possible implementation of the fifth aspect to be implemented, or cause the method as in the sixth aspect or any possible implementation of the sixth aspect to be implemented.

[0121] In a twelfth aspect, a computer program product is provided, the computer program product comprising computer program code or instructions that, when executed, cause the method of the first aspect and any possible implementation thereof to be implemented, or cause the method of the second aspect and any possible implementation thereof to be implemented, or cause the method of the third aspect and any possible implementation thereof to be implemented, or cause the method of the fourth aspect and any possible implementation thereof to be implemented, or cause the method of the fifth aspect and any possible implementation thereof to be implemented, or cause the method of the sixth aspect and any possible implementation thereof to be implemented.

[0122] In a thirteenth aspect, a communication system is provided, the communication system including means for performing the first aspect and any possible implementation thereof, or including means for performing the second aspect and any possible implementation thereof, or including means for performing the third aspect and any possible implementation thereof, or including means for performing the fourth aspect and any possible implementation thereof, or including means for performing the fifth aspect and any possible implementation thereof, or including means for performing the sixth aspect and any possible implementation thereof. Attached Figure Description

[0123] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment;

[0124] Figure 2 is a schematic diagram of another communication system applicable to the communication method of this application embodiment;

[0125] Figure 3 is a schematic diagram of a possible application framework in a communication system;

[0126] Figure 4 is a schematic diagram of another possible application framework in a communication system;

[0127] Figure 5 is a schematic diagram of the inference process for CSI prediction;

[0128] Figure 6 is a schematic diagram of the inference process of CSI compression;

[0129] Figure 7 is a schematic diagram of CSI calculation time;

[0130] Figure 8 is a schematic flowchart of the method 800 provided in an embodiment of this application;

[0131] Figure 9 is a schematic diagram illustrating the method for determining CSI calculation time based on the embodiments of this application;

[0132] Figure 10 is a schematic diagram of determining CSI reference resources based on the method provided in the embodiments of this application;

[0133] Figure 11 is a schematic flowchart of the method 1100 provided in an embodiment of this application;

[0134] Figure 12 is a schematic diagram of determining the CPU count value based on the method provided in the embodiments of this application;

[0135] Figure 13 is a schematic flowchart of method 1300 provided in an embodiment of this application;

[0136] Figure 14 is a schematic diagram illustrating the method for determining CSI calculation time based on the embodiments of this application;

[0137] Figure 15 is a schematic diagram of determining CSI reference resources based on the method provided in the embodiments of this application;

[0138] Figure 16 is a schematic diagram illustrating the method for determining CSI calculation time based on embodiments of this application;

[0139] Figure 17 is a schematic diagram of determining CSI reference resources based on the method provided in the embodiments of this application;

[0140] Figure 18 is a schematic flowchart of method 1800 provided in an embodiment of this application;

[0141] Figure 19 is a schematic block diagram of a communication device provided in an embodiment of this application;

[0142] Figure 20 is another schematic block diagram of the communication device provided in an embodiment of this application;

[0143] Figure 21 is a schematic diagram of the CPU rule determination module provided in an embodiment of this application;

[0144] Figure 22 is a schematic block diagram of the AI ​​processor provided in an embodiment of this application. Detailed Implementation

[0145] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0146] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0147] First, in this application, the terminal side can also be referred to as the UE (user equipment) side, including: terminal equipment, components deployed in the terminal equipment (such as circuits or chips inside the terminal equipment), equipment deployed outside the terminal equipment (such as OTT hosts or cloud servers), or components deployed in equipment outside the terminal equipment (such as circuits or chips inside the equipment). The network (NW) side includes: network equipment communicating with the terminal equipment, components deployed in the network equipment (such as circuits or chips with near real-time RAN intelligent control functions inside the network equipment), equipment deployed outside the network equipment (such as intelligent network elements, for example, intelligent network elements with near real-time RAN intelligent control functions), or components deployed in the intelligent network element (such as circuits or chips inside the intelligent network element). The network equipment may include: access network equipment, core network equipment, or operation administration and maintenance (OAM) equipment.

[0148] Second, in this application, the indication includes direct indication (also known as explicit indication) and indirect indication (also known as implicit indication). Directly indicating information A means including information A; indirectly indicating information A can mean indicating information A through the correspondence between information A and information B and by directly indicating information B; or by indicating information A through a preset rule that can be used to determine A based on B and by directly indicating information B. The correspondence between information A and information B, and the preset rule, can be predefined, pre-stored, pre-burned, or pre-configured.

[0149] Third, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0150] Fourth, in this application, the use of prefixes such as "first" and "second" is merely for the purpose of distinguishing and describing different things belonging to the same category, and does not constrain the order, size, or quantity of things. For example, "first information" and "second information" are simply different information, and do not limit the quantity of information, the order of transmission, or the relationship of priority.

[0151] Fifth, in this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between a terminal device and a computing node, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0152] Sixth, in the embodiments of this application, "when," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a time, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0153] Seventh, in this application, the words "example," "exemplary," "for example," or "likely" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "example," "exemplary," "for example," or "likely" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "example," "exemplary," "for example," or "likely" is intended to present the relevant concepts in a specific manner.

[0154] The technical solutions 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, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0155] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this disclosure can be replaced by a first network element, and the network device can be replaced by a second network element, both performing the corresponding communication methods described in this disclosure.

[0156] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment. As shown in Figure 1, the communication system 100A may include at least one access network device, such as access network device 110 shown in Figure 1; the communication system 100A may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1. Access network device 110 and terminal devices (such as terminal device 120 and terminal device 130) can communicate via a wireless link. The communication devices in this communication system, for example, access network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0157] 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 levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming (BF), and supporting beam management, network energy efficiency 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.

[0158] Figure 2 is a schematic diagram of another communication system applicable to the communication method of this application embodiment. Compared with the communication system 100A shown in Figure 1, the communication system 100B shown in Figure 2 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models. The AI ​​network element can also be simply referred to as an intelligent network element.

[0159] In one possible implementation, access 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 access 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 access network device 110, and another portion on terminal devices 120 and / or 130. Alternatively, the trained AI model may be deployed on access network device 110. Or, the trained AI model may be deployed on terminal devices 120 and / or 130.

[0160] It should be understood that Figure 2 is only used as an example of the AI ​​network element 140 being directly connected to the access network device 110. In other scenarios, the AI ​​network element 140 can also be connected to the terminal device. Alternatively, the AI ​​network element 140 can be connected to both the access network device 110 and the terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the access network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements. For example, the AI ​​network element 140 can also be set as a module in the access network device and / or the terminal device, for example, in the access network device 110 or the terminal device shown in Figure 1.

[0161] It should be noted that Figures 1 and 2 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 1 and 2. In practical applications, the communication system may include multiple access network devices and multiple terminal devices. The embodiments of this application do not limit the number of access network devices and terminal devices included in the communication system.

[0162] In the embodiments of this application, the terminal device may also be referred to as UE, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0163] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0164] 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.

[0165] 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.

[0166] The access network device in this application embodiment can be a device used to communicate with terminal devices. This access network device can also be called a network device, such as a base station. In this application embodiment, the access network device can refer to a 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 such as: 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, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technology or equipment form used in the access network equipment.

[0167] 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.

[0168] In some deployments, the access network equipment mentioned in the embodiments of this application may be a device including a CU, or a DU, or a device including both CU and DU, or a device with a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the access network equipment may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0169] 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.

[0170] 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, it moves some downlink and / or uplink baseband functions—for example, for downlink, precoding, digital beamforming, or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP)—from the DU to the RU; and for uplink, digital beamforming, or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP)—from the DU to the RU. In one possible implementation, this interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting methods between DU and RU are different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0171] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. The DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping itself), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming, or one or more of IFFT / CP addition) are implemented in the RU. For uplink transmission, de-RE mapping is used as the dividing line. The DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping itself), while other functions following de-mapping (e.g., digital BF or FFT / CP removal) are implemented in the RU. It is understood that descriptions of the functions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol and will not be elaborated upon here.

[0172] 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.

[0173] 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 open RAN (ORAN) architecture, CU can also be called open CU (open-CU, O-CU), DU can also be called open DU (open-DU, O-DU), CU-CP can also be called open CU-CP (open-CU-CP) O-CU-CP, CU-UP can also be called open CU-UP (open-CU-UP, O-CU-UP), and RU can also be called open RU (open-RU, 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.

[0174] 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.

[0175] 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.

[0176] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network equipment, terminal equipment, or core network elements. Alternatively, the AI ​​node can also 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 OTT system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: access network equipment, terminal equipment, or core network elements.

[0177] 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.

[0178] 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.

[0179] AI nodes can be AI network elements or AI modules.

[0180] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected via interfaces (e.g., next-generation (NG) interfaces, Xn interfaces) or air interfaces. The NG interface is the interface between the radio access network and the 5G core network. The Xn interface is the interface between access network devices, and the air interface is the interface between access network devices and terminal devices. These network element nodes, such as core network devices, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (only one is shown in Figure 3 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in the CU-CP and / or CU-UP.

[0181] 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.

[0182] 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.

[0183] Network devices can be network devices equipped with one or more AI modules. These network devices can include one or more devices in the core network, access network nodes (RAN nodes), or OAM as shown in Figure 3. For example, the AI ​​module can be a RAN intelligent controller (RIC) as shown in Figure 4, such as a near-real-time RIC (near-RT RIC) or a non-real-time RIC (non-RT RIC). For instance, a near-real-time RIC is located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC is located in the OAM, a cloud server, a core network device, or other access 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 train based on the training dataset. Exemplarily, near-real-time RICs and non-real-time RICs can also be set up as separate network elements, and the access network device can be either a near-real-time RIC or a non-real-time RIC.

[0184] Figure 4 illustrates another possible application framework in a communication system. In addition to access network nodes (CU, DU, and RU are shown in the figure) and terminals, the communication system shown in Figure 4 also includes an RIC (Regulator-Integrated Circuit). For example, the RIC could be the AI ​​module shown in Figure 3, which can be used to implement AI-related functions. The RIC includes near-real-time RICs and non-real-time RICs. Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0185] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0186] 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., one or more of CU, CU-CP, CU-UP, DU, 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.

[0187] 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.

[0188] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained below.

[0189] (1) Artificial Intelligence. This refers to enabling machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, artificial intelligence refers to the technology of presenting human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or reasoning.

[0190] (2) Machine Learning (ML). This is one implementation method of artificial intelligence. Machine learning is a method that endows machines with the ability to perform functions that cannot be directly programmed. In practical terms, machine learning is a method that uses data to train a model and then uses the model to make predictions. There are many machine learning methods, such as neural networks (NN), decision trees, and support vector machines. Machine learning theory mainly involves designing and analyzing algorithms that allow computers to learn automatically. Machine learning algorithms are a class of algorithms that automatically analyze data to obtain patterns and use these patterns to predict unknown data.

[0191] (3) Channel information.

[0192] In communication systems, network devices determine one or more of the following configurations for scheduling the downlink data channel of terminal equipment based on channel information: resources, modulation and coding scheme (MCS), and precoding. Channel information, also known as CSI or channel environment information, is information that reflects channel characteristics and quality.

[0193] CSI measurement refers to the process by which the receiver deciphers channel information based on a reference signal transmitted by the transmitter; that is, it estimates channel information using channel estimation methods. For example, the reference signal may include one or more of the following: channel state information reference signal (CSI-RS), synchronizing signal / physical broadcast channel block (SSB), sounding reference signal (SRS), or demodulation reference signal (DMRS). One or more of CSI-RS, SSB, and DMRS can be used to measure downlink channel information. SRS and DMRS can be used to measure uplink channel information.

[0194] Taking FDD communication as an example, since uplink and downlink channels lack reciprocity or cannot guarantee reciprocity, network devices need to obtain downlink CSI through uplink feedback from terminal devices. Network devices typically send a downlink reference signal to the terminal device, which receives this signal. Since the terminal device knows the transmission information of the downlink reference signal, it can perform channel measurements and interference measurements based on the received signal to estimate the downlink channel it traverses. The terminal device then generates the downlink CSI based on this measurement and the resulting downlink channel matrix. Finally, the terminal device generates a CSI report according to a predefined protocol method or network device configuration and feeds it back to the network device so that it can obtain the downlink CSI.

[0195] In this embodiment, the meaning of CSI is broader than that in traditional schemes. It is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI). It can also be one or more of the following: channel response information (such as channel response matrix), channel matrix, channel feature matrix, precoding matrix, reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), the identity (ID) of the optimal beam, or the ID of the top K beams. The signal to interference plus noise ratio can also be called the signal-to-interference-plus-noise ratio. The optimal beam refers to the beam that maximizes the received or transmitted energy. For example, if the receiver uses different receiving beams to receive signals, the optimal beam may include the beam with the largest RSRP among the signals received from multiple different receiving beams. For example, if the transmitter uses different transmit beams to send signals, the optimal beam can include the beam with the highest RSRP (Receiving Power Ratio) of the signal when it arrives at the receiver. Similarly, the optimal top K beams refer to the top K beams that maximize the received or transmitted energy.

[0196] In this system, RI indicates the number of downlink transmission layers suggested by the terminal device, CQI indicates the modulation and coding schemes supported by the current channel conditions as determined by the terminal device, and PMI indicates the precoding suggested by the receiver of the reference signal, such as the terminal device. The number of precoding layers indicated by PMI corresponds to RI. The channel response and channel matrix represent the channel itself, while the channel feature matrix and precoding matrix are matrices composed of features extracted from the channel.

[0197] (4) Channel Reporting.

[0198] Channel reports can be used to reflect channel measurement information or channel information corresponding to a reference signal (which can be used for channel measurement or channel estimation). In other words, channel reports are information generated based on the information obtained from measuring the reference signal, and they can reflect channel environment information, etc.

[0199] Channel report can also be replaced by channel measurement report, or measurement report, or CSI report, or CSI feedback information, or CSI compression information, etc., without limiting other terms that may be used.

[0200] (5) AI-based CSI-RS feedback enhancement.

[0201] AI-based CSI-RS feedback enhancement can perform CSI prediction and CSI compression.

[0202] CSI prediction: For example, it can include time-domain CSI prediction based on the UE side model.

[0203] Figure 5 illustrates the inference process for CSI prediction. As shown in Figure 5, the AI / ML-based CSI prediction model is used to predict future CSI based on historical CSI. The historical CSI can be of the type of raw channel matrix, precoding matrix, etc. The input data of the CSI prediction model is related to the channel measurement results; for example, the input data of the CSI prediction model can be obtained by preprocessing (such as normalization) the channel measurement results. The output data of the CSI prediction model may also require some processing.

[0204] For example, the training data for training the CSI prediction model can be acquired or generated by the UE. This training data may include the target CSI within the observation window and / or the target CSI within the prediction window. For the UE-side model inference process, the UE internally performs model inference using the corresponding input data. The output data of the CSI prediction model's inference process may include the predicted CSI. For the network-side performance monitoring process, the performance metrics used for model monitoring or the data used to calculate these metrics are acquired or generated by the UE and fed back to the base station, which then performs performance monitoring. The data related to the CSI prediction model's model monitoring process may include the ground-truth CSI, calculated performance metrics, and the results of performance monitoring.

[0205] CSI compression can include, for example, spatial-frequency domain CSI compression or spatial-temporal domain CSI compression based on a two-side model. Spatial-frequency domain CSI compression can be understood as the joint compression of CSI in both the spatial and frequency domains. Spatial-temporal domain CSI compression can also be understood as the joint compression of CSI in both the spatial and temporal domains.

[0206] Figure 6 illustrates the inference process of CSI compression. The AI / ML-based CSI generation section generates CSI feedback information at the UE side. The AI / ML-based CSI reconstruction section reconstructs the CSI at the base station side based on the received CSI feedback information. The UE can select a CSI generation model compatible with the CSI reconstruction model used by the gNB based on model pairing information. The input (for the CSI generation section) or output (for the CSI reconstruction section) of the AI / ML model used for CSI compression can be of the type of raw channel matrix or precoding matrix, etc. Further preprocessing of the channel measurement results may be required to generate the input to the CSI generation model. Further processing may also be required for the output of the CSI reconstruction model.

[0207] For the NW portion of two-side model inference, input data can be generated or acquired by the UE and terminates at the base station. For the UE portion of two-side model inference, input data is available within the UE. Data related to the CSI-compressed model inference process may include CSI feedback information.

[0208] For model training, the training data used for model training can be generated or acquired by the UE or base station. Data related to the CSI-compressed model training process may include target CSI, CSI feedback information, or gradients of CSI feedback information, etc.

[0209] For NW-side performance monitoring, the calculated performance metrics or the data used for performance metric calculation can be generated or acquired by the UE and terminate at the base station. Data related to the model monitoring process of CSI compression may include target CSI or calculated performance metrics, etc.

[0210] For CSI feedback enhancement use cases, the monitoring method can be:

[0211] 1) NW side monitoring, such as base stations estimating the performance of AI / ML models based on the target CSI reported by the UE (the actual channel estimation results associated with the CSI report) and further generating monitoring decisions.

[0212] 2) UE-side monitoring, for example, the UE performs model monitoring based on the output of the CSI reconstruction model indicated by the base station (the UE needs the output of the CSI reconstruction model to be associated with the CSI report), or, based on the output of the CSI reconstruction model of the UE-side agent, or, directly estimates intermediate KPIs, or estimates the monitoring output. The base station can configure thresholds to the UE to instruct the UE to perform model monitoring.

[0213] (7) CSI processing rules.

[0214] The NR protocol specifies the CSI processing guidelines on the terminal device side. The terminal device reports the number N of CSI calculations it can process simultaneously, based on its own capabilities. CPU That is, the UE is configured with N CPU Each CSI processing unit (CPU) is used to process all CSI reports configured on all configuration component carriers (CCs).

[0215] At a given symbol, if the computation reported by the CSI uses L CPUs, then the terminal device has N CPUs. CPU -L represents unused CPU resources. For a given symbol S, there are N... CPU If -L CPUs are not occupied, and there are N CSI reports that need to occupy their respective CPUs starting from symbol S, then the number of CPUs corresponding to the nth CSI report among the N CSI reports is... Then the terminal device does not need to update the (NM) lowest priority CSI reports out of N CSI reports, where n = 1, 2, ..., N, 0 ≤ M ≤ N, and M is a subset of N CSI reports. The maximum value.

[0216] When there is insufficient idle CPU, the UE does not need to update the CSI report, but rather does not need to provide feedback. When there is insufficient CPU, the CSI report provided by the UE can be a cached previous CSI report or anything else, entirely depending on the UE implementation.

[0217] The amount of CPU used varies depending on the different types of CSI reports.

[0218] When performing time-frequency tracking of the tracking reference signal (TRS), i.e., when the report quantity is configured to 'none' and the CSI-RS-ResourceSet contains higher-level parameter TRS information (trs-Info), it does not consume CPU, i.e., O. CPU =0.

[0219] For Layer 1 Reference Signal Received Power (L1-RSRP) measurement, i.e., when reportQuantity is configured as 'cri-RSRP', 'ssb-index-RSRP', or 'none', and the CSI-RS-ResourceSet does not contain the higher-layer parameter trs-Info, the CPU usage is 1, i.e., O. CPU =1.

[0220] For CSI reports where the high-level parameter `reportQuantity` is 'tdcp' and the latency `Y` is configured by the high-level parameter `Y`, O CPU = (Y+1)÷X, where the value of X is reported by the UE capability.

[0221] When reportQuantity is configured as 'cri-RI-PMI-CQI', 'cri-RI-i1', 'cri-RI-i1-CQI', 'cri-RI-CQI', or 'cri-RI-LI-PMI-CQI', O CPU =K s K here s This indicates the number of non-zero power (NZP) CSI-RS resources in CSI-RS ResourceConfigMobility (CMR).

[0222] When an aperiodic (AP) CSI report is triggered, if there is no physical uplink shared channel (PUSCH) transmission and no CPU is occupied, and this CSI report is wideband, Type I codebook, or has no PMI feedback, and there is only one CSI-RS resource with 4 or fewer ports in the CMR, then all CPU is occupied, i.e., 0. CPU =N CPU .

[0223] For each CSI report processed, the CPU will continuously occupy a certain number of symbols. The protocol specifies that when the reporting type (reportConfigType) is not set to 'none', the number of CPU symbols occupied is determined according to the following rules.

[0224] The CPU time occupied by periodic (P) or semi-persistent (SP) CSI reports (excluding the initial semi-persistent CSI report reported on the PUSCH after the physical downlink control channel (PDCCH) triggers the CSI report) is as follows: starting from the first orthogonal frequency division multiplexing (OFDM) symbol of the earliest of the latest resources in the CSI-RS / CSI interference measurement (CSI-IM) / SSB occasions that are earlier than the CSI reference resource, until the last symbol of the PUSCH / physical uplink control channel (PUCCH) carrying the report.

[0225] CPU time consumed by non-periodic CSI reports: from the first symbol after the PDCCH that triggers the CSI report to the last symbol of the PUSCH that carries the report.

[0226] The CPU time occupied by the initial semi-persistent CSI report reported on the PUSCH after the PDCCH triggers the CSI report is from the first symbol after the PDCCH until the last symbol of the PUSCH carrying the report.

[0227] The NR protocol also specifies the CSI calculation time. Network devices must allow sufficient time for terminal devices when triggering CSI reporting. For CSI reports triggered by DCI on the PUSCH, the protocol stipulates that a terminal device will only report a valid CSI report if the following two conditions are met:

[0228] 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 ;

[0229] 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).

[0230] Here, Z ref An uplink symbol is defined as one in which the interval between the start time of its cyclic prefix (CP) and the end time of the last symbol of the PDCCH that triggers the CSI report is greater than or equal to T. proc,CSI =(Z)(2048+144)·κ2-μ ·T c And it is the earliest uplink symbol to satisfy this condition. When aperiodic CSI-RS is used for channel measurements of the nth triggered CSI report, Z' ref (n) is defined as an uplink symbol whose CP start time is greater than or equal to the interval between the start time of the CP and the end time of the last symbol of the latest-ending resource among the resources used for channel measurements. proc,CSI =(Z′)(2048+144)·κ2 -μ ·T c Furthermore, it must be the earliest uplink symbol to meet this condition. The above provision can be understood as the time interval between the end time of the first symbol of the PUSCH carrying the CSI report and the end time of the last symbol of the PDCCH triggering the CSI report being 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 all reference resources used for channel measurements must be greater than or equal to the specified time parameter T′. proc,CSI As shown in Figure 7. 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 are determined according to the tables and principles given in the protocol, and the constant κ is 64. T c Represents time units, where T c =1 / (Δf) max ·N F ), where Δf max =480×10 3 Hz, N f =4096. μ represents the value corresponding to the subcarrier spacing, for example, 0 represents a subcarrier spacing of 15kHz, 1 represents a subcarrier spacing of 30kHz, 2 represents a subcarrier spacing of 60kHz, and 3 represents a subcarrier spacing of 120kHz.

[0231] Furthermore, for CSI reporting not triggered by DCI (periodic and semi-persistent reporting), the protocol defines a CSI reference resource to limit the CSI calculation time, ensuring that the terminal device only needs to update the reported CSI when there is sufficient CSI 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 CSI calculation. In the time domain, the CSI reference resource is defined as a valid timeslot preceding the uplink timeslot for CSI reporting, and the symbol interval between the timeslot containing the CSI reference resource and the CSI reporting timeslot must be greater than the value specified 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 timeslot corresponding to a certain CSI reporting configuration, the terminal device may not report the CSI. The above provisions can be understood as the time interval between the CSI-RS used to calculate the CSI report and the CSI reporting timeslot being greater than or equal to the specified time parameter.

[0232] In view of this, this application provides a communication method that enables the UE and network device to align the CPU usage mode and the number of CPUs occupied in the AI-based CSI-RS feedback enhancement scenario. This helps the network device to determine whether any CSI report reported at a specific time has not been updated due to insufficient CPU resources, thereby helping the network device to obtain accurate CSI reports.

[0233] The communication method provided in the embodiments of this application will be described below with reference to the accompanying drawings, taking the interaction between a terminal device and a network device as an example.

[0234] Terminal devices can be the terminal device itself, the communication module within the terminal device, or the circuits or chips within the terminal device responsible for communication functions (such as modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores, etc.), or AI entities on the terminal device side. AI entities on the terminal device side can be the terminal device itself, or AI entities serving the terminal device, such as servers, such as OTT servers or cloud servers.

[0235] The network device side can be the network device itself, the communication module within the network device, or the circuits or chips within the network device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip or SIP chip containing a modem core, etc.), or it can be an AI entity on the network device side. The AI ​​entity on the network device side can be the network device itself, or it can be an AI entity serving the network device, such as a RIC, OAM, or a server, such as an OTT server or a cloud server.

[0236] It should be understood that the time mentioned in the embodiments of this application can be replaced with a time unit, which can be understood as any one or more of a slot, subframe, frame, or OFDM symbol. For example, the time corresponding to A represents the slot, subframe, frame, or OFDM symbol in which A is located, or the first slot, subframe, frame, or OFDM symbol in which A is located, or the last slot, subframe, frame, or OFDM symbol in which A is located. As another example, the start time corresponding to A represents the first slot, subframe, frame, or OFDM symbol in which A is located, and the end time corresponding to A represents the last slot, subframe, frame, or OFDM symbol in which A is located.

[0237] It should also be understood that the unit of duration (such as first duration, sixth duration, or seventh duration, etc.) mentioned in the embodiments of this application can be any time unit, such as symbol, time slot, frame, second (s), millisecond (ms), etc.

[0238] It should also be understood that the CPU in the following embodiments can be replaced by any of the following: a CSI processing unit, an AI / ML-based CSI processing unit, a processing unit for measurement information carried in CSI reports, a processing unit for AI information carried in CSI reports, a processing unit for information carried in AI-based CSI reports, a unit for processing CSI reports, and a unit for processing AI-based CSI reports. The AI ​​information can be information related to AI inference, AI training, or AI monitoring. This application does not limit the use cases for AI; for example, AI use cases can be AI-based CSI prediction, AI-based beam management (BM) (which may include beam management or beam prediction), AI-based CSI compression, etc.

[0239] Figure 8 is a schematic flowchart of a communication method 800 provided in an embodiment of this application. The steps of method 800 will be described in detail below.

[0240] S810 allows terminal devices and network devices to configure inference parameters.

[0241] For example, in S810, the terminal device and the network device determine a first value of at least one first inference parameter and a second value of at least one second inference parameter. The first value of the at least one first inference parameter is used for a first prediction task based on AI, and the second value of the at least one second inference parameter is used for a first compression task based on AI.

[0242] Among them, the AI-based first prediction task and the AI-based first compression task belong to the first task, and the input data of the first compression task is determined based on the output data of the first prediction task.

[0243] For example, the first AI-based prediction task is AI-based CSI prediction, and the first AI-based compression task is AI-based CSI compression. Further descriptions of AI-based CSI prediction and AI-based CSI compression can be found in the terminology section above.

[0244] Optionally, the first task can be called separate CSI prediction followed by CSI compression (SPC). Alternatively, the first task can be called a joint task of CSI prediction and CSI compression. Alternatively, the first task can be called a joint task of CSI prediction and CSI compression in the space-time-frequency domain. Alternatively, the first task can be called a joint task of CSI prediction and CSI compression in the angle-domain, time-delay-domain, and Doppler-domain. Space-time-frequency domain CSI compression can be understood as the joint compression of CSI in the spatial, frequency, and time domains, or the joint compression of CSI in the spatial and frequency domains using time-domain correlation. Angle-domain, time-delay-domain, and Doppler-domain CSI compression can be understood as the joint compression of CSI in the angle-domain, time-delay-domain, and Doppler-domain, or the joint compression of CSI in the angle-domain and Doppler-domain using time-domain correlation.

[0245] For example, the first AI-based prediction task is AI-based beam prediction, and the first AI-based compression task is AI-based beam compression. For instance, AI-based beam prediction may include predicting the K optimal beams (referred to as the top-K beams) in set A at the current time based on AI and information about the beams included in set B (such as RSRP), or predicting the K optimal beams in set A at future times. Here, set B belongs to set A, and the top-K beams belong to set A. AI-based beam compression may include compressing the beam information (such as the RSRP of the top-K beams) that the terminal device will report to the network device based on AI.

[0246] For example, the first prediction task can be replaced by: the NW instructing / requesting the UE to send a CSI report (e.g., denoted as the second CSI report) carrying data related to the first prediction task. In other words, the second CSI report is used to carry data related to the first prediction task. For example, the second CSI report can carry inference information related to the first prediction task, such as the predicted CSI. As another example, the second CSI report can carry monitoring information related to the first prediction task, such as one or more of the following: the square generalized cosine similarity (SGCS) or normalized mean square error (NMSE) corresponding to the predicted CSI, the CSI measured corresponding to the prediction window, and the CSI measured corresponding to the observation window. As yet another example, the second CSI report can carry training information related to the first prediction task, such as one or more of the following: the CSI measured corresponding to the prediction window and the CSI measured corresponding to the observation window.

[0247] For example, the first compression task can be replaced by: the NW instructing / requesting the UE to send a CSI report (e.g., denoted as the third CSI report) carrying data related to the first compression task. The third CSI report carries data related to the first compression task. For example, the third CSI report may carry inference information related to the first compression task, such as compressed CSI obtained by compressing the measured CSI. As another example, the third CSI report may carry monitoring information related to the first compression task, such as one or more of the following: the measured CSI, the SGCS or NMSE corresponding to the compressed CSI (obtained by compressing the measured CSI). As yet another example, the third CSI report may carry training information related to the first compression task, such as one or more of the following: the measured CSI, the compressed CSI, and the gradient of the compressed CSI.

[0248] For example, the first task can be replaced by: the NW instructing / requesting the UE to send a first CSI report carrying data related to the first task. In other words, the first CSI report is used to carry data related to the first task. For example, the first CSI report can carry inference information related to the first task, such as compressed predicted CSI obtained by compressing the predicted CSI. As another example, the first CSI report can carry monitoring information related to the first task, such as one or more of the following: monitoring information related to the first prediction task (such as the SGCS or NMSE corresponding to the predicted CSI, the measured CSI corresponding to the prediction window, and the measured CSI corresponding to the observation window), and monitoring information related to the first compression task (such as the predicted CSI, the SGCS or NMSE corresponding to the compressed predicted CSI (obtained by compressing the predicted CSI). For example, the first CSI report may carry training information related to the first task, such as one or more of the following: training information related to the first prediction task (such as the measured CSI corresponding to the prediction window, the measured CSI corresponding to the observation window), and training information related to the first compression task (such as the predicted CSI or the measured CSI, the compressed predicted CSI, and the gradient of the compressed predicted CSI).

[0249] The following describes at least one first inference parameter and at least one second inference parameter.

[0250] For example, at least one first inference parameter includes one or more of the following: whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting temporal location of the prediction window, dataset ID, associated ID, or functionality ID.

[0251] Whether AI features are supported can be replaced by any of the following: whether AI-based CSI prediction is supported, whether non-AI-based CSI prediction is supported, whether Doppler codebook is supported, whether both AI-based and non-AI-based CSI prediction are supported, or whether both AI-based CSI prediction and Doppler codebook are supported.

[0252] An observation window refers to a time window used to acquire input data for a prediction task. For example, if the prediction task is CSI prediction, then the observation window refers to the time period used to acquire the input data of the AI ​​model corresponding to the prediction task. The AI ​​model input data can be measurement information or measurement results of a reference signal (e.g., channel matrix, precoding matrix, CSI, codebook).

[0253] The number of observation instances included in an observation window refers to the number of reference signals within the window, the number of observation resources included in the window, or the number of input data points obtained from the reference signals within the window for the prediction task. For example, if the prediction task is CSI prediction, the number of observation instances included in the observation window could be the number of CSIs obtained from the reference signals within the window for the prediction task. The number of observation instances included in the observation window can be represented by K. An observation window can also refer to the duration corresponding to K observation resources.

[0254] Observation resources refer to the resources used to transmit the reference signal corresponding to an input data point for a prediction task. In other words, observation resources are used to transmit the reference signal to obtain an input data point for the prediction task. For example, if the prediction task is CSI prediction, then observation resources are used to transmit a reference signal corresponding to a CSI. The terms "observation resources" or "reference signal resources" can also be replaced with "reference resources," "CSI-RS resources," or "CSI-RS transmission occasion."

[0255] The interval between two adjacent observation resources included in an observation window refers to the interval between the start times of the two adjacent observation resources, or the interval between the end time of the observation resource with the earlier time domain location and the start time of the observation resource with the later time domain location. If the unit of the interval between two adjacent observation resources included in the observation window is a time slot, then the interval between two adjacent observation resources included in the observation window can be called the slot offsets of two resources included in the observation window. The interval between two adjacent observation resources included in the observation window can be represented by m.

[0256] A prediction window refers to the time window corresponding to the output data of a prediction task. For example, if the prediction task is CSI prediction, then the prediction window refers to the time period corresponding to the CSI output of the prediction task.

[0257] The number of prediction instances included in a prediction window refers to the number of output data points of the prediction task. For example, if the prediction task is CSI prediction, the number of prediction instances included in the prediction window can be the temporal length corresponding to the prediction results output by the prediction task, or the size of the temporal basis (DD-basis). The number of prediction instances included in the prediction window can be represented by N4.

[0258] The interval between two adjacent prediction instances included in the prediction window refers to the interval between the start times of two adjacent prediction instances, or the interval between the end time of the prediction instance that appears earlier in the time domain and the start time of the prediction instance that appears later in the time domain. For example, if the prediction task is CSI prediction, the interval between two adjacent prediction instances can be the size of the time domain cell corresponding to the aforementioned time domain base, such as the size of the time domain cell being a symbol or a time slot. The interval between two adjacent prediction instances included in the prediction window can be represented by d.

[0259] Dataset identifiers, association identifiers, and function identifiers are associated with the AI ​​model / function / feature used for the prediction task. For example, a dataset identifier refers to the identifier of the dataset corresponding to the AI ​​model / function / feature used for the prediction task; the dataset may include data or parameters used for model training, model validation or testing, or model inference. A function identifier is used to identify the function or corresponding parameter or combination of parameters of the AI ​​model / function / feature used for the prediction task. For example, a function identifier is used to identify the function of the AI ​​model / function / feature used for the prediction task and / or its adapted combination of parameters.

[0260] Optionally, at least one first inference parameter may be referred to as inference-related parameters for prediction task.

[0261] For example, at least one second inference parameter includes one or more of the following: dataset identifier, association identifier, model identifier, function identifier, format of input data for compression task, dimension of input data for compression task, dimension of output data for compression task, and processing method of output data for compression task.

[0262] Dataset identifiers, association identifiers, model identifiers, and function identifiers are associated with the AI ​​model / function / feature used for the compression task. For example, a dataset identifier refers to the identifier of the dataset corresponding to the AI ​​model / function / feature used for the compression task; the dataset may include data / parameters used for model training, model validation or testing, or model inference. A function identifier is used to identify the function or corresponding parameter or combination of parameters of the AI ​​model / function / feature used for the compression task. For example, a function identifier is used to identify the AI ​​model / function used for the compression task and / or its adapted combination of parameters.

[0263] The input data for the compression task is in the format of a precoding matrix and the codebook corresponding to the precoding matrix.

[0264] The dimensions of the input data for a compression task can include the dimensions of the precoding matrix and / or the codebook. The dimensions of the precoding matrix can include one or more of spatial, temporal, or frequency domain dimensions. The dimensions of the codebook can include one or more of the angle dimension (which can be denoted as L), the delay dimension (which can be denoted as M), and the Doppler dimension (which can be denoted as Q). For example, if the compression task is CSI compression, the aforementioned spatial dimension could be the number of CSI-RS ports, which can be denoted as P. CSI-RS = J * N1 * N2, where J represents the number of polarization directions, such as J = 1 or 2; N1 represents the number of logical antenna ports in the first direction (e.g., horizontal) within the same polarization direction; and N2 represents the number of logical antenna ports in the second direction (e.g., vertical) within the same polarization direction. The time-domain dimension can be the number of time-domain units corresponding to CSI-RS, or, if the input data of the compression task is determined based on the output data of the prediction task, the time-domain dimension can be the number of prediction instances included in the prediction window corresponding to the prediction task (which can be denoted as N4). The frequency-domain dimension can be the number of frequency-domain units corresponding to CSI-RS (which can be denoted as N3).

[0265] The dimension of the output data for a compression task can be the volume of the output data. For example, if the compression task is CSI compression, then the dimension of the output data for the compression task can be the CSI payload size.

[0266] The processing methods for the output data of a compression task can include one or more of the following: quantization methods (such as scalar quantization (SQ) or vector quantization (VQ)) or layer processing. Layer processing can include using the same processing method for different layers (layer / rank common) or using layer-specific processing methods for different layers (layer / rank specific).

[0267] Optionally, at least one second inference parameter may be referred to as inference-related parameters for compression.

[0268] For a more detailed description of the inference parameter configuration for terminal devices and network devices, please refer to Method 1800 below. For the sake of brevity, it will not be elaborated here.

[0269] It should be noted that S810 is an optional step. For example, if the first value of at least one first inference parameter and the second value of at least one second inference parameter are predefined or pre-configured by the network or operator, then method 800 may not execute S810.

[0270] S820, the terminal equipment and network equipment determine one or more of the following based on the first duration: the first CSI duration, the second CSI duration, and the CSI reference resource #1 corresponding to the first CSI report.

[0271] The first duration corresponds to the execution duration of the first task. The first duration corresponding to the execution duration of the first task may include at least one of the following: the first duration is related to the execution duration of the first task, the first duration is the execution duration of the first task, or the first duration is greater than or equal to the execution duration of the first task.

[0272] The first CSI duration corresponds to the interval between the end time of the first downlink channel and the start time of the transmission of the first CSI report.

[0273] The second CSI duration corresponds to the interval between the timing of the first reference signal transmission and the start time of the first CSI report transmission.

[0274] Among them, the first downlink channel, the first CSI report, and the first reference signal transmission timing correspond to the first task.

[0275] For example, the first downlink channel is used to trigger a first CSI report, or to trigger a first CSI report carrying data related to a first task. The end time of the first downlink channel can be replaced by the last symbol of the first downlink channel. For example, the first downlink channel is PDCCH.

[0276] The transmission start time of the first CSI report can be replaced by the uplink transmission unit of the first CSI report, the start time of the uplink transmission unit (or uplink channel) of the first CSI report, or the first symbol of the uplink transmission unit of the first CSI report, or the first symbol of the uplink transmission unit used to carry the first CSI report.

[0277] The first reference signal transmission occasion can correspond to the latest reference signal transmission occasion within the observation window corresponding to the first task, or it can be the latest time-domain unit (such as a slot or OFDM symbol) among the earliest reference signal transmission occasions within the observation window corresponding to the first task. The reference signal transmission occasion can correspond to the transmission time / opportunity of the reference signal, or the start time of reference signal transmission, or the reception time / opportunity of the reference signal, or the end time of reference signal transmission. The reference signal transmission occasion can be a CSI-RS transmission occasion.

[0278] The first part will be described below.

[0279] In one possible implementation, the first duration is a value pre-configured by the network or operator, or a value pre-defined by the protocol. For example, the first duration pre-configured by the network or operator or pre-defined by the protocol could be... Alternatively, it can be a predefined CSI duration #1, where CSI duration #1 is the minimum time interval between the CSI-RS used for CSI reporting and the CSI reporting time slot in non-AI mode. μ DL This indicates the value corresponding to the downlink subcarrier spacing. For example, 0 represents a 15kHz subcarrier spacing, 1 represents a 30kHz subcarrier spacing, 2 represents a 60kHz subcarrier spacing, and 3 represents a 120kHz subcarrier spacing.

[0280] In other words, in this implementation, network devices and / or terminal devices can determine the first duration based on information pre-configured by the network or operator or information pre-defined by the protocol.

[0281] Optionally, if the network or operator pre-configures multiple durations for the terminal device, or the protocol predefines multiple durations, the terminal device can select a first duration from the multiple durations pre-configured by the network or operator or pre-defined by the protocol, and indicate the first duration to the network device. For example, method 800 further includes: the terminal device sending indication information #a to the network device, the indication information #a indicating the first duration. For example, the indication information #a includes the first duration, or includes an index or identifier of the first duration, or includes the difference between the first duration and the predefined duration #a.

[0282] In one possible implementation, the first duration is associated with a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0283] In other words, in this implementation, the terminal device and / or network device can determine the first duration based on a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0284] For example, the network or operator pre-configures a correspondence #1 for the terminal device and / or network device, or the protocol predefines a correspondence #1, which includes the duration corresponding to different values ​​of the first inference parameter and / or different values ​​of the second inference parameter. Then, the terminal device and / or network device can determine the first duration based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, as well as the correspondence #1.

[0285] For example, an example of correspondence #1 is shown in Table 1 below.

[0286] Table 1

[0287] For example, if the network or operator pre-configures the values ​​of the first inference parameter and / or the values ​​of the second inference parameter with respect to the first duration (relationship #1), or if the protocol predefines the values ​​of the first inference parameter and / or the values ​​of the second inference parameter with respect to the first duration (relationship #1), then the terminal device and / or the network device can determine the first duration based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, and relation #1.

[0288] For example, an example of relation #1 is shown in formula (1). αK+βN1*N2+γN4=First duration formula (1).

[0289] Among them, one or more of α, β, and γ are coefficients pre-configured by the network or operator for the terminal device and / or network device, or coefficients pre-defined by the protocol, or coefficients indicated by the network device to the terminal device, or coefficients indicated by the terminal device to the network device.

[0290] It should be understood that the above formula (1) is merely an example and is not intended to limit the scope of this application. For example, relation #1 may also be associated with other first inference parameters and / or second inference parameters different from K, N1, N2, or N4. Furthermore, the "+" in the above formula may be replaced with "-" or other operators.

[0291] Optionally, in this implementation, the terminal device determines the first duration based on a first value of at least one first inference parameter and / or a second value of at least one second inference parameter, and indicates the first duration to the network device. For example, method 800 further includes: the terminal device sending indication information #b to the network device, the indication information #b indicating the first duration. For example, the indication information #b includes the first duration, or includes the difference between the first duration and a predefined duration #b.

[0292] In one possible implementation, the first duration is greater than or equal to the sum of the sixth and seventh durations.

[0293] In other words, in this implementation, the terminal device and / or network device can determine the first duration based on the sixth and seventh durations. For example, the first duration is equal to the sum of the sixth and seventh durations, or, for another example, the first duration is the sum of the sixth duration, the seventh duration, and a predefined duration #c.

[0294] The sixth duration corresponds to the execution duration of the first prediction task. The sixth duration corresponding to the execution duration of the first prediction task may include at least one of the following: the sixth duration is related to the execution duration of the first prediction task, the sixth duration is the execution duration of the first prediction task, or the sixth duration is greater than or equal to the execution duration of the first prediction task.

[0295] For example, the sixth duration is a predefined value. For instance, the sixth duration is a value pre-configured by the network or operator for the terminal device and / or network device, or a value pre-defined by the protocol. For example, the sixth duration pre-configured by the network or operator or pre-defined by the protocol could be... Or, the predefined CSI duration #1 for the protocol.

[0296] For example, the sixth duration is related to a first value of at least one first inference parameter. The relationship between the sixth duration and the first value of at least one first inference parameter can be referred to the relationship between the first duration and the first value of at least one first inference parameter and / or the second value of at least one second inference parameter described above.

[0297] The seventh duration corresponds to the duration of the first compression task. The seventh duration corresponding to the execution duration of the first compression task may include at least one of the following: the seventh duration is related to the execution duration of the first compression task, the seventh duration is the execution duration of the first compression task, or the seventh duration is greater than or equal to the execution duration of the first compression task.

[0298] For example, the seventh duration is a predefined value. For instance, the seventh duration might be a value pre-configured by the network or operator for the terminal device and / or network equipment, or a value pre-defined by the protocol. For example, the seventh duration pre-configured by the network or operator or pre-defined by the protocol could be... Or twice the predefined CSI duration #1 of the protocol.

[0299] For example, the seventh duration is related to a second value of at least one second inference parameter. The relationship between the seventh duration and the second value of at least one second inference parameter can be referenced to the relationship between the first duration and the first value of at least one first inference parameter and / or the second value of at least one second inference parameter described above.

[0300] Optionally, in this implementation, the terminal device determines the first duration based on the sixth and seventh durations and indicates the first duration to the network device. For example, method 800 further includes: the terminal device sending indication information #c to the network device, the indication information #c indicating the first duration. For example, the indication information #c includes the first duration, or includes the difference between the first duration and a predefined duration #b.

[0301] The following describes how terminal devices and network devices determine one or more of the following based on a first duration: first CSI duration, second CSI duration, and CSI reference resource #1 corresponding to the first CSI report.

[0302] In one possible implementation, if the first CSI report is an aperiodic CSI report, then in S820, the terminal device and the network device determine the first CSI duration and the second CSI duration based on the first duration.

[0303] For example, the terminal device and the network device determine the first CSI duration based on the first duration, including: the terminal device and the network device determine the first CSI duration based on the first duration and the duration of the first observation window corresponding to the first task. Optionally, the first observation window corresponding to the first task refers to the observation window corresponding to the first prediction task.

[0304] For example, the duration of the first observation window corresponds to the duration of the K observation resources included in the first observation window. The value of K is configured by the network and / or indicated by the capabilities of the terminal device.

[0305] Optionally, the first CSI duration is not less than the sum of the first duration, the duration of the first observation window, and the second duration predefined by the protocol. For example, the second duration is the minimum time interval #1 or minimum time interval #2 between the downlink channel used to trigger the CSI report and the CSI reporting time slot. Minimum time interval #1 corresponds to non-AI mode, and minimum time interval #2 corresponds to AI mode. Non-AI mode means that AI is not used during the CSI reporting process, while AI mode means that AI is used during the CSI reporting process.

[0306] For example, the second CSI duration determined by the terminal device and network device based on the first duration is not less than the sum of the first duration and the third duration predefined by the protocol. For example, the third duration is the minimum time interval #3 or minimum time interval #4 between the CSI-RS used for CSI reporting and the CSI reporting time slot, where minimum time interval #3 corresponds to the non-AI mode and minimum time interval #4 corresponds to the AI ​​mode.

[0307] Figure 9 shows an example of the first and second CSI durations. As shown in Figure 9, the minimum time interval #1 between the downlink channel used to trigger CSI reporting and the CSI reporting time slot in non-AI mode is denoted as Z, and the minimum time interval #3 between the CSI-RS used for CSI reporting and the CSI reporting time slot in non-AI mode is denoted as Z'. Then, the first CSI duration can be equal to Z + Z_b3 + Z_a3, and the second CSI duration can be equal to Z' + Z_a3. Here, Z_b3 is the duration of the first observation window, and Z_a3 is the first duration. For example, Z_a3 = Z_a1 + Z_a2, where Z_a1 represents the sixth duration and Z_a2 represents the seventh duration. For example, Z_a1 = 2Z', or Z_a1 = 14*(N4-1)*d, where N4 is the number of prediction instances included in the prediction window corresponding to the first prediction task, and d is the interval between two adjacent prediction instances. For example, Z_a2 = 2Z'. For example, Z_b3 = Z_b1, Z_b1 = 14*(K-1)*m, where K is the number of observation instances included in the observation window corresponding to the first prediction task, and m is the interval between two adjacent observation resources within the observation window corresponding to the first prediction task.

[0308] In one possible implementation, if the first CSI report is a periodic CSI report and a semi-persistent CSI report, then in S820, the terminal device and the network device determine the CSI reference resource #1 according to the first duration.

[0309] For example, the process of the terminal device and network device determining CSI reference resource #1 based on a first duration can be replaced by the process of the terminal device and network device determining the time domain resource corresponding to CSI reference resource #1 based on the first duration. In other words, CSI reference resource #1 can be replaced by the time domain resource corresponding to CSI reference resource #1, or by the time slot in which CSI reference resource #1 is located.

[0310] For example, the interval between CSI reference resource #1 and the start time of the transmission of the first CSI report is greater than or equal to the minimum of the fourth duration, which is the sum of the first duration and the fifth duration predefined by the protocol. For example, the fifth duration is the minimum time interval #5 or the minimum time interval #6 between the CSI reference resource and the CSI reporting time slot, where the minimum time interval #5 corresponds to the non-AI mode and the minimum time interval #6 corresponds to the AI ​​mode.

[0311] For example, if the reporting slot for the first CSI report is slot n', then in the time domain, CSI reference resource #1 is defined by a single downlink slot n-n_ref_a3, where... Indicates rounding down. μ DL and μ ULThese represent the values ​​corresponding to the downlink subcarrier spacing and the uplink subcarrier spacing, respectively. n_ref_a3 represents the first duration. In the frequency domain, CSI reference resource #1 is defined by the downlink physical resource block group corresponding to the frequency band involved in the CSI reported in the first CSI report.

[0312] Figure 10 shows an example of CSI reference resource #1. As shown in Figure 10, the minimum time interval #5 between the CSI reference resource and the CSI reporting time slot in non-AI mode is denoted as n_ref. Then, the interval between CSI reference resource #1 and the start time of the first CSI report transmission can be equal to n_ref + n_ref_a3. Here, n_ref_a3 is the first duration. For example, For example, n_ref_a3 = n_ref_a1 + n_ref_a2. Here, n_ref_a1 represents the sixth duration, for example... n_ref_a2 represents the seventh duration, for example,

[0313] It should be understood that when the terminal device and the network device determine one or more of the first CSI duration, the second CSI duration, and CSI reference resource #1, it is beneficial for the terminal device and the network device to align the CPU time period occupied by the first CSI report corresponding to the first task, and avoid resource waste or invalid reporting caused by misalignment of CPU time (i.e., the terminal device reports historical information that has not been updated due to insufficient CPU timeline occupancy).

[0314] For example, if the first CSI report is an aperiodic CSI report, the start time of the time period during which the first CSI report occupies the CPU is the start time of the first downlink channel, and the end time of the time period during which the first CSI report occupies the CPU is the end time of the transmission of the first CSI report.

[0315] Wherein, the start time of the first downlink channel can be replaced with the first symbol of the first downlink channel. The end time of the transmission of the first CSI report can be replaced with the end time of the uplink transmission unit (or uplink channel) of the first CSI report, or the last symbol of the uplink transmission unit of the first CSI report, or the last symbol of the uplink transmission unit used to carry the first CSI report.

[0316] As mentioned above, the first CSI duration corresponds to the interval between the end time of the first downlink channel and the start time of the transmission of the first CSI report. Therefore, when the terminal device and the network device determine the first CSI duration based on the first duration, the terminal device and the network device can align the CPU time period occupied by the first CSI report.

[0317] For example, if the first CSI report is a periodic CSI report or a semi-continuous CSI report, the start time of the CPU time period occupied by the first CSI report is the second reference signal transmission time, and the end time of the CPU time period occupied by the first CSI report is the transmission end time of the first CSI report.

[0318] The second reference signal transmission timing can correspond to the earliest reference signal transmission timing within the observation window corresponding to the first task, or it can be the earliest time-domain unit (such as slot or OFDM symbol) reference signal transmission timing within the earliest reference signal transmission timing within the observation window corresponding to the first task. For more details, please refer to the above.

[0319] The timing of the transmission of the reference signal corresponding to the first task is no later than CSI reference resource #1. Therefore, when the terminal device and the network device determine CSI reference resource #1 based on the first duration, the terminal device and the network device can align the CPU time period occupied by the first CSI report.

[0320] In this embodiment, by defining one or more of the first CSI duration, second CSI duration, and CSI reference resource #1 as related to the first duration, it is beneficial for the terminal device and the network device to determine the same first CSI duration, second CSI duration, or CSI reference resource #1. This facilitates the alignment of the CPU time period occupied by the first CSI report between the terminal device and the network device. When the terminal device and the network device align the CPU time period occupied by the first CSI report, it is beneficial for the network device to determine, based on the CPU usage of the terminal device at various times, whether any CSI reports submitted by the terminal device at a specific time have not been updated due to insufficient CPU resources. In other words, it helps the network device obtain accurate CSI reports.

[0321] For example, if the CPU resources are insufficient to update CSI report #a due to the first CSI report occupying CPU time, then the CSI report #a reported by the terminal device at time #a will be an outdated CSI report. However, because the terminal device and the network device are not aligned on the time period when the first CSI report occupied CPU time, the network device may determine that CSI report #a is an updated CSI report even if it is certain that the first CSI report did not occupy CPU time. This could lead the network device to determine an inaccurate communication strategy based on the outdated CSI report #a, thus affecting communication quality. If the terminal device and the network device are aligned on the time period when the first CSI report occupied CPU time, the network device can determine that the CSI report #a reported by the terminal device at time #a is an outdated CSI report, which allows the network device to determine a more accurate communication strategy based on the received CSI report.

[0322] The methods for aligning the CPU usage time periods of CSI reports between terminal devices and network devices, as described above with reference to Figures 8 to 10, are now described below with reference to Figure 11, which describes the methods for aligning the CPU usage count values ​​of CSI reports between terminal devices and network devices. It should be understood that the methods shown in Figure 11 and Figure 8 can be used independently or in combination, and this application does not limit their use in this regard.

[0323] Figure 11 is a schematic flowchart of a communication method 800 provided in an embodiment of this application. The steps of method 800 will be described in detail below.

[0324] S1110, terminal devices and network devices configure inference parameters.

[0325] S1110 can be referenced from S810 in method 800 above.

[0326] S1120, the terminal device sends the first instruction information.

[0327] Accordingly, the network device receives the first instruction information.

[0328] The first indication information is used to indicate the first weighting coefficient corresponding to the first quantity and / or the second weighting coefficient corresponding to the second quantity.

[0329] The first quantity refers to the number of CPUs required to execute the first prediction task, and the second quantity refers to the number of CPUs required to execute the first compression task. The first prediction task and the first compression task can be referred to the description in Method 800 above.

[0330] The first data, the second quantity, the first weighting coefficient, and the second weighting coefficient are used to determine the CPU count value occupied by the first CSI report. The first CSI report corresponds to the first task, which can be referred to the description in method 800 above. The method for determining the first quantity and the second quantity can be referred to the description in S1140 below.

[0331] The first weighting coefficient and / or the second weighting coefficient are described below.

[0332] For example, the first weighting coefficient and / or the second weighting coefficient are weighting coefficients pre-configured by the network or operator, or weighting coefficients pre-defined by the protocol.

[0333] For example, if the network or operator pre-configures multiple weighting coefficients for the terminal device, or the protocol pre-defines multiple weighting coefficients, the terminal device can select a first weighting coefficient and / or a second weighting coefficient from the multiple weighting coefficients pre-configured by the network or operator or pre-defined by the protocol, and indicate the first weighting coefficient and / or the second weighting coefficient to the network device.

[0334] In one possible implementation, the first weighting coefficient and / or the second weighting coefficient are associated with a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0335] In other words, in this implementation, the terminal device can determine the first weighting coefficient and / or the second weighting coefficient based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, and indicate the first weighting coefficient and / or the second weighting coefficient to the network device.

[0336] For example, the network or operator pre-configures a correspondence #2 for the terminal device, or the protocol predefines a correspondence #2. The correspondence #2 includes the values ​​of the first weighting coefficient and / or the second weighting coefficient corresponding to different values ​​of the first inference parameter and / or different values ​​of the second inference parameter. Then, the terminal device can determine the first weighting coefficient and / or the second weighting coefficient based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, as well as the correspondence #2.

[0337] For example, an example of correspondence #2 is shown in Table 2 below. The first weighting coefficient is denoted as K1, and the second weighting coefficient is denoted as K2.

[0338] Table 2

[0339] For example, if the network or operator pre-configures the values ​​of the first inference parameter and / or the second inference parameter for the terminal device and the relationship #2 that the first weighting coefficient and / or the second weighting coefficient must satisfy, or if the protocol pre-defines the relationship #2 that the values ​​of the first inference parameter and / or the second inference parameter must satisfy, the terminal device can determine the first weighting coefficient and / or the second weighting coefficient based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, and the relationship #2.

[0340] For example, an example of relation #2 is shown in formulas (2-1) and (2-2). α1K+β1N1*N2+γ1N4=first weighting coefficient formula (2-1); α2K+β2N1*N2+γ2N4=second weighting coefficient formula (2-2).

[0341] Among them, one or more of α1, β1, γ1, α2, β2 or γ2 are coefficients pre-configured by the network or operator for the terminal device, or coefficients pre-defined by the protocol, or coefficients indicated by the network device to the terminal device, or coefficients indicated by the terminal device to the network device.

[0342] It should be understood that formulas (2-1) and (2-2) above are merely examples, and this application does not limit them. For example, relation #2 may also be related to other first inference parameters and / or second inference parameters different from K, N1, N2, or N4. Furthermore, the "+" in the above formulas may be replaced with "-" or other operators, etc.

[0343] Optionally, in one possible implementation, in S1120, the network device determines the first weighting coefficient and / or the second weighting coefficient, and indicates the first weighting coefficient and / or the second weighting coefficient to the terminal device. In other words, in S1120, the network device sends first indication information to the terminal device. The method by which the network device determines the first weighting coefficient and / or the second weighting coefficient can refer to the method described above for the terminal device to determine the first weighting coefficient and / or the second weighting coefficient.

[0344] It should be noted that S1120 is an optional step. For example, if the terminal device and / or network device determine the CPU usage count of the first CSI report based on other methods, or if the first weighting coefficient and / or the second weighting coefficient are values ​​pre-configured by the network or operator for the terminal device and network device, or are predefined values ​​by the protocol, then method 1100 may not execute S1120.

[0345] S1130, the terminal device sends the second instruction information.

[0346] Correspondingly, the network device receives the second instruction information.

[0347] The second instruction indicates the first moment.

[0348] For example, the second indication information includes the first moment, or the second indication information includes at least one of the eighth duration, the ninth duration, or the sixth duration.

[0349] The eighth duration is used to determine the first moment. For example, the first moment is before CSI reference resource #1, and the interval between the first moment and CSI reference resource #1 is the eighth duration. CSI reference resource #1 corresponds to the first CSI report, and the method for determining CSI reference resource #1 can be referred to the description in S820 above.

[0350] The ninth duration is used to determine the first time point. For example, the first time point is after the first reference signal transmission opportunity, and the interval between the first reference signal transmission opportunity and the first time point is the ninth duration. The ninth duration is related to the sixth duration; for example, the ninth duration is greater than or equal to the sixth duration. The sixth duration corresponds to the execution duration of the first prediction task. The first reference signal transmission opportunity can be referred to the description in S820 above.

[0351] In one possible implementation, in S1130, the network device indicates the first moment to the terminal device. In other words, in S1130, the network device sends second indication information to the terminal device.

[0352] It should be noted that S1130 is an optional step. For example, if the first moment is the moment when the network or operator pre-configures the terminal device and / or network device, or if the first moment is the moment when the protocol is predefined, then method 1100 may not execute S1130.

[0353] S1140, the terminal equipment and network equipment determine the CPU count value used by the first CSI report.

[0354] For example, the terminal device and / or network device determine the CPU count value occupied by the first CSI report based on one or more of the following: a first quantity, a second quantity, a first value of at least one first inference parameter, and a second value of at least one second inference parameter.

[0355] A first value of at least one first inference parameter is used for the first AI-based prediction task, and a second value of at least one second inference parameter is used for the first AI-based compression task. For further description of the first and second inference parameters, please refer to Method 800 above.

[0356] The following describes how terminal devices and network devices determine the CPU count value used by the first CSI report.

[0357] In Implementation Method 1, during the time period when the first CSI report occupies CPU, the count value of the first CSI report occupying CPU is determined based on any of the following methods.

[0358] Method 1: The CPU usage count in the first CSI report is the maximum of the first and second counts. For example, the first count is recorded as 0. CPU-p The second quantity is denoted as O. CPU-c The CPU usage count in the first CSI report is recorded as 0. CPU-SPC Then O CPU-p O CPU-c With O CPU- SPC Satisfy: O CPU-SPC =max{O CPU-p O CPU-c}

[0359] Method 2: The CPU usage count in the first CSI report is a weighted sum of a first count and a second count. For example, the first count is denoted as 0. CPU-p The second quantity is denoted as O. CPU-c The CPU usage count in the first CSI report is recorded as 0. CPU-SPCThen O CPU-p O CPU-c With O CPU- SPC Satisfy: O CPU-SPC =K1*O CPU-p +K2*O CPU-c Where K1 represents the first weighting coefficient and K2 represents the second weighting coefficient. Further descriptions of the first and second weighting coefficients can be found in section S1120 above.

[0360] Method 3: The CPU count value reported by the first CSI is associated with a first value of at least one first inference parameter and / or a second value of at least one second inference parameter.

[0361] In other words, in this method 3, the terminal device and / or network device can determine the CPU count value occupied by the first CSI report based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter.

[0362] For example, the network or operator pre-configures a correspondence #3 for the terminal device and / or network device, or the protocol predefines a correspondence #3, which includes CPU count values ​​corresponding to different values ​​of the first inference parameter and / or different values ​​of the second inference parameter. Then, the terminal device and / or network device can determine the CPU count value occupied by the first CSI report based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, as well as the correspondence #3.

[0363] For example, an example of correspondence #3 is shown in Table 3 below.

[0364] Table 3

[0365] Optionally, the terminal device may report the above correspondence #3 to the network device, so that the network device can determine the CPU count value occupied by the first CSI report based on the above correspondence #3.

[0366] For example, if the network or operator pre-configures the values ​​of the first inference parameter and / or the second inference parameter for the terminal device and / or network device and the CPU count value to satisfy relationship #3, or if the protocol predefines the values ​​of the first inference parameter and / or the second inference parameter and the CPU count value to satisfy relationship #3, then the terminal device and / or network device can determine the CPU count value occupied by the first CSI report based on the first value of at least one first inference parameter and / or the second value of at least one second inference parameter, and relationship #3.

[0367] For example, an example of relation #3 is shown in formula (3). α3K+β3N1*N2+γ3N4=CPU count value formula (3).

[0368] Among them, one or more of α3, β3 or γ3 are coefficients pre-configured by the network or operator for the terminal device and / or network device, or coefficients pre-defined by the protocol, or coefficients indicated by the network device to the terminal device, or coefficients indicated by the terminal device to the network device.

[0369] It should be understood that the above formula (3) is merely an example and is not intended to limit the scope of this application. For example, relation #3 may also be associated with other first inference parameters and / or second inference parameters different from K, N1, N2, or N4. Furthermore, the "+" in the above formula may be replaced with "-" or other operators.

[0370] In implementation method 2, from the start of the time period during which the first CSI report occupies CPU to the first time point, the count value of the CPU occupied by the first CSI report is a first quantity; from the first time point to the end of the time period during which the first CSI report occupies CPU, the count value of the CPU occupied by the first CSI report is a second quantity. The first time point can be referred to the description in S1130 above.

[0371] The first quantity is described below.

[0372] For example, the first quantity is the CPU count value pre-configured by the network or operator for the prediction task (or AI-based prediction task), or the CPU count value pre-defined by the protocol for the prediction task (or AI-based prediction task).

[0373] Optionally, if the network or operator pre-configures multiple CPU count values ​​corresponding to the prediction task for the terminal device, or the protocol pre-defines multiple CPU count values ​​corresponding to the prediction task, the terminal device can select a first number from the multiple CPU count values ​​pre-configured by the network or operator or pre-defined by the protocol, and indicate the first number to the network device.

[0374] For example, the first quantity is associated with a first value of at least one first inference parameter.

[0375] For example, the network or operator pre-configures a correspondence #4 for the terminal device and / or network device, or the protocol predefines a correspondence #4, which includes CPU count values ​​corresponding to different values ​​of the first inference parameter. Then, the terminal device and / or network device can determine the first quantity based on the first value of at least one first inference parameter and the correspondence #4.

[0376] For example, if the network or operator pre-configures the value of the first inference parameter and the relationship #4 that the first quantity must satisfy for the terminal device and / or network device, or if the protocol pre-defines the relationship #4 between the value of the first inference parameter and the first quantity, then the terminal device and / or network device can determine the first quantity based on the first value of at least one first inference parameter and the relationship #4.

[0377] For example, one example of relation #4 is shown in formula (4-1), formula (4-2), or formula (4-3). For instance, if the first CSI report is an aperiodic CSI report, the terminal device and / or network device can determine the first quantity according to formula (4-1) below. As another example, if the first CSI report is a periodic or semi-persistent CSI report, the terminal device and / or network device can determine the first quantity according to formula (4-2) below. CPU-p =Y1*K Formula (4-1); O CPU-p =max{Y2*N4,4} Formula (4-2); O CPU-p =α4K+γ4N4 Formula (4-3).

[0378] Among them, one or more of Y1, Y2, α4 or γ4 are coefficients pre-configured by the network or operator for the terminal device, or coefficients pre-defined by the protocol, or coefficients indicated by the network device to the terminal device, or coefficients indicated by the terminal device to the network device.

[0379] Optionally, the value of one or more coefficients among Y1, Y2, α4 or γ4 mentioned above is related to the first value of at least one first inference parameter.

[0380] It should be understood that formulas (4-1) to (4-3) above are merely examples, and this application does not limit them. For example, relation #4 may also be related to other first inference parameters different from K or N4. Furthermore, the "+" in the above formulas may be replaced with "-" or other operators, etc.

[0381] The second quantity is described below.

[0382] For example, the second quantity is a CPU count value pre-configured by the network or operator for the compression task (or an AI-based compression task), or a CPU count value pre-defined by the protocol for the compression task (or an AI-based compression task).

[0383] Optionally, if the network or operator pre-configures multiple CPU count values ​​corresponding to the compression task for the terminal device, or the protocol pre-defines multiple CPU count values ​​corresponding to the compression task, the terminal device can select a second number from the multiple CPU count values ​​pre-configured by the network or operator or pre-defined by the protocol, and indicate the second number to the network device.

[0384] For example, the second quantity is associated with a second value of at least one second inference parameter.

[0385] For example, if the network or operator pre-configures a correspondence #5 for the terminal device and / or network device, or if the protocol predefines a correspondence #5, and the correspondence #5 includes CPU count values ​​corresponding to different values ​​of the second inference parameter, then the terminal device and / or network device can determine the second quantity based on the second value of at least one second inference parameter and the correspondence #5.

[0386] Optionally, correspondence #2 includes the CPU count value corresponding to the model ID of different CSI compressions.

[0387] For example, if the network or operator pre-configures the value of the second inference parameter and the relationship #5 that the second quantity must satisfy for the terminal device and / or network device, or if the protocol predefines the relationship #5 between the value of the second inference parameter and the second quantity, then the terminal device and / or network device can determine the second quantity based on the second value of at least one second inference parameter and the relationship #5.

[0388] An example of relation #5 is shown in equation (5). CPU-c =α5N1*N2+γ5N3+β5CSI payload size formula (5).

[0389] Among them, one or more of α5, β5 or γ5 are coefficients pre-configured by the network or operator for the terminal device, or coefficients pre-defined by the protocol, or coefficients indicated by the network device to the terminal device, or coefficients indicated by the terminal device to the network device.

[0390] Optionally, the value of one or more of the coefficients α5, β5 or γ5 mentioned above is related to the second value of at least one second inference parameter.

[0391] It should be understood that the above formula (5) is merely an example and is not intended to limit the scope of this application. For example, relation #5 may also be associated with other second inference parameters different from N1, N2, or N3. Furthermore, the "+" in the above formula may be replaced with "-" or other operators.

[0392] For example, Figure 12 illustrates the CPU usage pattern of the first CSI report. As shown in Figure 12(a), based on the above implementation method 1, the CPU usage count of the first CSI report is always 0 during the time period when the first CSI report occupies the CPU. CPU-SPC As shown in Figure 12(b), based on the above implementation method 1, from the start time of the first CSI report's CPU usage period to the first time, the count value of the first CSI report's CPU usage is 0. CPU-p During the period from the first moment to the end of the time period in which the first CSI report occupied CPU, the CPU usage count of the first CSI report was 0. CPU-c .

[0393] In one possible implementation, in S1140, the terminal device determines the CPU count value occupied by the first CSI report and indicates the CPU count value occupied by the first CSI report to the network device.

[0394] For example, method 1100 further includes: the terminal device sending an indication message #d to the network device, the indication message #d indicating the count value of CPU usage reported by the first CSI.

[0395] Optionally, the indication information #d indicates the parameter used to determine the CPU count value occupied by the first CSI report. The indication information #1 indicates the corresponding relationship #3 described above, or indicates the coefficient corresponding to formula (3), formula (4-1), formula (4-2), formula (4-3) or formula (5) described above.

[0396] In this embodiment, defining the method for determining the CPU usage count of the first CSI report facilitates the alignment of the CPU usage count between the terminal device and the network device. When the terminal device and network device align the CPU usage count of the first CSI report, the network device can determine whether any CSI reports submitted by the terminal device at a specific time were not updated due to insufficient CPU resources, based on the terminal device's CPU usage at various times. In other words, this helps the network device obtain accurate CSI reports.

[0397] The method for determining the CPU usage pattern corresponding to the first prediction task or the first compression task is described below with reference to Figure 13.

[0398] Figure 13 is a schematic flowchart of a communication method 1300 provided in an embodiment of this application. The steps of method 1300 will be described in detail below.

[0399] S1310, the terminal device and network device configure inference parameters.

[0400] Unlike S810 and S1110, if the terminal device performs the reporting of a second CSI report, which corresponds to the first prediction task, then in S1310, the terminal device and the network device configure the first inference parameters. If the terminal device performs the reporting of a third CSI report, which corresponds to the first compression task, then in S1310, the terminal device and the network device configure the second inference parameters.

[0401] For a more detailed description of the first prediction task, the first compression task, the first inference parameter, and the second inference parameter, please refer to S810 above. For a more detailed description of S1310, please refer to Method 1800 below.

[0402] Furthermore, if the terminal device performs the reporting of a second CSI report, then method 1300 executes S1320a. If the terminal device performs the reporting of a third CSI report, then method 1300 executes S1320b.

[0403] S1320a, the terminal equipment and network equipment determine one or more of the following based on the sixth duration: the third CSI duration, the fourth CSI duration, and the CSI reference resource #2 corresponding to the second CSI report.

[0404] The sixth duration corresponds to the execution duration of the first prediction task. Further details about the sixth duration can be found in Method 800 above.

[0405] The third CSI duration corresponds to the interval between the end time of the second downlink channel and the start time of the transmission of the second CSI report.

[0406] The fourth CSI duration corresponds to the interval between the timing of the third reference signal transmission and the start time of the second CSI report transmission.

[0407] The timing of the transmission of the second downlink channel, the second CSI report, and the third reference signal corresponds to the first prediction task.

[0408] For example, the second downlink channel is used to trigger a second CSI report, or to trigger a second CSI report carrying data related to the first prediction task.

[0409] The third reference signal transmission timing is the latest reference signal transmission timing within the observation window corresponding to the first prediction task, or, the latest time-domain unit (such as a slot or OFDM symbol) within the latest reference signal transmission timing within the observation window corresponding to the first prediction task. Further description of the reference signal transmission timing can be found in Method 800 above.

[0410] For a more detailed description of the end time of the second downlink channel, please refer to the description of the end time of the first downlink channel in S820 above. For a more detailed description of the start time of the transmission of the second CSI report, please refer to the description of the start time of the transmission of the first CSI report in S820 above.

[0411] The following describes how terminal devices and network devices determine one or more of the following based on the sixth duration: the third CSI duration, the fourth CSI duration, and the CSI reference resource #2 corresponding to the second CSI report.

[0412] In one possible implementation, if the second CSI report is an aperiodic CSI report, then in S1320a, the terminal device and the network device determine the third CSI duration and the fourth CSI duration based on the sixth duration.

[0413] For example, the terminal device and the network device determine the third CSI duration based on the sixth duration, including: the terminal device and the network device determine the third CSI duration based on the sixth duration and the duration of the second observation window corresponding to the first prediction task.

[0414] For example, the duration of the second observation window corresponds to the duration of the K observation resources included in the second observation window. The value of K is configured by the network and / or indicated by the capabilities of the terminal device.

[0415] Optionally, the duration of the third CSI shall not be less than the sum of the sixth duration, the duration of the second observation window, and the second duration predefined in the protocol. The second duration can be referred to the description in S820 above.

[0416] For example, the fourth CSI duration determined by the terminal device and the network device based on the sixth duration is not less than the sum of the sixth duration and the third duration predefined by the protocol. The third duration can be referred to the description in S820 above.

[0417] Figure 14 shows an example of the durations of the third and fourth CSIs. As shown in Figure 14, the minimum time interval #1 between the downlink channel used to trigger CSI reporting and the CSI reporting slot in non-AI mode is denoted as Z, and the minimum time interval #3 between the CSI-RS used for CSI reporting and the CSI reporting slot in non-AI mode is denoted as Z'. Then, the duration of the third CSI can be equal to Z + Z_b1 + Z_a1, and the duration of the fourth CSI can be equal to Z' + Z_a1. Where Z_b1 is the duration of the second observation window, and Z_a1 is the sixth duration. For example, Z_b1 = 14*(K-1)*m, where K is the number of observation instances included in the observation window corresponding to the first prediction task, and m is the interval between two adjacent observation resources within the observation window corresponding to the first prediction task. Z_a1 = 2Z', or Z_a1 = 14*(N4-1)*d, where N4 is the number of prediction instances included in the prediction window corresponding to the first prediction task, and d is the interval between two adjacent prediction instances.

[0418] In one possible implementation, if the second CSI report is a periodic CSI report and a semi-persistent CSI report, then in S1320a, the terminal device and the network device determine the CSI reference resource #2 according to the sixth duration.

[0419] For example, the terminal device and network device determining CSI reference resource #2 based on the sixth duration can be replaced by: the terminal device and network device determining the time domain resource corresponding to CSI reference resource #2 based on the sixth duration. In other words, CSI reference resource #2 can be replaced by the time domain resource corresponding to CSI reference resource #2, or it can be replaced by the time slot where CSI reference resource #2 is located.

[0420] For example, the interval between CSI reference resource #2 and the start time of transmission of the second CSI report is greater than or equal to the minimum of the fourth duration #a, where the fourth duration #a is the sum of the sixth duration and the fifth duration predefined by the protocol. The fifth duration can be referred to the description in S820 above.

[0421] For example, if the reporting slot for the second CSI report is slot n', then in the time domain, CSI reference resource #2 is defined by a single downlink slot n_n_ref_a1, where n_n_ref_a1 represents the sixth duration. In the frequency domain, CSI reference resource #2 is defined by a group of downlink physical resource blocks corresponding to the frequency band involved in the CSI of the second CSI report.

[0422] Figure 15 shows an example of CSI reference resource #2. As shown in Figure 15, the minimum time interval #5 between the CSI reference resource and the CSI reporting time slot in non-AI mode is denoted as n_ref. Then, the interval between CSI reference resource #2 and the start time of the second CSI report transmission can be equal to n_ref + n_ref_a1. Here, n_ref_a1 is the sixth duration. For example, It should be understood that when the terminal device and network device determine one or more of the third CSI duration, the fourth CSI duration, and CSI reference resource #2, it is beneficial for the terminal device and network device to align the CPU time period occupied by the second CSI report corresponding to the first prediction task.

[0423] For example, if the second CSI report is an aperiodic CSI report, the start time of the time period during which the second CSI report occupies the CPU is the start time of the second downlink channel, and the end time of the time period during which the second CSI report occupies the CPU is the end time of the transmission of the second CSI report.

[0424] As mentioned above, the third CSI duration corresponds to the interval between the end time of the second downlink channel and the start time of the transmission of the second CSI report. Therefore, when the terminal device and the network device determine the third CSI duration based on the sixth duration, the terminal device and the network device can align the CPU time period occupied by the second CSI report.

[0425] For example, if the second CSI report is a periodic CSI report or a semi-continuous CSI report, the start time of the CPU time period occupied by the second CSI report is the fourth reference signal transmission time, and the end time of the CPU time period occupied by the second CSI report is the transmission end time of the second CSI report.

[0426] The fourth reference signal transmission timing can correspond to the earliest reference signal transmission timing within the observation window corresponding to the first prediction task, or it can be the earliest time-domain unit (such as a slot or OFDM symbol) among the earliest reference signal transmission timings within the observation window corresponding to the first prediction task. Further description of the reference signal transmission timing can be found in Method 800 above.

[0427] The timing of the transmission of the reference signal corresponding to the first prediction task is no later than CSI reference resource #2. Therefore, when the terminal device and the network device determine CSI reference resource #2 based on the sixth duration, the terminal device and the network device can align the CPU time period occupied by the second CSI report.

[0428] S1320b, terminal equipment and network equipment determine one or more of the following based on the seventh duration: the fifth CSI duration, the sixth CSI duration, and CSI reference resource #3 corresponding to the third CSI report.

[0429] The seventh duration corresponds to the execution duration of the first compression task. For more details on the seventh duration, please refer to Method 800 above.

[0430] The duration of the fifth CSI corresponds to the interval between the end time of the third downlink channel and the start time of the transmission of the third CSI report.

[0431] The duration of the sixth CSI corresponds to the interval between the timing of the fifth reference signal transmission and the start time of the transmission of the third CSI report.

[0432] The timing of the transmission of the third downlink channel, the third CSI report, and the fifth reference signal corresponds to the first compression task.

[0433] For example, the third downlink channel is used to trigger a third CSI report, or to trigger a third CSI report carrying data related to the first compression task.

[0434] The fifth reference signal transmission timing is the latest reference signal transmission timing within the observation window corresponding to the first compression task, or, the latest time-domain unit (such as a slot or OFDM symbol) within the latest reference signal transmission timing within the observation window corresponding to the first compression task. Further description of the reference signal transmission timing can be found in Method 800 above.

[0435] For a more detailed description of the end time of the third downlink channel, please refer to the description of the end time of the first downlink channel in S820 above. For a more detailed description of the start time of the transmission of the third CSI report, please refer to the description of the start time of the transmission of the first CSI report in S820 above.

[0436] In this embodiment, by defining one or more of the third CSI duration, fourth CSI duration, and CSI reference resource #2 as related to the sixth duration, it is beneficial for the terminal device and the network device to determine the same third CSI duration, fourth CSI duration, or CSI reference resource #2. This facilitates the alignment of the CPU usage time of the second CSI report between the terminal device and the network device. When the terminal device and the network device align the CPU usage time of the second CSI report, it is beneficial for the network device to determine whether any CSI reports submitted by the terminal device at a specific time have not been updated due to insufficient CPU resources, based on the CPU usage of the terminal device at various times. In other words, it helps the network device obtain accurate CSI reports.

[0437] The following describes how terminal devices and network devices determine one or more of the following based on the seventh duration: the fifth CSI duration, the sixth CSI duration, and the CSI reference resource #3 corresponding to the third CSI report.

[0438] In one possible implementation, if the third CSI report is an aperiodic CSI report, then in S1320b, the terminal device and the network device determine the duration of the fifth CSI and the duration of the sixth CSI based on the seventh duration.

[0439] For example, the fifth CSI duration determined by the terminal device and the network device based on the seventh duration is not less than the sum of the seventh duration and the second duration predefined by the protocol. The second duration can be referred to the description in S820 above.

[0440] For example, the terminal device and network device determining CSI reference resource #3 based on the seventh duration can be replaced by: the terminal device and network device determining the time domain resource corresponding to CSI reference resource #3 based on the seventh duration. In other words, CSI reference resource #3 can be replaced by the time domain resource corresponding to CSI reference resource #3, or it can be replaced by the time slot where CSI reference resource #3 is located.

[0441] For example, the sixth CSI duration determined by the terminal device and the network device based on the seventh duration is not less than the sum of the seventh duration and the third duration predefined by the protocol. The third duration can be referred to the description in S820 above.

[0442] For example, if the reporting slot for the third CSI report is slot n', then in the time domain, CSI reference resource #3 is defined by a single downlink slot n-n_ref_a2, where n-n_ref_a2 represents the seventh duration. In the frequency domain, CSI reference resource #3 is defined by a group of downlink physical resource blocks corresponding to the frequency band involved in the CSI report of the third CSI.

[0443] Figure 16 shows an example of the durations of the fifth and sixth CSIs. As shown in Figure 16, the minimum time interval #1 between the downlink channel used to trigger CSI reporting and the CSI reporting slot in non-AI mode is denoted as Z, and the minimum time interval #3 between the CSI-RS used for CSI reporting and the CSI reporting slot in non-AI mode is denoted as Z'. Therefore, the duration of the fifth CSI can be equal to Z + Z_a2, and the duration of the sixth CSI can be equal to Z' + Z_a2. Here, Z_a2 is the seventh duration. For example, Z_a2 = 2Z'.

[0444] In one possible implementation, if the third CSI report is a periodic CSI report or a semi-persistent CSI report, then in S1320b, the terminal device and the network device determine the CSI reference resource #3 according to the seventh duration.

[0445] For example, the interval between CSI reference resource #3 and the start time of transmission of the third CSI report is greater than or equal to the minimum of the fourth duration #b, where the fourth duration #b is the sum of the seventh duration and the fifth duration predefined by the protocol. The fifth duration can be referred to the description in S820 above.

[0446] Figure 17 shows an example of CSI reference resource #3. As shown in Figure 17, the minimum time interval #5 between the CSI reference resource and the CSI reporting time slot in non-AI mode is denoted as n_ref. Then, the interval between CSI reference resource #3 and the start time of the transmission of the third CSI report can be equal to n_ref + n_ref_a2. Here, n_ref_a2 is the seventh duration. For example,

[0447] It should be understood that when the terminal device and network device determine one or more of the fifth CSI duration, the sixth CSI duration, and CSI reference resource #3, it is beneficial for the terminal device and network device to align the CPU time period occupied by the third CSI report corresponding to the first compression task.

[0448] For example, if the third CSI report is an aperiodic CSI report, the start time of the CPU time period occupied by the third CSI report is the start time of the third downlink channel, and the end time of the CPU time period occupied by the third CSI report is the end time of the transmission of the third CSI report.

[0449] As mentioned above, the fifth CSI duration corresponds to the interval between the end time of the third downlink channel and the start time of the transmission of the third CSI report. Therefore, when the terminal device and the network device determine the fifth CSI duration based on the seventh duration, the terminal device and the network device can align the CPU time period occupied by the third CSI report.

[0450] For example, if the third CSI report is a periodic CSI report or a semi-continuous CSI report, the start time of the CPU time period occupied by the third CSI report is the sixth reference signal transmission time, and the end time of the CPU time period occupied by the third CSI report is the transmission end time of the third CSI report.

[0451] The sixth reference signal transmission timing can correspond to the earliest reference signal transmission timing within the observation window corresponding to the first compression task, or it can be the earliest time-domain unit (such as a slot or OFDM symbol) among the earliest reference signal transmission timings within the observation window corresponding to the first compression task. Further description of the reference signal transmission timing can be found in Method 800 above.

[0452] The timing of the transmission of the reference signal corresponding to the first compression task is no later than CSI reference resource #3. Therefore, when the terminal device and the network device determine CSI reference resource #3 based on the seventh duration, the terminal device and the network device can align the CPU time period occupied by the third CSI report.

[0453] In this embodiment, by defining one or more of the fifth CSI duration, sixth CSI duration, and CSI reference resource #3 as related to the seventh duration, it is beneficial for the terminal device and the network device to determine the same fifth CSI duration, sixth CSI duration, or CSI reference resource #3. This facilitates the alignment of the CPU usage time of the third CSI report between the terminal device and the network device. When the terminal device and the network device align the CPU usage time of the third CSI report, it is beneficial for the network device to determine whether any CSI reports submitted by the terminal device at a specific time have not been updated due to insufficient CPU resources, based on the CPU usage of the terminal device at various times. In other words, it helps the network device obtain accurate CSI reports.

[0454] The following description, in conjunction with Figure 18, illustrates the method for configuring inference parameters for terminal devices and network devices. The method shown in Figure 18 can be used in conjunction with any of the methods described above, or used alone; this application does not limit its use in this regard.

[0455] Figure 18 is a schematic flowchart of a communication method 1800 provided in an embodiment of this application. The steps of method 1800 will be described in detail below.

[0456] S1810, the network device sends the fourth message.

[0457] Correspondingly, the terminal device receives the fourth piece of information.

[0458] The fourth piece of information is used to request the terminal device to support values ​​for inference parameters used for prediction tasks, and / or to request the terminal device to support values ​​for inference parameters used for compression tasks.

[0459] Optionally, the fourth information is used to request the maximum value of the inference parameters for the prediction task supported by the terminal device, and / or to request the maximum value of the inference parameters for the compression task supported by the terminal device.

[0460] Optionally, the fourth information is used to request inference parameters for the second task supported by the terminal device. The second task includes a prediction task and a compression task, and the inference parameters for the second task include inference parameters for the prediction task and inference parameters for the compression task. The second task includes the first task in method 800 above.

[0461] The inference parameters used for the prediction task can be denoted as at least one first inference parameter, and the inference parameters used for the compression task can be denoted as at least one second inference parameter. Further descriptions of the at least one first inference parameter and the at least one second inference parameter can be found in Method 800 above.

[0462] For example, the fourth piece of information is carried in the UE Capability Enquiry message.

[0463] It should be noted that step S1810 is optional. For example, if the values ​​of the inference parameters for the prediction task and / or the inference parameters for the compression task supported by the terminal device are pre-configured by the network or operator, or pre-defined by the protocol, then method 1800 may not execute S1810. Alternatively, if the terminal device can proactively report the values ​​of the inference parameters for the prediction task and / or the inference parameters for the compression task supported by the terminal device to the network device, then method 1800 may not execute S1810.

[0464] S1820, the terminal device sends the fifth message.

[0465] Correspondingly, the network device receives the fifth piece of information.

[0466] The fifth piece of information includes the values ​​of inference parameters supported by the terminal device for the prediction task, and / or the values ​​of inference parameters supported by the terminal device for the compression task.

[0467] Optionally, the fifth piece of information includes the maximum value of the inference parameters supported by the terminal device for the prediction task, and / or the maximum value of the inference parameters supported by the terminal device for the compression task.

[0468] Optionally, the fifth piece of information includes inference parameters supported by the terminal device for the second task. The second task includes a prediction task and a compression task, and the inference parameters for the second task include inference parameters for the prediction task and inference parameters for the compression task.

[0469] For example, the values ​​of the inference parameters used for the prediction task included in the second task may differ from the values ​​of the inference parameters used for the separate prediction task. For instance, the maximum value of K for the number of observation instances K included in the observation window is 4, while the maximum value of K for the separate prediction task is 6.

[0470] For example, the values ​​of the inference parameters used for the compression task included in the second task may differ from the values ​​of the inference parameters used for the compression task alone. For instance, the maximum value of N1*N2 for the number of CSI-RS ports N1*N2 in the dimension of the input data corresponding to the compression task is 8 for the second task, while the maximum value of N1*N2 for the compression task alone is 16.

[0471] Optionally, if the values ​​of the inference parameters used for the second task, including the prediction task, may differ from the values ​​of the inference parameters used for the separate prediction task, the fifth information may include the values ​​of the inference parameters used for the second task supported by the terminal device.

[0472] Optionally, if the values ​​of the inference parameters for the included compression task used for the second task may differ from the values ​​of the inference parameters used for the separate compression task, the fifth information may include the values ​​of the inference parameters for the second task supported by the terminal device.

[0473] In other words, if the values ​​of the inference parameters used for a single prediction task cannot be arbitrarily combined with the values ​​of the inference parameters used for a single compression task for the second task, the fifth information may include the values ​​of the inference parameters used for the second task supported by the terminal device.

[0474] For example, the values ​​of inference parameters supported by the terminal device for the prediction task can be referred to as the supported prediction feature. The values ​​of inference parameters supported by the terminal device for the compression task can be referred to as the supported compression model / feature. The values ​​of inference parameters supported by the terminal device for the second task can be referred to as the supported CSIPC model / feature. Here, PC represents prediction + compression.

[0475] For example, the fifth piece of information can be carried in the UE Capability Information.

[0476] It should be noted that S1820 is an optional step. For example, if the values ​​of the inference parameters for the prediction task and / or the inference parameters for the compression task supported by the terminal device are pre-configured by the network or operator, or pre-defined by the protocol, then method 1800 may not execute S1820.

[0477] S1830, the network device sends the first message.

[0478] Accordingly, the terminal device receives the first information.

[0479] The first information includes at least one third value for each of the first inference parameters, and / or includes at least one fourth value for each of the second inference parameters.

[0480] For example, after receiving the fifth information from the terminal device, the network device can send the first information to the terminal device based on the fifth information.

[0481] For example, at least one third value of each first inference parameter included in the first information does not exceed the maximum value of the first inference parameter supported by the terminal device. For instance, for the number K of observation instances included in the observation window, if the fifth information includes the maximum value of K, and the maximum value of K is 4, then any third value of at least one third value of K included in the first information does not exceed 4.

[0482] For example, in the first information, at least one fourth value of each of the at least one second inference parameter does not exceed the maximum value of the second inference parameter supported by the terminal device. For instance, for the number of CSI-RS ports N1*N2 in the dimension of the input data corresponding to the compression task, if the fifth information includes the maximum value of N1*N2, and the maximum value of N1*N2 is 16, then any fourth value in the first information that is at least one fourth value of N1*N2 does not exceed 16.

[0483] For example, the first information can be carried in an RRC Reconfiguration message.

[0484] In one possible implementation, if the network device configures a first value for at least one first inference parameter for a single first prediction task for the terminal device, then in S1830, the network device can send first information #1 to the terminal device based on the values ​​of the inference parameters supported by the terminal device for the single prediction task. The first information #1 includes the first value of at least one first inference parameter. The first value of the first inference parameter does not exceed the value of the inference parameter supported by the terminal device for the single prediction task. For example, if the maximum value of K included in the fifth information is 4, then the first value of K included in the first information #1 does not exceed 4.

[0485] In one possible implementation, if the network device configures a second value for at least one second inference parameter for a single first compression task for the terminal device, then in S1830, the network device can send first information #2 to the terminal device based on the values ​​of the inference parameters supported by the terminal device for a single compression task. First information #2 includes the second value of at least one second inference parameter. The second value of the second inference parameter does not exceed the value of the inference parameter supported by the terminal device for a single compression task. For example, for the number of CSI-RS ports N1*N2, if the maximum value of N1*N2 included in the fifth information is 16, then the second value of N1*N2 included in the first information #2 does not exceed 16.

[0486] S1840, the terminal device sends the second information.

[0487] Correspondingly, the network device receives the second information.

[0488] The second information includes at least one set of inference parameters, each set of inference parameters including at least one first inference parameter and at least one second inference parameter, wherein the fifth value of the first inference parameter included in each set of inference parameters belongs to at least one third value, and / or the sixth value of the second inference parameter included belongs to at least one fourth value, and the at least one set of inference parameters is used for a second task, the second task including a prediction task and a compression task.

[0489] For example, after receiving the first information from the network device, the terminal device can send the second information to the network device based on the first information.

[0490] For example, after receiving the first information from the network device, the terminal device can combine the values ​​of the inference parameters for the prediction task and the inference parameters for the compression task included in the first information, based on the values ​​of the inference parameters supported by the terminal device for the second task, to obtain at least one set of inference parameters. The values ​​of the inference parameters included in each of the at least one set of inference parameters do not exceed the maximum value of the inference parameters supported by the terminal device for the second task.

[0491] For example, the first information includes the following: the number of observation instances K included in the observation window takes the value {2, 4, 6}; the number of prediction instances N4 included in the prediction window takes the value {2, 4, 6}; the number of CSI-RS ports N1*N2 takes the value {4, 8, 16}; and the CSI payload size takes the value {128 bits}. The maximum values ​​of K, N4, N1*N2, and CSI payload size supported by the terminal device for the second task are 4, 4, 8, and 128, respectively. Then, the at least one set of inference parameters determined by the terminal device can include at least one of the following sets of inference parameters: Inference parameter set #1 = {K = 2, N4 = 2, N1*N2 = 4, CSI payload size = 128 bits}, Inference parameter set #2 = {K = 4, N4 = 2, N1*N2 = 4, CSI payload size = 128 bits}, Inference parameter set #3 = {K = 2, N4 = 4, N1*N2 = 4, CSI payload size = 128 bits}. The following sets of parameters are defined: #4 = {K = 4, N4 = 4, N1*N2 = 4, CSI payload size = 128 bits}, #5 = {K = 2, N4 = 2, N1*N2 = 8, CSI payload size = 128 bits}, #6 = {K = 4, N4 = 2, N1*N2 = 8, CSI payload size = 128 bits}, #7 = {K = 2, N4 = 4, N1*N2 = 8, CSI payload size = 128 bits}, and #8 = {K = 4, N4 = 4, N1*N2 = 8, CSI payload size = 128 bits}.

[0492] For example, the second information can be carried in an applicable functionality reporting.

[0493] S1850, the network device sends third information.

[0494] Correspondingly, the terminal device receives third-party information.

[0495] The third information includes a first inference parameter set, which belongs to the at least one inference parameter set and is used for the first task.

[0496] For example, after receiving the second information from the terminal device, the network device can select a first inference parameter set from at least one inference parameter set included in the second information for the first task.

[0497] For example, third-party information can be carried in an RRCReconfiguration message.

[0498] It should be understood that after the network device configures the first inference parameter set for the first task for the terminal device, the terminal device can execute the first task based on the first inference parameter set.

[0499] Optionally, the terminal device and network device can also perform operations such as model activation, model deactivation, model inference, or model monitoring based on the first inference parameter.

[0500] In this embodiment, the terminal device can combine the values ​​of inference parameters configured by the network device for the prediction task and the values ​​of inference parameters configured for the compression task to obtain at least one set of inference parameters for the second task, and send at least one set of inference parameters to the network device. This allows the network device to accurately issue inference parameter configurations that meet the model deployment implementation of the terminal device based on at least one set of inference parameters reported by the terminal device, without having to send too many combinations of inference parameter values ​​to the terminal device, thereby saving signaling overhead.

[0501] Furthermore, when the set of inference parameters for the second task is determined by the terminal device, the terminal device can combine the values ​​of the inference parameters configured by the network device for the prediction task and the inference parameters for the compression task according to the maximum value of the inference parameters for the second task supported by the terminal device, thereby avoiding the network device configuring inference parameter values ​​for the terminal device that exceed the terminal device's capabilities.

[0502] It should be understood that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0503] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0504] It should also be understood that in the above embodiments, the examples are mainly based on devices in existing network architectures, and it should be understood that the specific form of the device is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0505] It is understood that, in the above-described method embodiments, the methods and operations implemented by a device (such as a terminal device or a network device) can also be implemented by components of the device (such as chips or circuits).

[0506] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0507] The methods provided in the embodiments of this application have been described in detail above with reference to several accompanying drawings. The apparatus provided in the embodiments of this application will now be described with reference to the accompanying drawings.

[0508] Figures 19 and 20 are schematic block diagrams of possible apparatuses provided in embodiments of this application. These apparatuses can be used to implement the terminal-side or network-side functions in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0509] Figure 19 is a schematic block diagram of an apparatus provided in an embodiment of this application. The apparatus 1900 shown in Figure 19 may include a processing module 1910 and a communication module 1920.

[0510] In one possible design, device 1900 can be used to implement the communication method implemented by the terminal device in any of the embodiments shown in FIG8, FIG11, FIG13, or FIG18. For example, processing module 1910 is used to implement processing-related steps performed by the terminal device in each method embodiment, such as determining the first CSI duration, the second CSI duration, or CSI reference resources; communication module 1920 is used to implement sending and / or receiving steps performed by the terminal device in each method embodiment, such as sending first indication information or sending second indication information.

[0511] For example, the processing module 1910 is configured to: determine one or more of the following based on a first duration: a first CSI duration, a second CSI duration, and a CSI reference resource corresponding to the first CSI report; the first CSI duration corresponds to the interval between the end time of the first downlink channel and the start time of the transmission of the first CSI report, the second CSI duration corresponds to the interval between the transmission timing of the first reference signal and the transmission start time of the first CSI report; the first duration corresponds to the execution duration of a first task, the first task including an AI-based first prediction task and an AI-based first compression task, the input data of the first compression task being determined based on the output data of the first prediction task, and the first CSI report, the first downlink channel, and the transmission timing of the first reference signal corresponding to the first task.

[0512] A more detailed description of the processing module 1910 and the communication module 1920 can be obtained directly from the relevant descriptions in the method embodiments shown in Figures 8, 11, 13 or 18, and will not be repeated here.

[0513] In another possible design, device 1900 can be used to implement the communication method implemented by a network device in any of the embodiments shown in FIG8, FIG11, FIG13, or FIG18. For example, processing module 1910 is used to implement processing-related steps performed by the network device in each method embodiment, such as determining a first CSI duration, a second CSI duration, or a CSI reference resource; communication module 1920 is used to implement sending and / or receiving steps performed by the network device in each method embodiment, such as receiving a first indication information or receiving a second indication information.

[0514] For example, the processing module 1910 is configured to: determine one or more of the following based on a first duration: a first CSI duration, a second CSI duration, and a CSI reference resource corresponding to the first CSI report; the first CSI duration corresponds to the interval between the end time of the first downlink channel and the start time of the transmission of the first CSI report, the second CSI duration corresponds to the interval between the transmission timing of the first reference signal and the transmission start time of the first CSI report; the first duration corresponds to the execution duration of a first task, the first task including an AI-based first prediction task and an AI-based first compression task, the input data of the first compression task being determined based on the output data of the first prediction task, and the first CSI report, the first downlink channel, and the transmission timing of the first reference signal corresponding to the first task.

[0515] A more detailed description of the processing module 1910 and the communication module 1920 can be obtained directly from the relevant descriptions in the method embodiments shown in Figures 8, 11, 13 or 18, and will not be repeated here.

[0516] It should be noted that the communication module can also be called a transceiver module, transceiver unit, transceiver, transceiver device, or transceiver apparatus, etc. The processing module can also be called a processor, processing board, processing unit, or processing apparatus, etc. Optionally, the communication module is used to perform the sending and receiving operations of the terminal device or network device in the above method. The device in the communication module that implements the receiving function can be considered as the receiving module, and the device in the communication module that implements the sending function can be considered as the sending module; that is, the communication module can include both a receiving module and a sending module.

[0517] It should also be noted that, in one possible design, the aforementioned processing module and / or communication module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. In another possible design, the processing module or communication module can also be implemented through physical devices. For example, if the device is implemented using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module can be an integrated processor, a microprocessor, or an integrated circuit.

[0518] The module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional modules in the various examples of this embodiment can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0519] Figure 20 is a schematic diagram of the structure of a communication device provided in another embodiment of this application. As shown in Figure 20, the device 2000 includes a processing circuit 2010 and a communication circuit 2020. The processing circuit 2010 and the communication circuit 2020 are coupled to each other.

[0520] It can be understood that the processing circuit 2010 can be one or more processors, or it can be all or part of the circuits with processing functions in one or more processors.

[0521] It is understandable that the communication circuit 2020 can be a transceiver or an input / output interface.

[0522] Optionally, the device 2000 may further include a memory 2030 for storing instructions executed by the processing circuit 2010, or storing input data required for the running instructions of the processing circuit 2010, or storing data generated after the running instructions of the processing circuit 2010.

[0523] It is understood that the memory 2030 may be located outside the processing circuit 2010 or inside the processing circuit 2010.

[0524] As an example, the processing circuit 2010 is used to implement the functions of the processing module 1910, and the communication circuit 2020 is used to implement the functions of the communication module 1920.

[0525] As an example, device 2000 can be a communication device (such as a terminal device or network device) or a chip used in a communication device.

[0526] When device 2000 is a communication device, the communication circuit can be a transceiver; when device 2000 is a chip, the communication circuit can be an input / output circuit, a bus, pins, or other types of communication interfaces. The input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0527] In one possible implementation, the apparatus 2000 is used to implement the various processes and steps corresponding to the terminal device in the above method embodiments. In another possible implementation, the apparatus 2000 is used to implement the various processes and steps corresponding to the network device in the above method embodiments.

[0528] It is understood that the device 2000 can specifically be the terminal device or network device in the above embodiments, or it can be a chip or chip system. Correspondingly, the communication circuit can be the interface circuit of the chip, or an input / output circuit, which is not limited here. Specifically, the device 2000 can be used to execute the various steps and / or processes corresponding to the terminal device or network device in the above method embodiments.

[0529] When the aforementioned communication device is a chip or OTT device applied to a terminal device, the chip or OTT device of the terminal device implements the functions of the terminal device in the above method embodiments, for example, implementing the processing functions of the terminal device. The terminal device chip or OTT device receiving information from the network device can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the terminal device, and then sent by these modules to the terminal device chip or OTT device. The terminal device chip or OTT device sending information to the network device can be understood as the information being first sent by the terminal device chip or OTT device to other modules (such as radio frequency modules or antennas) in the network device, and then sent by these modules to the network device.

[0530] When the aforementioned communication device is a chip or OTT device applied to a network device, the chip or OTT device of the network device implements the functions of the network device in the above method embodiments, for example, implementing the processing functions of the network device. The chip or OTT device of the network device receiving information from the terminal device can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the network device, and then sent by these modules to the chip or OTT device. The chip or OTT device of the network device sending information to the terminal device can be understood as the information being first sent by the chip or OTT device to other modules (such as radio frequency modules or antennas) in the network device, and then sent by these modules to the terminal device.

[0531] Optionally, as shown in Figure 21, the device 2000 may further include a CPU rule determination module. The CPU rule determination module is used to determine the CPU count and timeline occupancy rules of the SPC inference report (such as the first CSI report described above) based on the CSI report configuration signaling and UE capability reporting, thereby controlling the transmit / receive chain through communication circuits and processing circuits. Optionally, the functionality of the CPU rule determination module can also be processed on a computer-readable medium.

[0532] This application also provides a computer program product that, when run on a processor, can implement the communication method executed by the terminal device or the communication method executed by the network device in the above method embodiments.

[0533] This application also provides a computer-readable storage medium containing computer instructions that, when executed on a processor, can implement the communication method executed by a terminal device or a network device in the above method embodiments.

[0534] This application also provides a communication system, including the aforementioned terminal equipment and network equipment.

[0535] It is understood that the processor in the embodiments of this application may be any of the following devices or all or part of the circuitry used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), processors for AI, field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0536] For example, the processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0537] For example, one possible implementation of a processor for AI could be the AI ​​processor 2200 shown in Figure 22.

[0538] As shown in Figure 22, the AI ​​processor 2200 may include one or more of the following: AI core, digital vision pre-processing (DVPP) module, task scheduler (TS), L3 cache, AI CPU (central processing unit), control CPU (central processing unit), L2 cache, universal serial bus (USB) interface, network card, peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), double data rate (DDR) / high bandwidth memory (HBM) interface, generation purpose input / output (GPIO) / inter-integrated circuit (I2C) bus, etc. It is understood that the specific meanings of these terms are well known to those skilled in the art and will not be elaborated upon here.

[0539] The terms “unit”, “module”, etc., used in this specification may be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution.

[0540] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0541] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0542] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0543] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0544] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0545] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0546] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0547] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applied to the first device, comprising: The following one or more are determined based on the first duration: the duration of the first channel state information (CSI), the duration of the second CSI, and the CSI reference resource corresponding to the first CSI report; the first CSI duration corresponds to the interval between the end time of the first downlink channel and the start time of the transmission of the first CSI report, and the second CSI duration corresponds to the interval between the transmission timing of the first reference signal and the start time of the transmission of the first CSI report. The first duration corresponds to the execution duration of the first task, which includes a first prediction task based on artificial intelligence (AI) and a first compression task based on AI. The input data of the first compression task is determined based on the output data of the first prediction task. The first CSI report, the first downlink channel, and the first reference signal transmission timing correspond to the first task.

2. The method according to claim 1, characterized in that, Determining the first CSI duration based on the first duration includes: The first CSI duration is determined based on the first duration and the duration of the first observation window corresponding to the first task.

3. The method according to claim 2, characterized in that, The duration of the first CSI is not less than the sum of the first duration, the duration of the first observation window, and the second duration predefined by the protocol.

4. The method according to any one of claims 1 to 3, characterized in that, The duration of the second CSI is not less than the sum of the first duration and the third duration predefined by the protocol.

5. The method according to any one of claims 1 to 4, characterized in that, The interval between the CSI reference resource and the transmission start time of the first CSI report is greater than or equal to the minimum of the fourth duration, where the fourth duration is the sum of the first duration and the fifth duration predefined by the protocol.

6. The method according to any one of claims 1 to 5, characterized in that, The first duration is a predefined value; or, The first duration is related to a first value of at least one first inference parameter and / or a second value of at least one second inference parameter, wherein the first value of the at least one first inference parameter is used for the first prediction task, and the second value of the at least one second inference parameter is used for the first compression task.

7. The method according to any one of claims 1 to 5, characterized in that, The first duration is greater than or equal to the sum of the sixth duration and the seventh duration, wherein the sixth duration corresponds to the execution duration of the first prediction task and the seventh duration corresponds to the execution duration of the first compression task.

8. The method according to claim 7, characterized in that, The sixth duration is a predefined value; or, The sixth duration is related to a first value of at least one first inference parameter, and the first value of the at least one first inference parameter is used for the first prediction task.

9. The method according to claim 7 or 8, characterized in that, The seventh duration is a predefined value; or, The seventh duration is related to a second value of at least one second inference parameter, and the second value of the at least one second inference parameter is used for the first compression task.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: The count value of the first CSI report channel state information processing unit CPU is determined according to one or more of the following: a first count, a second count, a first value of at least one first inference parameter, and a second value of at least one second inference parameter; Wherein, the first quantity is the number of CPUs required to execute the first prediction task, the second quantity is the number of CPUs required to execute the first compression task, the first value of the at least one first inference parameter is used for the first prediction task, and the second value of the at least one second inference parameter is used for the first compression task.

11. The method according to claim 10, characterized in that, During the period when the first CSI report occupied CPU time, the CPU usage count of the first CSI report was: The maximum value between the first quantity and the second quantity; or, The weighted sum of the first quantity and the second quantity; or, A count value determined based on a first value of the at least one first inference parameter and / or a second value of the at least one second inference parameter.

12. The method according to claim 11, characterized in that, The first CSI report's CPU usage count is a weighted sum of the first quantity and the second quantity, and the method further includes: Send or receive first indication information, the first indication information being used to indicate a first weighting coefficient corresponding to the first quantity and / or a second weighting coefficient corresponding to the second quantity, the first weighting coefficient and the second weighting coefficient being used to determine the CPU count value occupied by the first CSI report.

13. The method according to claim 10, characterized in that, From the start of the time period during which the first CSI report occupies CPU to the first time, the count value of the CPU occupied by the first CSI report is the first quantity; During the period from the first moment to the end of the time period in which the first CSI report occupies CPU, the count value of the first CSI report occupying CPU is the second quantity.

14. The method according to claim 13, characterized in that, The first moment is a predefined moment; or, The first time point is prior to the CSI reference resource, and the interval between the first time point and the CSI reference resource is an eighth duration; or, The first moment is after the first reference signal transmission opportunity, and the interval between the first reference signal transmission opportunity and the first moment is related to the execution time of the first prediction task.

15. The method according to claim 14, characterized in that, The method further includes: Send or receive a second indication message, the second indication message indicating the first moment.

16. The method according to any one of claims 10 to 15, characterized in that, The first quantity is a predefined value; or, The first quantity is related to a first value of the at least one first inference parameter.

17. The method according to any one of claims 10 to 16, characterized in that, The second quantity is a predefined value; or, The second quantity is related to a second value of the at least one second inference parameter.

18. The method according to any one of claims 1 to 17, characterized in that, The method further includes: Receive first information, the first information including at least one third value of each of the first inference parameters, and / or including at least one fourth value of each of the second inference parameters; the first inference parameters are used for prediction tasks, and the second inference parameters are used for compression tasks; Send a second message, the second message including at least one set of inference parameters, each set of inference parameters including at least one first inference parameter and at least one second inference parameter, wherein the fifth value of the first inference parameter included in each set of inference parameters belongs to at least one third value, and / or the sixth value of the second inference parameter included in each set of inference parameters belongs to at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; Receive third information, the third information including a first inference parameter set, the first inference parameter set belonging to the at least one inference parameter set, the first inference parameter set being used for the first task.

19. The method according to claim 18, characterized in that, Before receiving the first information, the method further includes: Receive fourth information, the fourth information being used to request the value of the first inference parameter supported by the first device, and / or to request the value of the second inference parameter supported by the first device; Send a fifth message, the fifth message including the value of the first inference parameter supported by the first device, and / or including the value of the second inference parameter supported by the first device.

20. The method according to any one of claims 6 to 19, characterized in that, The at least one first inference parameter includes one or more of the following: Whether AI features are supported, the number of observation instances included in the observation window, the interval between two adjacent observation resources included in the observation window, the number of prediction instances included in the prediction window, the interval between two adjacent prediction instances included in the prediction window, the starting time domain position of the prediction window, the dataset identifier, the association identifier, or the function identifier.

21. The method according to any one of claims 6 to 20, characterized in that, The at least one second inference parameter includes one or more of the following: Dataset identifier, association identifier, model identifier, function identifier, dimensions of input data for compression task, dimensions of output data for compression task, and processing method of output data for compression task.

22. A communication method, characterized in that, include: The count value of the first channel state information (CSI) report occupying the CSI processing unit CPU is determined based on one or more of the following: a first count, a second count, a first value of at least one first inference parameter, and a second value of at least one second inference parameter; wherein the first count is the number of CPUs required to execute the first prediction task, the second count is the number of CPUs required to execute the first compression task, the first value of the at least one first inference parameter is used for the first prediction task, and the second value of the at least one second inference parameter is used for the first compression task.

23. The method according to claim 22, characterized in that, During the period when the first CSI report occupied CPU time, the CPU usage count of the first CSI report was: The maximum value between the first quantity and the second quantity; or, The weighted sum of the first quantity and the second quantity; or, A count value determined based on a first value of the at least one first inference parameter and / or a second value of the at least one second inference parameter.

24. The method according to claim 23, characterized in that, The first CSI report's CPU usage count is a weighted sum of the first quantity and the second quantity, and the method further includes: Send or receive first indication information, the first indication information being used to indicate a first weighting coefficient corresponding to the first quantity and / or a second weighting coefficient corresponding to the second quantity, the first weighting coefficient and the second weighting coefficient being used to determine the CPU count value occupied by the first CSI report.

25. The method according to claim 23, characterized in that, From the start of the time period during which the first CSI report occupies CPU to the first time, the count value of the CPU occupied by the first CSI report is the first quantity; During the period from the first moment to the end of the time period in which the first CSI report occupies CPU, the count value of the first CSI report occupying CPU is the second quantity.

26. The method according to claim 25, characterized in that, The first moment is a predefined moment; or, The first time point is before the CSI reference resource, and the interval between the first time point and the CSI reference resource is an eighth time period; or, The first time point is after the first reference signal transmission opportunity, and the interval between the first reference signal transmission opportunity and the first time point is related to the execution duration of the first prediction task.

27. The method according to claim 25, characterized in that, The method further includes: Send or receive a second instruction message, which indicates the first moment.

28. A communication method, characterized in that, include: Based on the sixth duration, one or more of the following are determined: the duration of the third channel state information (CSI), the duration of the fourth CSI, and the CSI reference resource corresponding to the second CSI report; Wherein, the third CSI duration corresponds to the interval between the end time of the second downlink channel and the start time of the transmission of the second CSI report; the fourth CSI duration corresponds to the interval between the transmission timing of the third reference signal and the transmission start time of the second CSI report; the sixth duration corresponds to the execution duration of the first prediction task based on artificial intelligence (AI); and the second CSI report, the second downlink channel, and the transmission timing of the third reference signal correspond to the first prediction task.

29. The method according to claim 28, characterized in that, The third CSI duration is determined based on the sixth duration, including: The third CSI duration is determined based on the sixth duration and the duration of the observation window corresponding to the first prediction task.

30. The method according to claim 29, characterized in that, The duration of the third CSI is not less than the sum of the sixth duration, the duration of the observation window corresponding to the first prediction task, and the second duration predefined by the protocol.

31. The method according to any one of claims 28 to 30, characterized in that, The duration of the fourth CSI is not less than the sum of the sixth duration and the third duration predefined by the protocol.

32. The method according to any one of claims 28 to 31, characterized in that, The interval between the CSI reference resource and the transmission start time of the second CSI report is greater than or equal to the minimum of the fourth duration #a, where the fourth duration #a is the sum of the sixth duration and the fifth duration predefined by the protocol.

33. A communication method, characterized in that, include: Based on the seventh duration, one or more of the following can be determined: the duration of the fifth channel state information (CSI), the duration of the sixth CSI, and the CSI reference resource corresponding to the third CSI report; Wherein, the fifth CSI duration corresponds to the interval between the end time of the third downlink channel and the start time of the transmission of the third CSI report; the sixth CSI duration corresponds to the interval between the transmission timing of the fifth reference signal and the transmission start time of the third CSI report; the seventh duration corresponds to the execution duration of the first compression task based on artificial intelligence (AI); and the third CSI report, the third downlink channel, and the transmission timing of the fifth reference signal correspond to the first compression task.

34. The method according to claim 33, characterized in that, The duration of the fifth CSI is not less than the sum of the seventh duration and the second duration predefined by the protocol.

35. The method according to claim 33 or 34, characterized in that, The duration of the sixth CSI is not less than the sum of the seventh duration and the third duration predefined by the protocol.

36. The method according to any one of claims 33 to 35, characterized in that, The interval between the CSI reference resource and the transmission start time of the third CSI report is greater than or equal to the minimum of the fourth duration #b, where the fourth duration #b is the sum of the seventh duration and the fifth duration predefined by the protocol.

37. A communication method, characterized in that, include: Receive first information, the first information including at least one third value of each of the first inference parameters, and / or including at least one fourth value of each of the second inference parameters; wherein the first inference parameters are used for prediction tasks, and the second inference parameters are used for compression tasks; Send a second message, the second message including at least one set of inference parameters, each set of inference parameters including at least one first inference parameter and at least one second inference parameter, the fifth value of the first inference parameter included in each set of inference parameters belonging to the at least one third value, and / or the sixth value of the second inference parameter included belonging to the at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; Receive third information, the third information including a first inference parameter set, the first inference parameter set belonging to the at least one inference parameter set, the first inference parameter set being used for the first task.

38. The method according to claim 37, characterized in that, Before receiving the first information, the method further includes: Receive fourth information, the fourth information being used to request the value of the first inference parameter supported by the first device, and / or to request the value of the second inference parameter supported by the first device; Send a fifth message, the fifth message including the value of the first inference parameter supported by the first device, and / or including the value of the second inference parameter supported by the first device.

39. A communication method, characterized in that, include: Send a first message, the first message including at least one third value of each of the first inference parameters, and / or including at least one fourth value of each of the second inference parameters; the first inference parameters are used for prediction tasks, and the second inference parameters are used for compression tasks; Receive second information, the second information including at least one set of inference parameters, each set of inference parameters including at least one first inference parameter and at least one second inference parameter, the fifth value of the first inference parameter included in each set of inference parameters belonging to at least one third value, and / or the sixth value of the second inference parameter included in each set of inference parameters belonging to at least one fourth value, the at least one set of inference parameters being used for a second task, the second task including a prediction task and a compression task; Send a third message, the third message including a first inference parameter set, the first inference parameter set belonging to the at least one inference parameter set, the first inference parameter set being used for the first task.

40. The method according to claim 39, characterized in that, Before sending the first information, the method further includes: Send a fourth message, the fourth message being used to request the value of the first inference parameter supported by the first device, and / or to request the value of the second inference parameter supported by the first device; The fifth information is received, which includes the value of the first inference parameter supported by the first device, and / or includes the value of the second inference parameter supported by the first device.

41. A communication device, characterized in that, It includes functional modules for implementing the method as described in any one of claims 1 to 21, or includes functional modules for implementing the method as described in any one of claims 22 to 27, or includes functional modules for implementing the method as described in any one of claims 28 to 32, or includes functional modules for implementing the method as described in any one of claims 33 to 36, or includes functional modules for implementing the method as described in any one of claims 37 to 38, or includes functional modules for implementing the method as described in any one of claims 39 to 40.

42. A communication device, characterized in that, The device includes one or more processors and communication circuitry, the communication circuitry being used for at least one of inputting or outputting signals; the one or more processors are used to implement the method as described in any one of claims 1 to 21, or to implement the method as described in any one of claims 22 to 27, or to implement the method as described in any one of claims 28 to 32, or to implement the method as described in any one of claims 33 to 36, or to implement the method as described in any one of claims 37 to 38, or to implement the method as described in any one of claims 39 to 40.

43. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed by a processor, cause the method as described in any one of claims 1 to 21 to be performed, or the method as described in any one of claims 22 to 27 to be performed, or the method as described in any one of claims 28 to 32 to be performed, or the method as described in any one of claims 33 to 36 to be performed, or the method as described in any one of claims 37 to 38 to be performed, or the method as described in any one of claims 39 to 40 to be performed.

44. A computer program product, characterized in that, Includes a computer program that, when run, causes the method as described in any one of claims 1 to 21 to be performed, or causes the method as described in any one of claims 22 to 27 to be performed, or causes the method as described in any one of claims 28 to 32 to be performed, or causes the method as described in any one of claims 33 to 36 to be performed, or causes the method as described in any one of claims 37 to 38 to be performed, or causes the method as described in any one of claims 39 to 40 to be performed.

45. A communication system, characterized in that, It includes one or more of the following means: means for implementing the method as described in any one of claims 1 to 21, or means for implementing the method as described in any one of claims 22 to 27, or means for implementing the method as described in any one of claims 28 to 32, or means for implementing the method as described in any one of claims 33 to 36, or means for implementing the method as described in any one of claims 37 to 38, or means for implementing the method as described in any one of claims 39 to 40.

Images