Communication method and communication device

Abstract

[0010] An embodiment of this application provides a communication method and a communication device. The method includes: receiving a first reference signal from a first device; determining whether p pieces of predictive channel information are valid; and sending first indication information to the first device, the first indication information indicating at least one piece of channel information; when it is determined that the p pieces of predictive channel information are valid, the at least one piece of channel information includes p pieces of predictive channel information; or when it is determined that the p pieces of predictive channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predictive channel information; or the at least one piece of channel information includes channel information measured based on the first reference signal, where p is a positive integer, and the time corresponding to the p pieces of predictive channel information is not earlier than the time of sending the first indication information. According to the solution in the embodiment of this application, the channel information acquired by the first device can accurately reflect the channel state.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims priority to Chinese Patent Application No. 202211668669.9, entitled "COMMUNICATION METHOD AND COMMUNICATION APPARATUS," filed with the State Intellectual Property Office of China on December 23, 2022, which is incorporated herein by reference in its entirety.

[0002] [Technical field] TECHNICAL FIELD Embodiments of this application relate to the field of communications, and more particularly to a communication method and a communication device. [Background technology]

[0003] In a communication system, a network device needs to determine related configuration information, such as resources, modulation and coding scheme (MCS), and precoding, to be used for scheduling a downlink data channel for a terminal device based on channel state information (CSI) parameters.

[0004] Channel aging means that the current channel is different from the channel used during measurement due to processing delays or relative movement between the terminal device and the network device. For example, when a terminal device currently moves at high speed, the CSI acquired by the network device becomes outdated due to fast fading due to fast channel changes caused by multipath fading. Channel aging has a serious adverse effect on various adaptive transmission systems. CSI prediction helps to alleviate channel aging. CSI prediction means that future CSI is predicted with reference to past CSI by using channel correlations in the time, frequency, and spatial domains.

[0005] However, in practical scenarios, the predicted CSI may not accurately reflect the actual channel quality, affecting the accuracy of subsequent related configurations of the network device. For example, when a terminal device feeds back CSI, if an artificial intelligence (AI) prediction model is deployed in the terminal device, the terminal device may feed back the CSI predicted by the AI ​​prediction model to the network device. However, when the distribution difference between the training data of the AI ​​prediction model and the current data of the AI ​​prediction model is large, the performance of the AI ​​prediction model is affected, affecting the accuracy of the predicted CSI. When the accuracy of the predicted CSI is low, CSI prediction cannot bring about performance gains and may even affect subsequent related configurations of the network device, resulting in performance degradation. Summary of the Invention

[0006] The embodiments of this application provide a communication method and a communication apparatus for expecting that the channel information acquired by associated devices can accurately reflect the channel conditions.

[0007] According to a first aspect, there is provided a communication method. The method may be performed by a second device, or may be performed by a chip or circuit located in the second device. This is not limited in this application. For example, the second device may be a terminal device. In another example, the second device may be a network device.

[0008] The method includes the steps of receiving a first reference signal from the first device; determining whether p pieces of predictive channel information are valid; and sending first indication information to the first device, the first indication information indicating at least one piece of channel information, wherein when it is determined that the p pieces of predictive channel information are valid, the at least one piece of channel information includes p pieces of predictive channel information; alternatively, when it is determined that the p pieces of predictive channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predictive channel information; alternatively, the at least one piece of channel information includes channel information measured based on the first reference signal, where p is a positive integer, and the time corresponding to the p pieces of predictive channel information is not earlier than the time of sending the first indication information.

[0009] In the solution of this embodiment of the present application, the content to be fed back to the first device, i.e., the content indicated by the first indication information, is determined based on whether the p pieces of predictive channel information are valid, and it is expected that the channel information acquired by the first device can accurately reflect the channel state. For example, when the p pieces of predictive channel information are invalid, the channel information fed back to the first device includes at least channel information measured based on the first reference signal. In this way, the first device can acquire channel information that can more accurately reflect the channel state and avoid performance degradation that may occur when the first device performs data transmission based on inaccurate predictive channel information. In another example, when the p pieces of predictive channel information are valid, the p pieces of predictive channel information may be fed back to the first device, so that the first device can perform data transmission based on the predictive channel information and mitigate the channel aging problem. Furthermore, when the p pieces of predictive channel information are invalid, some of the p pieces of predictive channel information may be accurate. The second device may feed back the channel information measured based on the first reference signal and the p pieces of predicted channel information to the first device, so as to enable the first device to perform subsequent processing based on the p pieces of predicted channel information.

[0010] For example, the channel information may be predicted in multiple ways. For example, the channel information may be predicted in one or more of the following ways: linear fitting, Kalman filtering, AI model, etc. An AI model-based prediction method is used as an example. Channel information measured at one or more past time points is input into the AI ​​prediction model, and the AI ​​prediction model outputs channel information at one or more future time points.

[0011] Referring to the first aspect, in some implementation manners of the first aspect, the step of determining whether the p pieces of predicted channel information are valid includes the step of determining whether the p pieces of predicted channel information are valid based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, where the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and the time corresponding to the n pieces of predicted channel information is earlier than the time of transmitting the first indication information.

[0012] In the solution of this embodiment of the present application, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information may be used to reflect the accuracy of the channel information prediction. In this way, whether the p pieces of predicted channel information are valid can be determined based on the accuracy of the channel information prediction, and the content indicated by the first indication information can further be determined, so that it can be expected that the channel information acquired by the first device can accurately reflect the channel state. For example, if the channel information prediction is accurate, it may be determined that the p pieces of predicted channel information are valid. In another example, if the channel information prediction is inaccurate, it may be determined that the p pieces of predicted channel information are invalid.

[0013] Referring to the first aspect, in some implementation manners of the first aspect, the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and the difference between the time point corresponding to the i-th predicted channel information and the time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .., n.

[0014] For example, the first threshold may be predefined, indicated by the first device, or determined by the second device.

[0015] In the solution of this embodiment of this application, the time point corresponding to the measured channel information is close to the time point corresponding to the predicted channel information which has a corresponding relationship with the measured channel information, so that the interference of time factors on the comparison result is avoided as much as possible, and the comparison result obtained in this case has a higher reference value and can more accurately reflect the accuracy of the channel information prediction.

[0016] Referring to the first aspect, in some implementations of the first aspect, the n pieces of measured channel information include channel information measured based on a first reference signal.

[0017] For the channel information used for comparison, a time point closer to the time point corresponding to the p pieces of predicted channel information indicates that the comparison result of the channel information used for comparison can better reflect the accuracy of the prediction result around the time point corresponding to the p pieces of predicted channel information. The time point corresponding to the p pieces of predicted channel information is not earlier than the time point at which the first instruction information is transmitted. The first reference signal may be a reference signal at a time point closest to the time point at which the first instruction information is transmitted, and the channel information measured based on the first reference signal can more accurately reflect the channel conditions at the time point at which the first instruction information is transmitted. In the solution of this embodiment of the present application, the n pieces of measured channel information include channel information measured based on the first reference signal. This helps to determine the accuracy of channel information prediction around the time point corresponding to the p pieces of predicted channel information, helps to more accurately determine whether the p pieces of predicted channel information are valid, and helps to ensure that the first device obtains more accurate channel information.

[0018] Referring to the first aspect, in some implementation manners of the first aspect, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information includes any one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

[0019] Referring to the first aspect, in some implementation manners of the first aspect, the difference between the n channel information prediction results and the n channel information measurement results includes at least one of the following: a mean square error between the n channel information prediction results and the n channel information measurement results, or a normalized error between the n channel information prediction results and the n channel information measurement results.

[0020] Referring to the first aspect, in some implementation manners of the first aspect, the channel correlation between the n channel information prediction results and the n channel information measurement results includes at least one of the following: a generalized cosine similarity between the n channel information prediction results and the n channel information measurement results, or a squared generalized cosine similarity between the n channel information prediction results and the n channel information measurement results.

[0021] Referring to the first embodiment, in some implementation manners of the first embodiment, the p pieces of predicted channel information are obtained through prediction based on the m pieces of measured channel information, where m is a positive integer.

[0022] The m pieces of measurement channel information may be completely or partially the same as the n pieces of measurement channel information. Alternatively, the m pieces of measurement channel information may be completely different from the n pieces of measurement channel information. This is not limited in this embodiment of the present application.

[0023] Referring to the first aspect, in some implementations of the first aspect, the m pieces of measured channel information include channel information measured based on a first reference signal.

[0024] For the measured channel information used to predict channel information at a future time point, a time point closer to the time point at which the prediction needs to be performed usually indicates higher accuracy of the predicted channel information. The time point corresponding to the p predicted channel information is not earlier than the time point at which the first indication information is transmitted. In the solution of this embodiment of this application, the first reference signal may be a reference signal at a time point closest to the time point at which the first indication information is transmitted, and the time point corresponding to the channel information measured based on the first reference signal is closer to the time point corresponding to the p predicted channel information. The n measured channel information includes channel information measured based on the first reference signal, i.e., the channel information measured based on the first reference signal is used to determine the p predicted channel information, so that the p predicted channel information is more accurate.

[0025] Referring to the first aspect, in some implementation manners of the first aspect, the first indication information further indicates a label of at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

[0026] Referring to the first aspect, in some implementation manners of the first aspect, when the at least one piece of channel information includes p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on a first reference signal and the p pieces of predicted channel information, the first indication information further indicates a time point corresponding to the p pieces of predicted channel information.

[0027] Referring to the first aspect, in some implementations of the first aspect, the method further includes a step of sending second instruction information to the first device, the second instruction information indicating the comparison result.

[0028] Referring to the first aspect, in some implementations of the first aspect, n=1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference; a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation; a difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, and a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation; or The difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, or the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation. When any one of the following conditions is satisfied, it is determined that the p pieces of predicted channel information are invalid.

[0029] Referring to the first aspect, in some implementation manners of the first aspect, n>1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference; a statistic value of channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation; a statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference, and a statistical value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation; or The statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference, or the statistical value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation. When any one of the following conditions is satisfied, it is determined that the p pieces of predicted channel information are invalid.

[0030] Referring to the first aspect, in some implementation manners of the first aspect, n>1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; a channel correlation between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; a difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, a channel correlation between the y pieces of predicted channel information and the y pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; or A difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, or a channel correlation between the y pieces of predicted channel information and the y pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information. When any one of the following conditions is satisfied, it is determined that the p pieces of predicted channel information are invalid.

[0031] According to a second aspect, there is provided a communication method. The method may be performed by a first device, or may be performed by a chip or circuit located in the first device. This is not limited in this application. For example, the first device may be a terminal device. In another example, the first device may be a network device.

[0032] The method includes the steps of transmitting a first reference signal to a second device and receiving first instruction information from the second device, the first instruction information indicating at least one piece of channel information, wherein when p pieces of predicted channel information are valid, the at least one piece of channel information includes p pieces of predicted channel information, or when p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on the first reference signal, where p is a positive integer, and the time corresponding to the p pieces of predicted channel information is not earlier than the time of transmitting the first instruction information.

[0033] Referring to the second aspect, in some implementation manners of the second aspect, the first indication information further indicates a label of at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

[0034] Referring to the second aspect, in some implementation manners of the second aspect, the method further includes: when the at least one piece of channel information includes channel information measured based on a first reference signal, performing data transmission based on the channel information measured based on the first reference signal; or when the at least one piece of channel information does not include channel information measured based on the first reference signal, performing data transmission based on the p pieces of predicted channel information.

[0035] Referring to the second aspect, in some implementation manners of the second aspect, the method further includes: determining, based on a label of at least one piece of channel information, that at least one piece of channel information includes a measurement result, and performing data transmission based on the channel information measured based on the first reference signal; or determining, based on the label of the at least one piece of channel information, that at least one piece of channel information does not include the measurement result, and performing data transmission based on p pieces of predicted channel information.

[0036] Referring to the second aspect, in some implementation manners of the second aspect, when the at least one piece of channel information includes p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on a first reference signal and the p pieces of predicted channel information, the first indication information further indicates a time point corresponding to the p pieces of predicted channel information.

[0037] Referring to the second aspect, in some implementation manners of the second aspect, p pieces of predicted channel information are obtained through prediction based on m pieces of measured channel information, where the m pieces of measured channel information include channel information measured based on a first reference signal, and m is a positive integer.

[0038] Referring to the second aspect, in some implementation manners of the second aspect, based on the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, p pieces of predicted channel information are valid or p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and the time corresponding to the n pieces of predicted channel information is earlier than the time of transmission of the first indication information.

[0039] Referring to the second aspect, in some implementation manners of the second aspect, the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and the difference between the time point corresponding to the i-th predicted channel information and the time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .., n.

[0040] Referring to the second aspect, in some implementation manners of the second aspect, the n pieces of measured channel information include channel information measured based on a first reference signal.

[0041] Referring to the second aspect, in some implementation manners of the second aspect, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information includes any one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

[0042] According to a third aspect, there is provided a communication method. The method may be performed by a first device, or may be performed by a chip or circuit located in the first device. This is not limited in this application. For example, the first device may be a terminal device. In another example, the first device may be a network device.

[0043] The method includes a step of receiving first instruction information from a second device, the first instruction information indicating at least one channel information and a label of the at least one channel information, the label of the at least one channel information indicating that the at least one channel information is a predicted result or a measured result, respectively; and a step of performing data transmission based on the at least one channel information.

[0044] According to the solution in this embodiment of the present application, the channel information indicated by the first indication information may be a predicted or measured channel information result, thereby enabling the first device to acquire channel information that can accurately reflect the channel state in different scenarios. For example, the channel information acquired by the first device includes a measured channel information result. In this case, the first device can acquire channel information that can more accurately reflect the channel state at the time of measurement, thereby avoiding performance degradation that may occur when the first device performs data transmission based only on inaccurate predicted channel information. In another example, the channel information acquired by the first device includes a predicted channel information result. In this case, the first device can perform data transmission based on the predicted channel information, thereby mitigating the channel aging problem.

[0045] Referring to the third aspect, in some implementation manners of the third aspect, the method further includes a step of transmitting a first reference signal to the second device, where when p pieces of predicted channel information are valid, the at least one piece of channel information includes p pieces of predicted channel information, or when p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on the first reference signal, and a time point corresponding to the p pieces of predicted channel information is not earlier than a time point of transmitting the first indication information, and p is a positive integer.

[0046] Referring to the third aspect, in some implementation manners of the third aspect, the step of performing data transmission based on the at least one piece of channel information includes: when the at least one piece of channel information includes channel information measured based on a first reference signal, performing data transmission based on the channel information measured based on a first reference signal; or when the at least one piece of channel information does not include channel information measured based on the first reference signal, performing data transmission based on p pieces of predicted channel information.

[0047] Referring to the third aspect, in some implementation manners of the third aspect, the step of performing data transmission based on at least one piece of channel information includes: determining, based on a label of the at least one piece of channel information, that the at least one piece of channel information includes a measurement result, and performing data transmission based on the channel information measured based on a first reference signal; or determining, based on the label of the at least one piece of channel information, that the at least one piece of channel information does not include a measurement result, and performing data transmission based on p pieces of predicted channel information.

[0048] Referring to the third aspect, in some implementation manners of the third aspect, when the at least one piece of channel information includes p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on a first reference signal and the p pieces of predicted channel information, the first indication information further indicates a time point corresponding to the p pieces of predicted channel information.

[0049] Referring to the third aspect, in some implementation manners of the third aspect, p pieces of predicted channel information are obtained through prediction based on m pieces of measured channel information, where the m pieces of measured channel information include channel information measured based on a first reference signal, and m is a positive integer.

[0050] Referring to the third aspect, in some implementation manners of the third aspect, based on the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, p pieces of predicted channel information are valid or p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and the time corresponding to the n pieces of predicted channel information is earlier than the time of transmission of the first indication information.

[0051] Referring to the third aspect, in some implementation manners of the third aspect, the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and the difference between the time point corresponding to the i-th predicted channel information and the time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .., n.

[0052] Referring to the third aspect, in some implementation manners of the third aspect, the n pieces of measured channel information include channel information measured based on a first reference signal.

[0053] Referring to the third aspect, in some implementation manners of the third aspect, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information includes any one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

[0054] Referring to the third aspect, in some implementations of the third aspect, the method further includes a step of receiving second instruction information from the second device, the second instruction information indicating the comparison result.

[0055] According to a fourth aspect, there is provided a communication method. The method may be performed by a first device, or may be performed by a chip or circuit located in the first device. This is not limited in this application. For example, the first device may be a terminal device. In another example, the first device may be a network device.

[0056] The method includes the steps of: transmitting a second reference signal to the second device; and receiving third instruction information from the second device, where the third instruction information indicates q pieces of predicted channel information, and a time corresponding to the q pieces of predicted channel information is not earlier than the time of transmitting the third instruction information; transmitting the third reference signal to the second device; and receiving fourth instruction information from the second device, where the fourth instruction information indicates channel information measured based on the third reference signal, or the fourth instruction information indicates channel information measured based on the third reference signal and the q' pieces of predicted channel information, and the time corresponding to the q' pieces of predicted channel information is not earlier than the time of transmitting the fourth instruction information.

[0057] According to the solution in this embodiment of the present application, the channel information acquired by the first device may be a predicted or measured result of channel information, thereby enabling the first device to acquire channel information that can accurately reflect the channel state in different scenarios. For example, the channel information acquired by the first device may include a measured result of channel information, such as channel information measured based on a third reference signal, thereby enabling the first device to acquire channel information that can more accurately reflect the channel state at the time of measurement and avoid performance degradation that may occur due to the first device performing data transmission based only on inaccurate predicted channel information. In another example, the channel information acquired by the first device may include a predicted result of channel information, such as q pieces of predicted channel information. In this case, the first device can perform data transmission based on the predicted channel information to mitigate the channel aging problem.

[0058] Referring to the fourth aspect, in some implementation manners of the fourth aspect, when q pieces of predicted channel information are valid, the third indication information indicates q pieces of predicted channel information; alternatively, when q' pieces of predicted channel information are invalid, the fourth indication information indicates channel information measured based on the third reference signal; alternatively, the fourth indication information indicates channel information measured based on the third reference signal and q' pieces of predicted channel information.

[0059] Referring to the fourth aspect, in some implementation manners of the fourth aspect, based on a comparison result between r pieces of predicted channel information and r pieces of measured channel information, q' pieces of channel information are invalid, the r pieces of predicted channel information correspond to r pieces of measured channel information, r is a positive integer, and the time corresponding to the r pieces of predicted channel information is earlier than the time of sending the fourth indication information.

[0060] According to a fifth aspect, there is provided a communication method. The method may be performed by a second device, or may be performed by a chip or circuit located in the second device, which is not limited in this application. For example, the second device may be a network device.

[0061] The method includes the steps of receiving a first reference signal from a first device; and determining, based on whether p pieces of predicted channel information are valid, to perform data transmission by using at least one of the p pieces of predicted channel information or channel information measured based on the first reference signal, where the time point corresponding to the p pieces of predicted channel information is later than the measurement time point of the first reference signal, and p is a positive integer.

[0062] For example, the first reference signal may be an uplink reference signal.

[0063] Referring to the fifth aspect, in some implementation manners of the fifth aspect, when the p pieces of predicted channel information are invalid, data transmission is performed based on channel information measured based on the first reference signal, or when the p pieces of predicted channel information are valid, data transmission is performed based on the p pieces of predicted channel information.

[0064] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the method further includes a step of sending first instruction information to the first device, where the first instruction information indicates at least one piece of channel information, and when the p pieces of predicted channel information are valid, the at least one piece of channel information includes the p pieces of predicted channel information, or when the p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on the first reference signal.

[0065] Referring to the fifth aspect, in some implementation manners of the fifth aspect, based on the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, p pieces of predicted channel information are valid or p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and the time corresponding to the n pieces of predicted channel information is earlier than the time of transmission of the first indication information.

[0066] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and the difference between the time corresponding to the i-th predicted channel information and the time corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .., n.

[0067] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the n pieces of measured channel information include channel information measured based on a first reference signal.

[0068] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information includes any one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

[0069] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the p pieces of predicted channel information are obtained through prediction based on m pieces of measured channel information, where m is a positive integer.

[0070] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the m pieces of measured channel information include channel information measured based on a first reference signal.

[0071] Referring to the fifth aspect, in some implementation manners of the fifth aspect, the first indication information further indicates a label of at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

[0072] Referring to the fifth aspect, in some implementation manners of the fifth aspect, when the at least one piece of channel information includes p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on a first reference signal and the p pieces of predicted channel information, the first indication information further indicates a time point corresponding to the p pieces of predicted channel information.

[0073] It should be understood that extensions to, limitations on, explanations of and descriptions of corresponding content in the first aspect are also applicable to the same content in the second, third, fourth and fifth aspects.

[0074] According to a sixth aspect, there is provided a communications apparatus. The communications apparatus may be a second device, or may be a device, module, circuit, chip, etc. configured and arranged within the second device, or may be an apparatus usable in cooperation with the second device. The second device may be a terminal device or a network device. In one design, the communications apparatus may include modules in a one-to-one correspondence with the methods / operations / steps / actions set forth in the first or fifth aspect. The modules may be implemented by hardware circuits, software, or a combination of hardware circuits and software. In one design, the communications apparatus may include a processing module, a receiving module, and a transmitting module. In one design, the communications apparatus may include the processing module and the receiving module. Additionally, the communications apparatus may further include a transmitting module.

[0075] The receiving module is configured to perform the receiving action in the method described in the first aspect, the transmitting module is configured to perform the transmitting action in the method described in the first aspect, and the processing module is configured to perform the processing action in the method described in the first aspect, for example, determining whether the p pieces of predictive channel information are valid. Alternatively, the receiving module is configured to perform the receiving action in the method described in the fifth aspect, the transmitting module is configured to perform the transmitting action in the method described in the fifth aspect, and the processing module is configured to perform the processing action in the method described in the fifth aspect, for example, determining to perform data transmission by using at least one of the p pieces of predictive channel information or channel information measured based on the first reference signal, based on whether the p pieces of predictive channel information are valid.

[0076] According to a seventh aspect, there is provided a communications apparatus. The communications apparatus may be a first device, or may be a device, module, circuit, chip, etc. configured and arranged within the first device, or may be an apparatus usable in cooperation with the first device. The first device may be a network device or a terminal device. In one design, the communications apparatus may include modules in a one-to-one correspondence with the methods / operations / steps / actions set forth in the second, third, or fourth aspects. The modules may be implemented by hardware circuits, software, or a combination of hardware circuits and software. In one design, the communications apparatus may include a transmitting module and a receiving module. Additionally, the communications apparatus may further include a processing module.

[0077] The receiving module is configured to perform the receiving action in the method described in the second aspect, the transmitting module is configured to perform the sending action in the method described in the second aspect, and the processing module is configured to perform the processing action in the method described in the second aspect. Alternatively, the receiving module is configured to perform the receiving action in the method described in the third aspect, the transmitting module is configured to perform the sending action in the method described in the third aspect, and the processing module is configured to perform the processing action in the method described in the third aspect. Alternatively, the receiving module is configured to perform the receiving action in the method described in the fourth aspect, the transmitting module is configured to perform the sending action in the method described in the fourth aspect, and the processing module is configured to perform the processing action in the method described in the fourth aspect.

[0078] According to an eighth aspect, there is provided a communications device including a processor and a storage medium, the storage medium storing instructions which, when executed by the processor, result in a method according to the first aspect or any one of possible implementations of the first aspect, a method according to the second aspect or any one of possible implementations of the second aspect, a method according to the third aspect or any one of possible implementations of the third aspect, a method according to the fourth aspect or any one of possible implementations of the fourth aspect, or a method according to the fifth aspect or any one of possible implementations of the fifth aspect.

[0079] According to a ninth aspect, there is provided a communications device including a processor. The processor is configured to process data and / or information, thereby implementing a method according to the first aspect or any one of its possible implementations, a method according to the second aspect or any one of its possible implementations, a method according to the third aspect or any one of its possible implementations, a method according to the fourth aspect or any one of its possible implementations, or a method according to the fifth aspect or any one of its possible implementations. Optionally, the communications device may further include a communications interface. The communications interface is configured to receive data and / or information and transmit the received data and / or information to the processor. Optionally, the communications interface is further configured to output data and / or information processed by the processor.

[0080] According to a tenth aspect, there is provided a chip including a processor. The processor is configured to execute a program or instructions, thereby implementing a method according to the first aspect or any one of its possible implementations, a method according to the second aspect or any one of its possible implementations, a method according to the third aspect or any one of its possible implementations, a method according to the fourth aspect or any one of its possible implementations, or a method according to the fifth aspect or any one of its possible implementations. Optionally, the chip may further include a memory, the memory configured to store the program or instructions. Optionally, the chip may further include a transceiver.

[0081] According to an eleventh aspect, there is provided a computer-readable storage medium comprising instructions which, when executed by a processor, result in the implementation of a method according to the first aspect or any one of its possible implementations, a method according to the second aspect or any one of its possible implementations, a method according to the third aspect or any one of its possible implementations, a method according to the fourth aspect or any one of its possible implementations, or a method according to the fifth aspect or any one of its possible implementations.

[0082] According to a twelfth aspect, there is provided a computer program product, the computer program product comprising computer program code or instructions which, when executed, result in the implementation of a method according to the first aspect or any one of its possible implementations, a method according to the second aspect or any one of its possible implementations, a method according to the third aspect or any one of its possible implementations, a method according to the fourth aspect or any one of its possible implementations, or a method according to the fifth aspect or any one of its possible implementations.

[0083] According to a thirteenth aspect, there is provided a communication system, the communication system comprising a combination of one or more of the following apparatuses: an apparatus for performing a communication method according to the first aspect or any one of the possible implementation manners of the first aspect; an apparatus for performing a communication method according to the second aspect or any one of the possible implementation manners of the second aspect; an apparatus for performing a communication method according to the third aspect or any one of the possible implementation manners of the third aspect; an apparatus for performing a communication method according to the fourth aspect or any one of the possible implementation manners of the fourth aspect; or an apparatus for performing a communication method according to the fifth aspect or any one of the possible implementation manners of the fifth aspect. [Brief explanation of the drawings]

[0084] [Figure 1] 1 is a diagram of a communication system to which embodiments of the present application are applicable; [Figure 2] FIG. 1 is a diagram of another communication system to which embodiments of the present application are applicable. [Figure 3] FIG. 1 is a schematic block diagram of an autocoder. [Figure 4] A diagram of an AI application framework. [Figure 5] 1 is a schematic flowchart of a communication method according to an embodiment of the present application; [Figure 6] 4 is a schematic flowchart of another communication method according to an embodiment of the present application. [Figure 7] 1 is a schematic flowchart of yet another communication method according to an embodiment of the present application. [Figure 8] FIG. 1 is a diagram of a CSI feedback procedure according to an embodiment of the present application. [Figure 9] FIG. 10 is a diagram of another CSI feedback procedure according to an embodiment of the present application. [Figure 10] FIG. 10 is a diagram of yet another CSI feedback procedure according to an embodiment of the present application. [Figure 11]FIG. 10 is a diagram of yet another CSI feedback procedure according to an embodiment of the present application. [Figure 12] 1 is a schematic block diagram of a communication device according to an embodiment of the present application; [Figure 13] FIG. 2 is a schematic block diagram of another communication device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0085] The technical solutions of this application are described below with reference to the accompanying drawings.

[0086] The technical solutions provided in this application may be used in various communication systems, for example, future 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, 6th generation (6G) mobile communication systems, or integrated systems of multiple systems. The technical solutions provided in this application may also be used in 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.

[0087] A network element in a communication system may transmit a signal to or receive a signal from another network element. The signal may include information, signaling, data, etc. A network element may alternatively be referred to as an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. In this disclosure, a network element is used as an example for explanation. For example, a communication system may include at least one terminal device and at least one network device. The network device may transmit a downlink signal to the terminal device, and / or the terminal device may transmit an uplink signal to the network device. It may be understood that the terminal device in this application may be replaced with a first network element, and the network device may be replaced with a second network element, and the terminal device and the network device perform the corresponding communication method in this disclosure.

[0088] In embodiments of this application, a terminal device may also be referred to as user equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0089] The terminal device may be a device that provides voice / data to a user, such as a handheld device or an in-vehicle device with wireless connectivity. Currently, some examples of terminals include a mobile phone, a tablet computer, a notebook computer, a palmtop computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a personal digital assistant (PDAs ... PDAs, handheld devices with wireless communication capabilities, computing devices with wireless communication capabilities or other processing devices with wireless communication capabilities and connected to a wireless modem, wearable devices with wireless communication capabilities, terminal devices in 5G networks, terminal devices in future evolved public land mobile networks (PLMNs), etc. This is not limited to the embodiments of this application.

[0090] By way of example and not limitation, in the embodiments of this application, the terminal device may alternatively be a wearable device. A wearable device may also be referred to as a wearable intelligent device, which is a general term for wearable devices, such as glasses, gloves, watches, clothing, and shoes, that are intelligently designed and developed for everyday wear by using wearable technology. A wearable device is a portable device that can be worn directly on the body or integrated into a user's clothing or accessories. A wearable device is not only a hardware device, but also realizes powerful functions through software support, data exchange, and cloud interaction. In a broad sense, wearable intelligent devices include full-function and large-scale devices, such as smart watches or smart glasses, that can achieve full or partial functions without relying on a smartphone, and devices that are dedicated to only one type of application function and need to work together with other devices, such as smartphones, such as various smart bands or smart jewelry for monitoring physical symptoms.

[0091] In the embodiments of this application, an apparatus configured to realize the functions of a terminal device may be a terminal device, or may be an apparatus capable of supporting the terminal device in realizing the functions, such as a chip system, and the apparatus may be mounted on the terminal device or used in cooperation with the terminal device. In the embodiments of this application, the chip system may include a chip, or may include a chip and other separate components. In the embodiments of this application, the apparatus for realizing the functions of a terminal device is used only as an example for explanation, but does not constitute a limitation on the solution in the embodiments of this application.

[0092] The network device in the embodiment of this application may be a device configured to communicate with a terminal device. The network device may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiment of this application may be a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. The base station may broadly cover the following names, or may be replaced with the following names, for example, Node B (Node B), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmission and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (MSR) node, home base station, network controller, access node, radio 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), and positioning node. The base station may also be a macro base station, a micro base station, a relay node, a donor node, etc., or a combination thereof. Alternatively, the base station may be a communication module, modem, or chip disposed in the above-mentioned device or apparatus. Alternatively, the base station may be a mobile switching center, a device performing base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, a device performing base station functions in a future communication system, etc.The base stations may support networks using the same access technology or different access technologies. The specific technology used by the network devices and the specific device type are not limited to the embodiments of this application.

[0093] A base station may be fixed or mobile. For example, a helicopter or unmanned aerial vehicle may be configured as a mobile base station, and one or more cells may move based on the location of the mobile base station. In other examples, a helicopter or unmanned aerial vehicle may be configured as a device for communicating with other base stations.

[0094] In some deployments, the network device referred to in the embodiments of this application may be a device including a CU, or a device including a DU, or a device including a CU and a DU, or a device including a control plane CU node (central unit-control plane, CU-CP), a user plane CU node (central unit-user plane, CU-UP) and a DU node.

[0095] In the embodiments of this application, the apparatus for realizing the functions of the network device may be a network device, or may be an apparatus that can support the network device in realizing the functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The apparatus may be installed in the network device or used in cooperation with the network device. In the embodiments of this application, the apparatus for realizing the functions of the network device is used only as an example for explanation, but does not constitute a limitation on the solution in the embodiments of this application.

[0096] The network devices and terminal devices may be deployed on land, on water, or in the air, including indoor or outdoor devices, handheld devices, or vehicle-mounted devices. The scenarios in which the network devices and terminal devices are located are not limited in the embodiments of this application.

[0097] In wireless communication networks, e.g., mobile communication networks, the services supported by the network are becoming increasingly diverse, and therefore the requirements that need to be met are becoming increasingly diverse. For example, networks need to be able to support very high rates, very low latency, and / or a large number of connections. This characteristic increases the complexity of network planning, network configuration, and / or resource scheduling. Furthermore, as networks have increasingly powerful capabilities, e.g., supporting higher and higher spectrum, and supporting new technologies such as higher-order multiple-input multiple-output (MIMO) technology, beamforming, and / or beam management, network energy conservation has become a hot research topic. These new requirements, scenarios, and characteristics pose unprecedented challenges to network planning, operation and maintenance, and efficient operation. To address these challenges, artificial intelligence techniques may be introduced into wireless communication networks to achieve network intelligence.

[0098] To support AI technology in a wireless network, a dedicated AI network element or AI module may be further introduced into the network. When an AI network element is introduced, the AI ​​network element corresponds to an independent network element. When an AI module is introduced, the AI ​​module may be located in a specific network element, and the corresponding network element may be a terminal device, a network device, etc.

[0099] 1 is a diagram of a communication system to which a communication method according to an embodiment of the present application can be applied. As shown in FIG. 1, the communication system 100 may include at least one network device, for example, the network device 110 shown in FIG. 1. The communication system 100 may further include at least one terminal device, for example, the terminal device 120 and the terminal device 130 shown in FIG. 1. The network device 110 may communicate with the terminal device (e.g., the terminal device 120 and the terminal device 130) via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, may communicate with each other by using multiple antenna technology.

[0100] 2 is a diagram of another communication system to which the communication method according to an embodiment of the present application can be applied. Compared with the communication system 100 shown in FIG. 1, the communication system 200 shown in FIG. 2 further includes an AI network element 140. The AI ​​network element 140 is configured to perform AI-related operations, such as building a training dataset or training an AI model.

[0101] In a possible embodiment, network device 110 may transmit data related to the training of an AI model to AI network element 140, which constructs a training dataset and trains the AI ​​model. For example, the data related to the training of an AI model may include data reported by the terminal device. AI network element 140 may transmit results of operations related to the AI ​​model to network device 110, which forwards the results of operations related to the AI ​​model to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, evaluation results or test results for the model, etc. For example, a portion of the trained AI model may be deployed to network device 110, and another portion may be deployed to the terminal device. Alternatively, the trained AI model may be deployed to network device 110. Alternatively, the trained AI model may be deployed to the terminal device.

[0102] It should be understood that in FIG. 2, the AI ​​network element 140 is directly connected to the network device 110 is used only as an example for purposes of illustration. In other scenarios, the AI ​​network element 140 may alternatively be connected to a terminal device. Alternatively, the AI ​​network element 140 may be connected to both the network device 110 and the terminal device. Alternatively, the AI ​​network element 140 may be connected to the network device 110 via a third-party network element. The connection relationship between the AI ​​network element and other network elements is not limited in the embodiments of this application.

[0103] The AI ​​network element 140 may alternatively be disposed as a module in a network device and / or a terminal device, for example, in the network device 110 or terminal device shown in FIG.

[0104] Optionally, the AI ​​node may be deployed in one or more of the following locations in a communications system: an access network device, a terminal device, a core network device, etc. Alternatively, the AI ​​node may be independently deployed, e.g., deployed in a location other than one of the above devices, e.g., in a host or cloud server of an over-the-top (OTT) system. The AI ​​node may communicate with other devices in the communications system, e.g., one or more of a network device, a terminal device, a network element of a core network, etc.

[0105] It can be understood that the number of AI nodes is not limited in this application. For example, when there are multiple AI nodes, the multiple AI nodes may be divided based on functions. For example, different AI nodes perform different functions.

[0106] It may be further understood that an AI node may be an independent device, or may be integrated into the same device to achieve different functions, or may be a network element within a hardware device, or may be a software function running on dedicated hardware, or may be a virtualized function instantiated on a platform (e.g., a cloud platform). The specific form of the AI ​​node is not limited in this application.

[0107] It should be noted that Figures 1 and 2 are merely simplified diagrams of examples for ease of understanding. For example, the communication system may further include other devices, such as a wireless relay device and / or a wireless backhaul device not shown in Figures 1 and 2. In actual applications, the communication system may include multiple network devices and may also include multiple terminal devices. The number of network devices and terminal devices included in the communication system is not limited in the embodiments of this application.

[0108] To facilitate understanding of the solutions in the embodiments of this application, the following describes terms that may be used in the embodiments of this application.

[0109] (1) AI model:

[0110] An AI model is an algorithm or computer program that can realize an AI function. An AI model describes the mapping relationship between the model's inputs and outputs. The type of AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or other machine learning (ML) model.

[0111] (2) Double-ended model:

[0112] A double-sided model may also be called a dual-sided model, a cooperative model, a dual model, a two-sided model, etc. A double-sided model is a model that includes multiple submodels. The multiple submodels included in the model need to be compatible with each other. The multiple submodels may be deployed on different nodes. An auto-encoder (AE) model includes an encoder and a decoder, as shown in FIG. 3. An AE model in which the encoder and decoder are separately deployed on different nodes is a typical bilateral model. The encoder and decoder of an AE model are usually trained together and used in collaboration. The encoder and decoder can be understood as AI models that are compatible with each other. The encoder processes an input V to obtain a processing result z, and the decoder can decode the encoder output z into the expected output V'. One encoder may include one or more submodels, and a decoder compatible with the encoder also includes one or more submodels. An encoder and decoder used in collaboration include the same number of submodels, and the submodels included in the encoder have a one-to-one correspondence with the submodels included in the decoder. The sub-model may be an AI model.

[0113] An autoencoder is an unsupervised learning neural network characterized by using input data as label data. Therefore, an autoencoder can also be understood as a self-supervised learning neural network. An autoencoder may be configured to compress and decompress data. For example, an encoder in an autoencoder may compress (encode) data A to obtain data B, and a decoder in the autoencoder may decompress (decode) data B to restore data A. Alternatively, this can be understood as the decoder performing the inverse operation of the operation performed by the encoder.

[0114] For example, the AI ​​prediction model in the embodiment of this application may include an encoder and a decoder. The encoder and the decoder are used in cooperation. It can be understood that the encoder and the decoder are AI models that are compatible with each other. The encoder and the decoder may be deployed separately in a terminal device and a network device.

[0115] Alternatively, the AI ​​prediction model in the embodiments of this application may be a one-sided model, and the AI ​​prediction model may be deployed on a terminal device or a network device.

[0116] (3) Neural network (NN):

[0117] Neural networks are a specific implementation of AI or machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, making them capable of learning any mapping.

[0118] The neural network may include neurons, where x s and an intercept of 1. The output of the calculation unit is: h W,b (x)=f(W T x)=f(Σ s=1 n W s x s +b) where s=1, 2, ... or n, where n is a natural number greater than 1, and W s x s where is the weight of the neuron, b is the bias of the neuron, and f is the activation function of the neuron, which is used to perform a nonlinear transformation on the features obtained from the neural network to introduce nonlinear features into the neural network and convert the input signal at the neuron into an output signal. The output signal of the activation function may serve as the input of the next convolutional layer. The activation function may be a sigmoid function. A neural network is a network formed by connecting many single neurons together. Specifically, the output of a neuron may be the input of another neuron. The input of each neuron may be connected to the local receptive field of the previous layer to extract features of the local receptive field. The local receptive field may be an area containing several neurons.

[0119] For example, the type of the AI ​​model is a neural network. The AI ​​model in this disclosure may be a deep neural network (DNN). Based on the network construction mode, the DNN may include a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), etc.

[0120] (4) Training dataset and inference data:

[0121] A training dataset is used to train an AI model. The training dataset may include inputs for the AI ​​model, or may include inputs for the AI ​​model and target outputs for the AI ​​model. The training dataset includes one or more training data. The training data may include training samples that are input to the AI ​​model, or may include target outputs for the AI ​​model. The target outputs may also be referred to as labels or label samples.

[0122] In the field of communications, a training dataset may include simulated data collected by using a simulation platform, experimental data collected in an experimental scenario, or actual measurement data collected in a real communications network. Because the geographical environments and channel conditions in which the data are generated are different, such as indoors, outdoors, moving speeds, frequency bands, antenna configurations, etc., the collected data may be classified when the data is acquired. For example, data having the same channel propagation environment and the same antenna configuration may be classified into one type.

[0123] Model training is essentially learning some features of training data from training data. In the process of training an AI model (e.g., a neural network model), the output of the AI ​​model is expected to be as close as possible to the actual desired predicted value. Therefore, the current network predicted value may be compared with the actual desired target value, and the weight vector of each layer of the AI ​​model is updated based on the difference between the predicted value and the target value. (Obviously, before the first update, an initialization process is usually performed, specifically, parameters are pre-configured for all layers of the AI ​​model.) For example, if the network predicted value is large, the weight vector is adjusted to reduce the predicted value, and the adjustment is continued until the AI ​​model can predict the actual desired target value or a value very close to the actual desired target value. Therefore, it is necessary to predefine "how to obtain the difference between the predicted value and the target value through comparison." This is the loss function or objective function. The loss function and objective function are important formulas used to measure the difference between the predicted value and the target value. The loss function is used as an example. A larger output value (loss) of the loss function indicates a larger difference. In this case, training the AI ​​model is a process of minimizing the loss so that the value of the loss function is less than a threshold or meets a target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number and width of layers of the neural network, the weights of neurons, or parameters in the activation functions of neurons.

[0124] The inference data may be used as input to a trained AI model and used for inference by the AI ​​model. During model inference, the inference data is input to the AI ​​model to obtain a corresponding output, i.e., an inference result.

[0125] (5) AI model design:

[0126] AI model design mainly includes a data collection stage (e.g., collecting training data and / or inference data), a model training stage, and a model inference stage, and may further include an inference result application stage.

[0127] Figure 4 shows the AI ​​application framework.

[0128] In the data collection phase, a data source is used to provide training data sets and inference data. In the model training phase, training data provided by the data source is analyzed or trained to obtain an AI model. The AI ​​model represents a mapping relationship between the input and output of the model. Obtaining an AI model through learning by using a model training node is equivalent to obtaining a mapping relationship between the input and output of the model through learning by using training data. In the model inference phase, the AI ​​model obtained through training in the model training phase is used to perform inference based on the inference data provided by the data source to obtain an inference result. This phase can also be understood as follows: inference data is input to the AI ​​model, and output is obtained through the AI ​​model, and the output is the inference result. The inference result may indicate configuration parameters used (executed) by the actor object and / or operations performed by the actor object. The inference result is published in the inference result application phase. For example, the inference result may be planned in a unified manner by an actor entity. For example, the actor entity may send the inference result to one or more actor objects (e.g., a network device or a terminal device) for execution. In other examples, the actor entity may further feed back the model's performance to the data source to facilitate subsequent model update training.

[0129] It may be understood that a communication system may include a network element having artificial intelligence capabilities. The above steps related to AI model design may be performed by one or more network elements having artificial intelligence capabilities. In a possible design, an AI function (e.g., an AI module or AI entity) may be configured in an existing network element in the communication system to perform AI-related operations, such as AI model training and / or inference. For example, the existing network element may be a network device or a terminal device. Alternatively, in another possible design, an independent network element may be introduced into the communication system to perform AI-related operations, such as AI model training. The independent network element may be referred to as an AI network element, an AI node, or the like. The names are not limited in the embodiments of this application. For example, the AI ​​network element may be directly connected to a network device in the communication system or indirectly connected to the network device via a third-party network element. The third-party network element may be a core network element, such as an authentication management function (AMF) network element or a user plane function (UPF) network element, an operation, administration, and maintenance (OAM) network element, a cloud server, or other network element. This is not limited to this. For example, the independent network element may be deployed on one or more of the network device side, the terminal device side, and the core network side. Optionally, the independent network element may be deployed on a cloud-side server. For example, the AI ​​network element 140 is introduced into the communication system shown in FIG. 2.

[0130] Training processes for different models may be deployed on different devices or nodes, or may be deployed on the same device or node. Inference processes for different models may be deployed on different devices or nodes, or may be deployed on the same device or node. For example, the model training stage is performed by a terminal device. After training the compatible encoder and decoder, the terminal device may send model parameters of the decoder to a network device. For example, the model training stage is performed by a network device. After training the compatible encoder and decoder, the network device may indicate the model parameters of the encoder to the terminal device. For example, the model training stage is performed by an independent AI network element. After training the compatible encoder and decoder, the AI ​​network element may send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, a model inference stage corresponding to the encoder is performed on the terminal device, and a model inference stage corresponding to the decoder is performed on the network device.

[0131] The model parameters may include one or more of the following: structural parameters of the model (e.g., the number of layers and / or model weights), input parameters of the model (e.g., input dimensions and the number of input ports), or output parameters of the model (e.g., output dimensions and the number of output ports). It may be understood that the input dimensions may be the size of one piece of input data. For example, when the input data is a sequence, the input dimensions corresponding to the sequence may indicate the length of the sequence. The number of input ports may be the number of input data. Similarly, the output dimensions may be the size of one piece of output data. For example, when the output data is a sequence, the output dimensions corresponding to the sequence may indicate the length of the sequence. The number of output ports may be the number of output data.

[0132] The following further describes examples of training and inference processes for AI predictive models in embodiments of this application.

[0133] The training dataset used to train the AI ​​prediction model includes training samples and sample labels, for example, the training samples are channel information measured at one or more time points, and the sample labels are channel information measured at one or more subsequent time points.

[0134] The specific training process is as follows: The model training node processes channel information measured at one or more time points (i.e., training samples) using an AI prediction model to predict channel information at one or more later time points (i.e., predicted channel information). Then, the difference between the predicted channel information and the corresponding sample labels (i.e., the value of a loss function) is calculated, and the parameters of the AI ​​prediction model are updated based on the value of the loss function, so that the difference between the predicted channel information and the corresponding sample labels (i.e., the loss function) is minimized. For example, the loss function may be minimum mean square error (MSE) or cosine similarity. The above operations are repeated to obtain an AI prediction model that meets the target requirements. The model training node may be a terminal device, a network device, or another network element with AI capabilities in a communication system.

[0135] (6) Channel State Information (CSI):

[0136] In a communication system (e.g., an LTE communication system or an NR communication system), a network device needs to determine configurations such as resources, MCS, and precoding used to schedule a downlink data channel for a terminal device based on CSI. It may be understood that CSI is channel information and can reflect channel characteristics and channel quality. The channel information may also be referred to as a channel response. For example, the CSI may be represented by using a channel matrix. For example, the CSI may include a channel matrix, or the CSI may include a channel eigenvector.

[0137] Measuring CSI means that the receiving end solves channel information based on a reference signal transmitted by the transmitting end, i.e., estimates channel information by using a channel estimation method. The propagation format of a wireless signal in a channel may be expressed as Y = HX + N, where H is CSI, X is a reference signal, N is noise, and Y is a received signal. The reference signal X is known information specified by the terminal device and the network device. After the received signal Y is obtained, channel estimation may be performed by using a channel estimation algorithm, such as the least squares method or the minimum mean square error method. For example, the reference signal X may include one or more of a channel state information reference signal (CSI-RS), a synchronization signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), a demodulation reference signal (DMRS), etc. The CSI-RS, SSB, DMRS, etc. may be used to measure downlink CSI. SRS, DMRS, etc. may be used to measure uplink CSI.

[0138] An FDD communication scenario is used as an example. In the FDD communication scenario, the uplink channel and the downlink channel do not have reciprocity or the reciprocity between the uplink channel and the downlink channel cannot be ensured, so the network device usually transmits a downlink reference signal to the terminal device. The terminal device performs channel measurement and interference measurement based on the received downlink reference signal to estimate downlink channel information. The downlink channel information includes CSI. The CSI is then fed back to the network device, so that the network device obtains downlink CSI.

[0139] For example, the CSI may include at least one of the following: a channel quality indication (CQI), a precoding matrix indicator (PMI), a rank indicator (RI), a CSI-RS resource indicator (CRI), a layer indicator (LI), a reference signal receiving power (RSRP), a signal-to-interference plus noise ratio (SINR), etc. The signal-to-interference plus noise ratio may also be referred to as the signal-to-interference-plus-noise ratio.

[0140] For example, the terminal device may use an AI-based CSI feedback scheme, specifically, may perform feedback by using an AI compression model. Specifically, the terminal device compresses and feeds back CSI by using the AI ​​model, and the network device restores the compressed CSI by using the AI ​​model. A sequence (e.g., a bit sequence) is transmitted in the AI-based CSI feedback, and the overhead is lower than that of conventional CSI report feedback. As described above, the AI ​​prediction model may be a two-sided model. The AI ​​prediction model and the AI ​​compression model may be the same model. Specifically, the encoder may be configured to predict CSI at a future time point and compress the predicted CSI at the future time point. In other words, the output of the encoder is compressed information of the predicted CSI. The decoder may be configured to decode and restore the compressed information of the predicted CSI to obtain the predicted CSI. Alternatively, the AI ​​prediction model and the AI ​​compression model may be different models.

[0141] Unless the moving speed of the terminal device is very slow, the acquired CSI will become outdated due to fast channel changes caused by multipath fading. Faded CSI has a serious adverse effect on various adaptive transmission systems.

[0142] CSI prediction helps alleviate the channel aging problem. CSI prediction means that future CSI is predicted with reference to past CSI by using channel correlation in the time, frequency, and spatial domains. CSI prediction may be realized by several methods, such as linear fitting-based CSI prediction or filtering-based CSI prediction. AI-based CSI prediction methods are generated by introducing AI technology into wireless communication networks. Compared with other methods, AI-based CSI prediction results usually have higher prediction accuracy and require a smaller amount of past CSI. AI-based CSI prediction means that an AI prediction model is acquired through training, so that when current CSI and / or past CSI are input into the AI ​​prediction model, the required future CSI can be output.

[0143] However, in a practical scenario, the CSI prediction result may not accurately reflect the actual channel quality, which will affect the accuracy of subsequent related configurations of network devices.

[0144] For example, when a terminal device feeds back CSI, if an AI prediction model is deployed on the terminal device, the terminal device may feed back future CSI predicted by the AI ​​prediction model to the network device. When the distribution difference between the training data of the AI ​​prediction model and the current data of the AI ​​prediction model is large, the performance of the AI ​​prediction model is affected, and the accuracy of the predicted CSI is further affected. When the accuracy of the predicted CSI is low, the CSI prediction cannot bring about performance gains, which further affects the accuracy of subsequent related configurations of the network device and results in performance degradation.

[0145] In view of this, this application provides a communication method and a communication device for determining channel information based on the accuracy of a channel information prediction result, so that the channel information acquired by a related device can accurately reflect the channel state. The communication method may be applied to the above communication system, for example, an FDD communication scenario. Furthermore, optionally, the communication method may further be applied to a TDD communication scenario, which is not limited in this disclosure.

[0146] In this application, instruction should be understood to include direct instruction (also called explicit instruction) and implicit instruction. Directly indicating information A means including information A. Implicitly indicating information A means indicating information A by directly indicating information B based on the correspondence between information A and information B. The correspondence between information A and information B may be predefined, pre-stored, pre-baked, or pre-configured.

[0147] In this application, it should be understood that the use of information C to determine information D includes the case where information D is determined based on information C only, and also the case where information D is determined based on information C and other information. Furthermore, the use of information C to determine information D may further include the case of indirect determination. For example, information D is determined based on information E, and information E is determined based on information C.

[0148] 5 is a schematic flowchart of a communication method according to the present application. As shown in FIG. 5, the method 500 may include the following steps:

[0149] 510: The first device transmits a first reference signal to the second device.

[0150] In a possible implementation, the second device may be a terminal device, and the first device may be a network device. In this case, the first reference signal may be a downlink reference signal, and the channel information may be downlink channel information. For example, the first reference signal may be one or more of CSI-RS, SSB, DMRS, etc.

[0151] In another possible implementation, the second device may be a network device and the first device may be a terminal device. In this case, the first reference signal may be an uplink reference signal, and the channel information may be uplink channel information. For example, the first reference signal may be one or more of SRS, DMRS, etc.

[0152] 520: Determine whether the p predicted channel information is valid.

[0153] 530: The second device transmits indication information #1 (an example of first indication information) to the first device. The indication information #1 indicates at least one piece of channel information. When p pieces of predicted channel information are valid, the at least one piece of channel information includes p pieces of predicted channel information. Alternatively, when p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal. Alternatively, when p pieces of predicted channel information are invalid, the at least one piece of channel information includes p pieces of predicted channel information and channel information measured based on the first reference signal, where p is a positive integer. The time corresponding to the p pieces of predicted channel information is not earlier than the time of transmission of the indication information #1.

[0154] In step 530, the second device may determine what to feed back to the first device based on whether the p pieces of predicted channel information are valid. For example, the p pieces of predicted channel information may be fed back. In another example, channel information measured based on the first reference signal may be fed back. In another example, channel information measured based on the first reference signal and the p pieces of predicted channel information may be fed back.

[0155] The content of the feedback may be indicated explicitly or implicitly by the instruction information #1.

[0156] The channel information is used to reflect the channel condition. For example, the channel information may be CSI. For example, the CSI may include one or more of CQI, PMI, RI, CRI, LI, RSRP, SINR, etc.

[0157] For example, the predicted channel information may be predicted CSI, and the measured channel information may be measured CSI.

[0158] The measured channel information is channel information obtained through measurements based on a reference signal, and may also be referred to as a measurement result of channel information.

[0159] Predicted channel information is information obtained through prediction. Specifically, channel information at one or more future time points is predicted by using channel information measured at one or more past time points. It should be understood that "past time point" and "future time point" in this specification are relative concepts, provided that a future time point is later than a past time point, i.e., the measurement time point of the measured channel information used for prediction is earlier than the time point at which the prediction needs to be performed. Predicted channel information may also be referred to as a predicted result of channel information.

[0160] The channel information may be predicted in multiple ways. For example, the channel information may be predicted in one or more of the following ways: linear fitting, Kalman filtering, AI model, etc. An AI model-based prediction method is used as an example. Channel information measured at one or more past time points is input into the AI ​​prediction model, and the AI ​​prediction model outputs channel information at one or more future time points.

[0161] It should be understood that the above are merely examples and do not constitute limitations on the solution in this embodiment of this application. Channel information may be predicted in other ways, which is not a limitation in this embodiment of this application.

[0162] The p pieces of predicted channel information may be understood as predicted channel information at p time points. The p time points are time points corresponding to the p pieces of predicted channel information. The first time point may also be called a feedback time point. The p time points are not earlier than the feedback time point.

[0163] For example, the predicted channel information #1 may be obtained by predicting channel information at time T. Specifically, the predicted channel information #1 is the predicted channel information at time T, and the time corresponding to the predicted channel information #1 is time T.

[0164] In a possible implementation, determining whether the p pieces of predicted channel information are valid may be determining the accuracy of channel information prediction. If the channel information prediction is accurate, the p pieces of predicted channel information are valid. If the channel information prediction is inaccurate, the p pieces of predicted channel information are invalid.

[0165] Optionally, step 520 includes determining whether the p pieces of predicted channel information are valid based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, where the n pieces of predicted channel information correspond to the n pieces of measured channel information, and n is a positive integer. The time corresponding to the n pieces of predicted channel information is earlier than the time of transmitting the indication information #1.

[0166] In other words, in step 530, the second device may determine what to feed back to the first device based on the comparison result. For example, p pieces of predicted channel information may be fed back. In another example, channel information measured based on the first reference signal may be fed back. In another example, channel information measured based on the first reference signal and p pieces of predicted channel information may be fed back.

[0167] The n predicted channel information may be understood as predicted channel information at n time points.

[0168] The n pieces of measured channel information may be understood as channel information measured at n time points or channel information obtained through measurements at n time points. The time points corresponding to the measured channel information may be the measurement time points of the channel information.

[0169] The comparison result between the n pieces of predicted channel information and the n pieces of measured channel information may be used to reflect the prediction accuracy, and the second device may determine the content to be fed back to the first device based on the prediction accuracy.

[0170] For ease of explanation, in this embodiment of this application, only the AI ​​predictive model is used as an example for illustration.

[0171] For example, the AI ​​prediction model may be a one-sided model. For example, the one-sided model may be deployed to a second device. In this case, the terminal device may obtain n pieces of predicted channel information by using the AI ​​prediction model. The n pieces of predicted channel information may be stored in the second device.

[0172] Alternatively, the AI ​​prediction model may be a two-sided model. For example, sub-models in the two-sided model may be deployed separately to the second device and the first device. In a possible implementation manner, the instruction information #1 sent by the second device to the first device may indicate p pieces of predicted channel information in the following manner: The instruction information #1 may directly indicate the output result of the sub-model deployed to the second device. The sub-model deployed to the first device may be used to process the output result to obtain p pieces of predicted channel information. For example, n pieces of predicted channel information may be received from the first device. Alternatively, the same model as the sub-model deployed to the first device may be deployed to the second device. Alternatively, the n pieces of predicted channel information may be obtained in other manners. This is not limited to this embodiment of the present application.

[0173] For example, the AI ​​prediction model may be a neural network model, such as an RNN, a long short-term memory (LSTM) network, or a transformer model.

[0174] It should be understood that the above are merely examples, and that the AI ​​prediction model may alternatively use models of other structures, which is not limited in this embodiment of the application.

[0175] The n pieces of predicted channel information and the p pieces of predicted channel information may be obtained through prediction based on the same AI prediction model.

[0176] In this case, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information may be used to reflect the performance of the AI ​​prediction model, or may be used as a monitoring result of the AI ​​prediction model.

[0177] The first time point is the feedback time point, and the p channel information items are channel information items predicted after the feedback time point.

[0178] 540: The first device performs data transmission based on the at least one channel information.

[0179] In the solution of this embodiment of the present application, the content to be fed back to the first device, i.e., the content indicated by the first indication information, is determined based on whether the p pieces of predictive channel information are valid, and it is expected that the channel information acquired by the first device can accurately reflect the channel state. For example, when the p pieces of predictive channel information are invalid, the channel information fed back to the first device includes at least channel information measured based on the first reference signal. In this way, the first device can acquire channel information that can more accurately reflect the channel state and avoid performance degradation that may occur when the first device performs data transmission based on inaccurate predictive channel information. In another example, when the p pieces of predictive channel information are valid, the p pieces of predictive channel information may be fed back to the first device, so that the first device can perform data transmission based on the predictive channel information and mitigate the channel aging problem. Furthermore, when the p pieces of predictive channel information are invalid, some of the p pieces of predictive channel information may be accurate. The second device may feed back the channel information measured based on the first reference signal and the p pieces of predicted channel information to the first device, so that the first device can perform subsequent processing based on the p pieces of predicted channel information. For example, the first device may transmit a reference signal based on a time corresponding to the p pieces of predicted channel information and continue to perform the method in this embodiment of the present application. It should be understood that the above is merely an example and does not constitute a limitation on the solution in this embodiment of the present application. For example, the transmission time of the reference signal, the time corresponding to the p pieces of predicted channel information, the transmission time of the indication information #1, etc. may alternatively be preset.

[0180] Furthermore, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information may be used to reflect the accuracy of the channel information prediction. In this way, whether the p pieces of predicted channel information are valid can be determined based on the accuracy of the channel information prediction, and the content indicated by the first indication information can further determine whether the channel information acquired by the first device can accurately reflect the channel state. For example, if the channel information prediction is accurate, it may be determined that the p pieces of predicted channel information are valid. In another example, if the channel information prediction is inaccurate, it may be determined that the p pieces of predicted channel information are invalid.

[0181] When n>1, the n pieces of predicted channel information may be obtained through one prediction, or may be obtained through multiple predictions.

[0182] Obtaining n pieces of predicted channel information through one prediction may be understood as obtaining n pieces of predicted channel information through prediction based on the same measured channel information. An AI prediction model is used as an example. The n pieces of predicted channel information may be obtained based on the same model input. For example, one or more pieces of measured channel information are input to the AI ​​prediction model for processing, and the measurement time point of one or more pieces of measured channel information is earlier than time point T'. The AI ​​prediction model may predict channel information at n' time points after T' and output n' pieces of predicted channel information. The n pieces of predicted channel information may be part or all of the n' pieces of predicted channel information. n' is an integer greater than 1.

[0183] The n pieces of predicted channel information obtained through multiple predictions can be understood as the n pieces of predicted channel information obtained through predictions based on different measured channel information. An AI prediction model is used as an example. The n pieces of predicted channel information may be obtained based on different model inputs.

[0184] As described above, there is a correspondence between the n pieces of predicted channel information and the n pieces of measured channel information.

[0185] For example, the correspondence may be predefined. Alternatively, the correspondence may be indicated by the first device.

[0186] For example, n may be 1, and n pieces of predictive channel information may be fed back at time T'', and the first device may broadcast a reference signal to indicate time T''. The second device acquires channel information through measurements based on the reference signal. There is a correspondence between the predictive channel information fed back at time T'' and the channel information acquired through measurements based on the reference signal. The second device may use the channel information acquired through measurements based on the reference signal as the n pieces of measured channel information, and use the predictive channel information fed back at time T'' as the n pieces of predictive channel information.

[0187] In another example, the first device may transmit a reference signal. The second device may acquire channel information through measurements based on the reference signal. There is a correspondence between the predicted channel information previously fed back by the second device and the channel information acquired through measurements based on the reference signal. The second device may use the channel information acquired through measurements based on the reference signal as the n pieces of measured channel information and the predicted channel information previously fed back as the n pieces of predicted channel information.

[0188] Optionally, the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and a difference between a time point corresponding to the i-th predicted channel information and a time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .., n.

[0189] In other words, for a group of predicted channel information and measured channel information having a corresponding relationship, the difference between the time point corresponding to the predicted channel information and the time point corresponding to the measured channel information is equal to or less than a first threshold.

[0190] For example, the first threshold may be predefined, indicated by the first device, or determined by the second device.

[0191] For example, the first threshold is equal to or less than the coherence time.

[0192] In this case, the time corresponding to the n predicted channel information is close to the time corresponding to the n measured channel information, and the comparison result obtained in this case can more accurately reflect the accuracy of the channel information prediction, which helps to avoid interference caused by time factors.

[0193] For example, the n pieces of measured channel information may not include channel information measured based on the first reference signal.

[0194] Optionally, the n pieces of measured channel information may include channel information measured based on the first reference signal.

[0195] For the channel information used for comparison, a time point closer to the time point corresponding to the p pieces of predicted channel information indicates that the comparison result of the channel information used for comparison can better reflect the accuracy of the prediction result around the time point corresponding to the p pieces of predicted channel information. The time point corresponding to the p pieces of predicted channel information is not earlier than the time point at which the first instruction information is transmitted. The first reference signal may be a reference signal at a time point closest to the time point at which the first instruction information is transmitted, and the channel information measured based on the first reference signal can more accurately reflect the channel conditions at the time point at which the first instruction information is transmitted. In the solution of this embodiment of the present application, the n pieces of measured channel information include channel information measured based on the first reference signal. This helps to determine the accuracy of channel information prediction around the time point corresponding to the p pieces of predicted channel information, helps to more accurately determine whether the p pieces of predicted channel information are valid, and helps to ensure that the first device obtains more accurate channel information.

[0196] The p pieces of predicted channel information may be obtained through prediction based on the m pieces of measured channel information, where m is a positive integer.

[0197] For example, m pieces of measured channel information are input to an AI prediction model for processing. The AI ​​prediction model may predict channel information at p' time points after a first time point and output p' pieces of predicted channel information. The p pieces of predicted channel information may be all or a portion of the p' pieces of predicted channel information. In other words, the p pieces of channel information may be all or a portion of the predicted channel information output by the AI ​​prediction model.

[0198] The m pieces of measurement channel information may be completely or partially the same as the n pieces of measurement channel information. Alternatively, the m pieces of measurement channel information may be completely different from the n pieces of measurement channel information. This is not limited in this embodiment of the present application.

[0199] Furthermore, the m pieces of measured channel information may include channel information measured based on the first reference signal.

[0200] For the measured channel information used to predict channel information at a future time point, a time point closer to the time point at which the prediction needs to be performed usually indicates higher accuracy of the predicted channel information. The time point corresponding to the p predicted channel information is not earlier than the time point at which the first indication information is transmitted. In the solution of this embodiment of this application, the first reference signal may be a reference signal at a time point closest to the time point at which the first indication information is transmitted, and the time point corresponding to the channel information measured based on the first reference signal is closer to the time point corresponding to the p predicted channel information. The n measured channel information includes channel information measured based on the first reference signal, i.e., the channel information measured based on the first reference signal is used to determine the p predicted channel information, so that the p predicted channel information is more accurate.

[0201] Optionally, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is one of the following: The channel correlation may include at least one of a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

[0202] The difference may be used as a prediction error, which is used to reflect the accuracy of the prediction result of the channel information.

[0203] The difference between the predicted channel information and the measured channel information may include one or more differences, which may be represented by one or more difference indicators.

[0204] For example, the difference measure may include MSE, normalized mean square error (NMSE), and the like.

[0205] The channel correlation may be used to reflect the accuracy of the predicted results of the channel information.

[0206] The channel correlation between the predicted channel information and the measured channel information may include one or more channel correlations, which may be represented by one or more channel correlation indices.

[0207] For example, the channel correlation measure may include generalized cosine similarity (GCS), squared generalized cosine similarity (SGCS), and so on.

[0208] The comparison result between the n pieces of predicted channel information and the n pieces of measured channel information may also be referred to as the comparison result between n groups of predicted channel information and measured channel information, where in each group, the predicted channel information corresponds to the measured channel information.

[0209] As mentioned above, the comparison result is used to reflect the accuracy of the channel information prediction. A smaller difference between the predicted channel information and the measured channel information of a group indicates a higher prediction accuracy. Alternatively, a higher channel correlation between the predicted channel information and the measured channel information of a group indicates a higher prediction accuracy.

[0210] When the prediction is inaccurate, the at least one piece of channel information includes channel information measured based on the first reference signal. In other words, the content fed back by the second device to the first device includes channel information measured based on the first reference signal.

[0211] In other words, when the prediction is inaccurate, the content fed back by the second device to the first device includes at least the actual measured channel information, thereby enabling the first device to obtain more accurate channel information.

[0212] When the prediction is accurate, the at least one piece of channel information includes p pieces of predicted channel information. In other words, the content fed back by the second device to the first device may include p pieces of predicted channel information.

[0213] When the prediction is accurate, the second device may feed back the predicted channel information to the first device. In this way, by using channel information prediction, the channel aging problem can be mitigated.

[0214] In the following, the case where n=1 (Example 1) and the case where n>1 (Example 2) are separately used as examples to explain the manner of determining at least one piece of channel information.

[0215] Example 1:

[0216] When n=1, step 520 can be understood as determining whether p pieces of predicted channel information are valid based on the comparison results between the predicted channel information and the measured channel information of a group, in other words, determining at least one piece of channel information based on the comparison results between the predicted channel information and the measured channel information of the group.

[0217] For example, the method for determining at least one piece of channel information may be realized by the following methods (method 1 to method 4).

[0218] Method 1:

[0219] Optionally, the at least one piece of channel information includes channel information measured based on a first reference signal. In other words, the content fed back by the second device to the first device includes channel information measured based on the first reference signal. If a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 1, it is determined that the p pieces of predicted channel information are invalid.

[0220] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy the preset condition 1, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal.

[0221] In other words, when a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 1, the prediction result may be determined to be inaccurate, and the content fed back to the first device may include at least channel information measured based on the first reference signal. When a difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1, the prediction result may be determined to be accurate, and the content fed back to the first device may not include channel information measured based on the first reference signal. For example, when the prediction result is determined to be accurate, and the content fed back to the first device may include p pieces of predicted channel information.

[0222] Method 2:

[0223] Optionally, step 520 may include: the at least one piece of channel information includes channel information measured based on a first reference signal; in other words, the content fed back by the second device to the first device includes channel information measured based on the first reference signal; and if the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2, it is determined that the p pieces of predicted channel information are invalid.

[0224] If the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy the preset condition 2, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal.

[0225] In other words, when the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2, the prediction result may be determined to be inaccurate, and the content fed back to the first device may include at least channel information measured based on the first reference signal. When the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1, the prediction result may be determined to be accurate, and the content fed back to the first device may not include channel information measured based on the first reference signal. For example, when the prediction result is determined to be accurate, the content fed back to the first device may include p pieces of predicted channel information.

[0226] Method 3:

[0227] Optionally, it is determined that p pieces of predicted channel information are invalid. At least one piece of channel information includes channel information measured based on a first reference signal. In other words, the content fed back by the second device to the first device includes channel information measured based on the first reference signal. A difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 1, and a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2.

[0228] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1, or the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 2, the p pieces of predicted channel information are determined to be valid. At least one piece of channel information may not include channel information measured based on the first reference signal.

[0229] In other words, when a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 1 and a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2, the prediction result may be determined to be inaccurate, and the content to be fed back to the first device may include at least channel information measured based on the first reference signal. When a difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1 or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 2, the prediction result may be determined to be accurate, and the content to be fed back to the first device may not include channel information measured based on the first reference signal. For example, when the prediction result is determined to be accurate, the content to be fed back to the first device may include p pieces of predicted channel information.

[0230] Method 4:

[0231] Optionally, it is determined that p pieces of predicted channel information are invalid. At least one piece of channel information includes channel information measured based on a first reference signal. In other words, the content fed back by the second device to the first device includes channel information measured based on the first reference signal. A difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 1, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2.

[0232] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1, and the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 2, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal.

[0233] In other words, when the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1 or the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies preset condition 2, the prediction result may be determined to be inaccurate, and the content to be fed back to the first device includes at least channel information measured based on the first reference signal. When the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 1 and the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 2, the prediction result may be determined to be accurate, and the content to be fed back to the first device may not include channel information measured based on the first reference signal. For example, when the prediction result is determined to be accurate, the content to be fed back to the first device may include p pieces of predicted channel information.

[0234] Preset Condition 1 and Preset Condition 2 are explained below by using an example.

[0235] The difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies the preset condition 1 may include: the difference between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a difference threshold corresponding to the difference.

[0236] For example, the differences between the n pieces of predicted channel information and the n pieces of measured channel information satisfying preset condition 1 may include: all differences between the n pieces of predicted channel information and the n pieces of measured channel information are greater than or equal to difference thresholds corresponding to all differences.

[0237] For example, the n pieces of predicted channel information may be predicted channel information #2, and the n pieces of measured channel information may be measured channel information #2. All the differences between the predicted channel information #2 and the measured channel information #2 may include two differences between the predicted channel information #2 and the measured channel information #2, such as the MSE between the predicted channel information #2 and the measured channel information #2, and the NMSE between the predicted channel information #2 and the measured channel information #2.

[0238] The difference between n pieces of predicted channel information and n pieces of measured channel information satisfies the preset condition 1 if: the MSE between predicted channel information #2 and measured channel information #2 is greater than or equal to the difference threshold corresponding to MSE, and the NMSE between predicted channel information #2 and measured channel information #2 is greater than or equal to the difference threshold corresponding to NMSE.

[0239] Alternatively, the satisfaction of the preset condition 1 of the differences between the n pieces of predicted channel information and the n pieces of measured channel information may include: a portion of the differences between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a difference threshold corresponding to a portion of the differences.

[0240] The number of the partial differences may be set based on requirements, for example, the partial differences may be at least Z differences, and the setting of Z may be adjusted based on the number of all differences.

[0241] For example, the n pieces of predicted channel information may be predicted channel information #2, and the n pieces of measured channel information may be measured channel information #2. All differences between the predicted channel information #2 and the measured channel information #2 may include two differences between the predicted channel information #2 and the measured channel information #2, such as the MSE between the predicted channel information #2 and the measured channel information #2, and the NMSE between the predicted channel information #2 and the measured channel information #2. Z may be 1.

[0242] The difference between n pieces of predicted channel information and n pieces of measured channel information satisfies the preset condition 1 if: the MSE between predicted channel information #2 and measured channel information #2 is equal to or greater than the difference threshold corresponding to MSE, or the NMSE between predicted channel information #2 and measured channel information #2 is equal to or greater than the difference threshold corresponding to NMSE.

[0243] The channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies the preset condition 2 may include: the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a similarity threshold corresponding to the channel correlation.

[0244] For example, the channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information satisfying the preset condition 2 may include: all channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information are less than or equal to a similarity threshold corresponding to all channel correlations.

[0245] For example, the n pieces of predicted channel information may be predicted channel information #2, and the n pieces of measured channel information may be measured channel information #2. All channel correlations between the predicted channel information #2 and the measured channel information #2 may include two channel correlations between the predicted channel information #2 and the measured channel information #2, for example, the GCS between the predicted channel information #2 and the measured channel information #2, and the SGCS between the predicted channel information #2 and the measured channel information #2.

[0246] The channel correlation between n pieces of predicted channel information and n pieces of measured channel information satisfies the preset condition 2 if: the GCS between predicted channel information #2 and measured channel information #2 is equal to or less than the similarity threshold corresponding to the GCS, and the SGCS between predicted channel information #2 and measured channel information #2 is equal to or less than the similarity threshold corresponding to the SGCS.

[0247] Alternatively, the channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information satisfying the preset condition 2 may include: a portion of the channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information is less than or equal to a similarity threshold corresponding to a portion of the channel correlations.

[0248] The number of the partial channel correlation indices may be set based on requirements. For example, the partial channel correlation may be at least Z' channel correlations. The setting of Z' may be adjusted based on the number of all channel correlation indices.

[0249] For example, the n pieces of predicted channel information may be predicted channel information #2, and the n pieces of measured channel information may be measured channel information #2. All channel correlations between the predicted channel information #2 and the measured channel information #2 may include two channel correlations between the predicted channel information #2 and the measured channel information #2, for example, the GCS between the predicted channel information #2 and the measured channel information #2 and the SGCS between the predicted channel information #2 and the measured channel information #2. Z may be 1. Z' may be 1. The channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information satisfy the pre-set condition 2 when: the GCS between the predicted channel information #2 and the measured channel information #2 is equal to or less than the similarity threshold corresponding to the GCS, or the SGCS between the predicted channel information #2 and the measured channel information #2 is equal to or less than the similarity threshold corresponding to the SGCS.

[0250] It should be understood that the above are just examples, and the preset condition 1 and the preset condition 2 may be set based on requirements.

[0251] Additionally, the above decision criteria may be used in combination.

[0252] For example, the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: all differences between the n pieces of predicted channel information and the n pieces of measured channel information are equal to or greater than the corresponding difference thresholds; all channel correlations between the n predicted channel information and the n measured channel information are less than or equal to a similarity threshold corresponding to all channel correlations; or A portion of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a difference threshold corresponding to the portion of the difference, or a portion of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a similarity threshold corresponding to the portion of the channel correlation. When any one of the following conditions is met, it is determined that the p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on the first reference signal.

[0253] The above combination schemes are merely examples, which are not limiting in this embodiment of this application.

[0254] Example 2:

[0255] When n>1, step 520 can be understood as determining whether p pieces of predicted channel information are valid based on the comparison results between the predicted channel information and the measured channel information of multiple groups, in other words, determining the content to be fed back to the first device based on the comparison results between the predicted channel information and the measured channel information of multiple groups.

[0256] Below, methods 5 to 9 are used as examples to explain step 520.

[0257] Method 5:

[0258] Referring to the condition of Example 1, a determination is made for n groups of predicted channel information and measured channel information. Specifically, the determination result obtained based on the predicted channel information and measured channel information of y groups among the n groups of predicted channel information and measured channel information is that the prediction result is inaccurate, and the content to be fed back to the first device is determined based on y, where y is an integer equal to or greater than 0.

[0259] In other words, the determination result obtained based on the y groups of predicted channel information and measured channel information is that the prediction result is inaccurate. If y is large, the at least one piece of channel information includes channel information measured based on the first reference signal. If y is not large, the at least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0260] For example, when y is equal to or greater than a specified threshold, it is determined that the p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on the first reference signal. When y is less than a specified threshold, it is determined that the p pieces of predicted channel information are valid, and at least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0261] For example, when the ratio of y to n is equal to or greater than a specified threshold, it is determined that p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on the first reference signal. When the ratio of y to n is less than a specified threshold, it is determined that p pieces of predicted channel information are valid, and at least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0262] In the following, methods 1 to 4 are used as examples to explain possible implementations of method 5.

[0263] For example, p pieces of predicted channel information are determined to be invalid, and at least one piece of channel information includes channel information measured based on a first reference signal. A difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 1. y is equal to or greater than threshold #2, or the ratio of y to n is equal to or greater than threshold #3 (an example of a second threshold).

[0264] The difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 1. When y is less than threshold #2 or the ratio of y to n is less than threshold #3, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0265] For example, p pieces of predicted channel information are determined to be invalid, and at least one piece of channel information includes channel information measured based on a first reference signal. The channel correlation between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 2. y is equal to or greater than threshold #2, or the ratio of y to n is equal to or greater than threshold #3.

[0266] The difference between y pieces of predicted channel information among the n pieces of predicted channel information and the corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 2. When y is less than threshold #2 or the ratio of y to n is less than threshold #3, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0267] For example, p pieces of predicted channel information are determined to be invalid, and at least one piece of channel information includes channel information measured based on a first reference signal, the difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 2, and the channel correlation between the y pieces of predicted channel information and corresponding y pieces of measured channel information satisfies preset condition 2, y is greater than or equal to threshold #2, or the ratio of y to n is greater than or equal to threshold #3.

[0268] The difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 1, and the channel correlation between the y pieces of predicted channel information and corresponding y pieces of measured channel information satisfies preset condition 2. When y is less than threshold #2 or the ratio of y to n is less than threshold #3, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0269] For example, p pieces of predicted channel information are determined to be invalid, and at least one piece of channel information includes channel information measured based on a first reference signal. The difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 2, or the channel correlation between the y pieces of predicted channel information and corresponding y pieces of measured channel information satisfies preset condition 2. y is greater than or equal to threshold #2, or the ratio of y to n is greater than or equal to threshold #3.

[0270] The difference between y pieces of predicted channel information among the n pieces of predicted channel information and corresponding y pieces of measured channel information among the n pieces of measured channel information satisfies preset condition 1, or the channel correlation between the y pieces of predicted channel information and corresponding y pieces of measured channel information satisfies preset condition 2. When y is less than threshold #2, or the ratio of y to n is less than threshold #3, it is determined that the p pieces of predicted channel information are valid. At least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes p pieces of predicted channel information.

[0271] It should be understood that the above are merely examples and do not constitute limitations on the solutions in this embodiment of this application.

[0272] Method 6:

[0273] Optionally, it is determined that p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on a first reference signal, and a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 3.

[0274] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy the preset condition 3, it is determined that the p pieces of predicted channel information are valid. The at least one piece of channel information may not include the channel information measured based on the first reference signal. For example, the at least one piece of channel information includes the p pieces of predicted channel information.

[0275] Method 7:

[0276] Optionally, it is determined that p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on a first reference signal, and a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 4.

[0277] If the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy the preset condition 4, it is determined that the p pieces of predicted channel information are valid. The at least one piece of channel information may not include the channel information measured based on the first reference signal. For example, the at least one piece of channel information includes the p pieces of predicted channel information.

[0278] Method 8:

[0279] Optionally, it is determined that p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on a first reference signal, and a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 3, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 4.

[0280] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 3, and the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 4, it is determined that the p pieces of predicted channel information are valid. The at least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes the p pieces of predicted channel information.

[0281] Method 9:

[0282] Optionally, it is determined that p pieces of predicted channel information are invalid, and at least one piece of channel information includes channel information measured based on a first reference signal, and a difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 3, and a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies a preset condition 4.

[0283] If the difference between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 3, or the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information does not satisfy preset condition 4, it is determined that the p pieces of predicted channel information are valid. The at least one piece of channel information may not include channel information measured based on the first reference signal. For example, the at least one piece of channel information includes the p pieces of predicted channel information.

[0284] Preset Condition 3 and Preset Condition 4 are explained below by using an example.

[0285] The difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfying the preset condition 3 may include: a statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a difference threshold corresponding to the difference.

[0286] The statistical value may be a maximum, minimum, average, weighted average, sum, etc.

[0287] When the weighted average is calculated, the weight corresponding to each group may be set based on requirements, for example, a group closer to the current time corresponds to a larger weight.

[0288] For example, the differences between the n pieces of predicted channel information and the n pieces of measured channel information satisfy the preset condition 3 including: the statistics of all differences between the n pieces of predicted channel information and the n pieces of measured channel information are greater than or equal to the difference thresholds corresponding to all differences;

[0289] The different differences may correspond to the same statistical value or different statistical values.

[0290] For example, the n pieces of predicted channel information may include predicted channel information #2 and predicted channel information #3, and the n pieces of measured channel information may include measured channel information #2 and measured channel information #3. All differences may include two differences, namely, MSE and NMSE. The statistic corresponding to MSE may be an average value. The statistic corresponding to NMSE may be a minimum value. All differences between the n pieces of predicted channel information and the n pieces of measured channel information may include MSE between predicted channel information #2 and measured channel information #2, NMSE between predicted channel information #2 and measured channel information #2, MSE between predicted channel information #3 and measured channel information #3, and NMSE between predicted channel information #3 and measured channel information #3.

[0291] The difference between n pieces of predicted channel information and n pieces of measured channel information satisfies preset condition 3 if: the average value of the MSE between predicted channel information #2 and measured channel information #2 and the average value of the MSE between predicted channel information #3 and measured channel information #3 are equal to or greater than the difference threshold corresponding to MSE, and the smaller value of the NMSE between predicted channel information #2 and measured channel information #2 and the NMSE between predicted channel information #3 and measured channel information #3 is equal to or greater than the difference threshold corresponding to NMSE.

[0292] Alternatively, the difference between the n pieces of predicted channel information and the n pieces of measured channel information satisfies the preset condition 3 includes: a statistical value of a portion of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a difference threshold corresponding to the portion of the difference.

[0293] The number of the partial differences may be set based on requirements, for example, the partial differences may be at least Z differences, and the setting of Z may be adjusted based on the number of all differences.

[0294] For example, the n pieces of predicted channel information may include predicted channel information #2 and predicted channel information #3, and the n pieces of measured channel information may include measured channel information #2 and measured channel information #3. All differences may include two differences, namely, MSE and NMSE. The statistic corresponding to MSE may be an average value. The statistic corresponding to NMSE may be a minimum value. All differences between the n pieces of predicted channel information and the n pieces of measured channel information may include MSE between predicted channel information #2 and measured channel information #2, NMSE between predicted channel information #2 and measured channel information #2, MSE between predicted channel information #3 and measured channel information #3, and NMSE between predicted channel information #3 and measured channel information #3.

[0295] Z may be 1. The difference between n pieces of predicted channel information and n pieces of measured channel information satisfies preset condition 3 if: the average value of the MSE between predicted channel information #2 and measured channel information #2 and the average value of the MSE between predicted channel information #3 and measured channel information #3 is equal to or greater than the difference threshold corresponding to MSE, or the smaller value of the NMSE between predicted channel information #2 and measured channel information #2 and the NMSE between predicted channel information #3 and measured channel information #3 is equal to or greater than the difference threshold corresponding to NMSE.

[0296] The channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies the preset condition 4 including the following: the statistical value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is less than or equal to the similarity threshold corresponding to the channel correlation;

[0297] The statistical value may be a maximum, minimum, average, weighted average, sum, etc.

[0298] When the weighted average is calculated, the weight corresponding to each group may be set based on requirements, for example, a group closer to the current time corresponds to a larger weight.

[0299] For example, the channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information satisfy the preset condition 4 including the following: the statistics of all channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information are less than or equal to the similarity threshold corresponding to all channel correlations.

[0300] Different channel correlations may correspond to the same statistics or different statistics.

[0301] For example, the n pieces of predicted channel information may include predicted channel information #2 and predicted channel information #3, and the n pieces of measured channel information may include measured channel information #2 and measured channel information #3. All channel correlations may include two channel correlations, namely, GCS and SGCS. The statistic corresponding to GCS may be an average value. The statistic corresponding to SGCS may be a maximum value. All channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information may include the GCS between predicted channel information #2 and measured channel information #2, the SGCS between predicted channel information #2 and measured channel information #2, the GCS between predicted channel information #3 and measured channel information #3, and the SGCS between predicted channel information #3 and measured channel information #3.

[0302] The channel correlation between n pieces of predicted channel information and n pieces of measured channel information satisfies preset condition 4 if: the average value of the GCS between predicted channel information #2 and measured channel information #2 and the average value of the GCS between predicted channel information #3 and measured channel information #3 are equal to or less than the channel correlation threshold corresponding to the GCS, and the larger value of the SGCS between predicted channel information #2 and measured channel information #2 and the SGCS between predicted channel information #3 and measured channel information #3 is equal to or less than the channel correlation threshold corresponding to the SGCS.

[0303] Alternatively, the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information satisfies the preset condition 4 including: a statistical value of a portion of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a channel correlation threshold corresponding to a portion of the channel correlation.

[0304] The number of the portion of the channel correlations may be set based on requirements. For example, the portion of the channel correlations may be at least Z' different. The setting of Z' may be adjusted based on the number of all the channel correlations.

[0305] For example, the n pieces of predicted channel information may include predicted channel information #2 and predicted channel information #3, and the n pieces of measured channel information may include measured channel information #2 and measured channel information #3. All channel correlations may include two channel correlations, namely, GCS and SGCS. The statistic corresponding to GCS may be an average value. The statistic corresponding to SGCS may be a maximum value. All channel correlations between the n pieces of predicted channel information and the n pieces of measured channel information may include the GCS between predicted channel information #2 and measured channel information #2, the SGCS between predicted channel information #2 and measured channel information #2, the GCS between predicted channel information #3 and measured channel information #3, and the SGCS between predicted channel information #3 and measured channel information #3.

[0306] Z' may be 1. The channel correlation between n pieces of predicted channel information and n pieces of measured channel information satisfies the preset condition 4 if: the average value of the GCS between predicted channel information #2 and measured channel information #2 and the average value of the GCS between predicted channel information #3 and measured channel information #3 is equal to or less than the channel correlation threshold corresponding to the GCS, or the larger value of the SGCS between predicted channel information #2 and measured channel information #2 and the SGCS between predicted channel information #3 and measured channel information #3 is equal to or less than the channel correlation threshold corresponding to the SGCS.

[0307] It should be understood that the above are just examples, and preset condition 3 and preset condition 4 may be set based on requirements.

[0308] Furthermore, the above decision criteria may be used in combination. For the combination method, please refer to Example 1. The details will not be described again in this specification.

[0309] Furthermore, a label may be added to the channel information fed back by the second device to the first device to indicate whether the fed back channel information is a measurement result or a prediction result.

[0310] Optionally, the indication information #1 further indicates a label of the at least one piece of channel information, where the label of the at least one piece of channel information indicates that the at least one piece of channel information is a predicted result or a measured result, respectively.

[0311] The label of the channel information measured based on the first reference signal indicates that the channel information measured based on the first reference signal is a measurement result, and the labels of the p pieces of predicted channel information indicate that the p pieces of predicted channel information are prediction results.

[0312] Furthermore, a time reference point may be added to the channel information fed back by the second device to the first device to indicate the time point corresponding to the fed back channel information.

[0313] Optionally, the indication information #1 further indicates a time reference point of the at least one channel information, wherein the time reference points of the at least one channel information respectively indicate time points corresponding to the at least one channel information.

[0314] The time reference point of the p pieces of predicted channel information indicates the time point corresponding to the p pieces of predicted channel information.

[0315] The time reference point corresponding to the channel information measured based on the first reference signal indicates a measurement time point of the channel information measured based on the first reference signal, and the measurement time point of the channel information measured based on the first reference signal is a time point for measuring the first reference channel.

[0316] Optionally, when the at least one channel information includes p pieces of predicted channel information, the indication information #1 further indicates time reference points of the p pieces of predicted channel information, where the time reference points of the p pieces of predicted channel information respectively indicate time points corresponding to the p pieces of predicted channel information.

[0317] Optionally, when the at least one channel information includes p pieces of predicted channel information and channel information measured based on the first reference signal, the indication information #1 further indicates time reference points of the p pieces of predicted channel information, where the time reference points of the p pieces of predicted channel information respectively indicate time points corresponding to the p pieces of predicted channel information.

[0318] For example, the first device may send instruction information to instruct the second device to perform steps 520 and 530 .

[0319] Alternatively, the second device may perform steps 520 and 530 periodically.

[0320] The period may be predefined, indicated by the first device, or determined by the second device.

[0321] Alternatively, the second device may decide to perform steps 520 and 530 .

[0322] The following describes step 540 by using an example.

[0323] After receiving the indication information #1, the first device may perform data transmission based on at least one piece of channel information.

[0324] In a possible implementation manner, when the at least one piece of channel information includes channel information measured based on the first reference signal, the first device may perform data transmission by using the channel information measured based on the first reference signal. When the at least one piece of channel information does not include channel information measured based on the first reference signal, the first device may perform data transmission based on the p pieces of predicted channel information.

[0325] For example, the first device may determine, based on the label, that at least one piece of channel information indicated by the indication information #1 is a predicted result or a measured result.

[0326] In other words, the first device may determine, based on the label, that at least one channel information indicated by the indication information #1 includes p pieces of predicted channel information and / or channel information measured based on the first reference signal.

[0327] For example, the first device may determine, based on the time reference point, that at least one piece of channel information indicated by the indication information #1 is a predicted result or a measured result.

[0328] Specifically, the first device may determine a time point corresponding to the channel information based on the time reference point, and the time point corresponding to the channel information may be used to determine a prediction result or a measurement result.

[0329] For example, if the time point corresponding to at least one piece of channel information indicated by the instruction information #1 is before the feedback time point, the channel information is a measurement result. In another example, if the time point corresponding to at least one piece of channel information indicated by the instruction information #1 is after the feedback time point, the channel information is a prediction result.

[0330] In another example, the time reference point indicated by the instruction information #1 only includes the time reference point of the prediction result, but does not include the time reference point of the measurement result. In this case, if the channel information indicated by the instruction information #1 includes channel information without a time reference point, the first device may determine that the channel information indicated by the instruction information #1 includes the measurement result.

[0331] Optionally, the method 500 further includes: the second device sends indication information #2 (an example of second indication information) to the first device, the indication information #2 indicating the comparison result.

[0332] For example, the indication information #2 may indicate the difference and / or channel correlation between the n predicted channel information pieces and the n measured channel information pieces.

[0333] The above describes a solution in which the second device determines the feedback content based on the comparison result. In another possible implementation, the first device may instead determine the information used for data transmission based on the comparison result. The following describes another possible implementation.

[0334] In a possible implementation, steps 520 to 540 in the method 500 may alternatively be replaced with the following steps:

[0335] 521: The second device sends indication information #3 to the first device, where the indication information #3 indicates a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, the channel information measured based on the first reference signal, and the p pieces of predicted channel information.

[0336] 531: The second device selects, based on the comparison result, at least one piece of channel information from the channel information measured based on the first reference signal and the p pieces of predicted channel information, and performs data transmission.

[0337] In steps 521 and 531, the second device transmits the comparison result to the first device, and the first device determines channel information to be used for data transmission based on the comparison result.

[0338] Alternatively, in step 521, the second device may further transmit the n pieces of measurement channel information to the first device.

[0339] When the first device stores n pieces of predicted channel information corresponding to the n pieces of measured channel information, the first device may perform a comparison to obtain a comparison result, and further determine channel information to be used for data transmission based on the comparison result.

[0340] When the second device stores n pieces of predicted channel information corresponding to the n pieces of measured channel information, the first device may receive the n pieces of predicted channel information from the second device, and the first device performs a comparison to obtain a comparison result, and further determines channel information to be used for data transmission based on the comparison result.

[0341] 6 is a diagram of another communication method according to an embodiment of the present application. As shown in FIG. 6, the method 600 includes the following steps:

[0342] 610: The first device transmits a second reference signal to the second device.

[0343] 620: The first device receives indication information #4 (an example of third indication information) transmitted by the second device. The indication information #4 indicates q pieces of predicted channel information. The time corresponding to the q pieces of predicted channel information is not earlier than the time of transmission of the indication information #4. q is a positive integer.

[0344] 630: The first device transmits a third reference signal to the second device.

[0345] 640: The first device receives indication information #5 (an example of fourth indication information) transmitted by the second device. The indication information #5 indicates q' pieces of predicted channel information and channel information measured based on a third reference signal. Alternatively, the indication information #5 indicates channel information measured based on the third reference signal. The time corresponding to the q' pieces of predicted channel information is not earlier than the time of transmission of the indication information #5. q' is a positive integer.

[0346] The order between steps 610 and 620 and between steps 630 and 640 is not limited in this application. For the second reference signal and the third reference signal in method 600, please refer to the relevant description of the first reference signal in method 500. For the q pieces of predicted channel information and the q' pieces of predicted channel information, please refer to the relevant description of the p pieces of predicted channel information in method 500. q and q' may be the same or different. For indication information #4 and indication information #5, please refer to the relevant description when indication information #1 indicates p pieces of predicted channel information. For indication information #5, please refer to the relevant description when indication information #1 indicates p pieces of predicted channel information and channel information measured based on the first reference signal, or when indication information #1 indicates channel information measured based on the first reference signal. To avoid repetition, the details will not be described again here.

[0347] Optionally, when q pieces of predicted channel information are valid, the indication information #4 indicates the q pieces of predicted channel information.

[0348] Optionally, when the q' pieces of predicted channel information are invalid, the indication information #5 indicates the q' pieces of predicted channel information and the channel information measured based on the third reference signal, or the indication information #5 indicates the channel information measured based on the third reference signal.

[0349] For the manner of determining whether the q pieces of predicted channel information and the q′ pieces of predicted channel information are valid, refer to the manner of determining whether the p pieces of predicted channel information are valid in method 500 .

[0350] Optionally, based on a comparison result between the r pieces of predicted channel information and the r pieces of measured channel information, q' pieces of predicted channel information are invalid, where the r pieces of predicted channel information correspond to the r pieces of measured channel information, where r is a positive integer, and the time corresponding to the r pieces of predicted channel information is earlier than the time of transmission of the indication information #5.

[0351] For the r pieces of predicted channel information and the r pieces of measured channel information, please refer to the relevant description of the n pieces of predicted channel information and the n pieces of measured channel information in the method 500 .

[0352] Other solutions in method 500 are also applicable to method 600. To avoid repetition, the details will not be described again here.

[0353] 7 is a diagram of another communication method according to an embodiment of the present application. As shown in FIG. 7, a method 700 includes the following steps:

[0354] 710: A first device transmits a first reference signal to a second device.

[0355] In this case, the first reference signal may be an uplink reference signal, and the channel information may be uplink channel information. For example, the first reference signal may be one or more of SRS, DMRS, etc. For example, the second device may be a network device, and the first device may be a terminal device.

[0356] 720: The second device determines, based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, to perform data transmission by using at least one of the p pieces of predicted channel information or the channel information measured based on the first reference signal.

[0357] The n pieces of predicted channel information correspond to the n pieces of measured channel information, and the time points corresponding to the p pieces of predicted channel information are later than the measurement time points of the first reference signal, where n is a positive integer and p is a positive integer.

[0358] In other words, in step 720, the second device may determine the channel information to be used for data transmission based on the comparison result.

[0359] Optionally, the method 700 further comprises step 730 .

[0360] 730: The second device sends indication information #1 (an example of first indication information) to the first device. The indication information #1 indicates at least one piece of channel information. The at least one piece of channel information includes p pieces of predicted channel information and / or channel information measured based on the first reference signal. The at least one piece of channel information is determined based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information.

[0361] For a specific description of the content in method 700 that is the same as or corresponds to method 500, please refer to method 500. To avoid repetition, the details will not be described again here.

[0362] Hereinafter, the method 500 will be described by using examples with reference to FIGS. 8 to 11. In FIGS. 8 to 11, only an example in which the first device may be a network device and the second device may be a terminal device is used for description purposes, and does not constitute a limitation on the scope of the embodiments of this application. In FIGS. 8 to 11, only an example in which the reference signal is CSI-RS is used for description purposes, and does not constitute a limitation on the solutions in the embodiments of this application. For specific descriptions, please refer to the related descriptions in the method 500. To avoid repetition, some descriptions will be omitted as appropriate when FIGS. 8 to 11 are described. In FIGS. 8 to 11, the channel information is CSI.

[0363] 8 is a diagram of a CSI feedback procedure. In the CSI feedback procedure shown in FIG. 8, a terminal device may predict CSI at one future time point. In this case, p is 1.

[0364] The terminal device may predict a CSI at a future time point based on the m measured CSIs. Specifically, the terminal device may predict the CSI at a future time point by using a prediction model. Specifically, the m measured CSIs are input to the prediction model for processing to predict the CSI at a future time point.

[0365] For example, the predictive model may be an AI predictive model, such as an RNN, an LSTM, or a Transformer.

[0366] It should be understood that the above is merely an example. Alternatively, the terminal device may predict future CSI in other manners, for example, through Kalman filtering. For example, the m measured CSI may include CSI measured at the current time point and CSI measured at the previous m-1 time points. The CSI measured at the current time point is CSI measured based on the current reference signal. In this case, the CSI measured at the current time point and the CSI measured at the previous m-1 time points may be input into a prediction model to predict CSI at one future time point. The future time point is a time point in the future relative to the current time point.

[0367] The predictive model may be deployed to a terminal device, and the terminal device may monitor the performance of the predictive model.

[0368] 8, the CSI feedback time points include t0, t1, and t2, where t0 is earlier than t1, and t2 is later than t1.

[0369] An example in which the current time point is time t1 is used below for explanation. CSI at time point t2 is predicted at time point t1. Specifically, CSI-RS is measured at time point t1 to obtain CSI measured at time point t1. The CSI measured at time point t1 may also be referred to as a CSI measurement result at time point t1. The CSI measured at time point t1 and CSI measured at previous m-1 time points are input into a prediction model to predict CSI at future time point t2, i.e., obtain CSI at time point t2 predicted at time point t1. The terminal device stores the CSI at time point t1 predicted at time point t0. The CSI at time point t1 predicted at time point t0 may also be referred to as a CSI prediction result at time point t1. The terminal device may compare the CSI measured at time point t1 with the CSI at time point t1 predicted at time point t0, and determine the content to be fed back by the terminal device at time point t1 based on the comparison result.

[0370] 9 is a diagram of another CSI feedback procedure. In the CSI feedback procedure shown in FIG. 9, the terminal device may predict CSI at one future time point. In this case, p is 1.

[0371] The solution shown in Fig. 8 is a simple example of the method 500. In the solution shown in Fig. 8, the CSI feedback time point and the CSI measurement time point overlap at time point t1. However, the CSI feedback time point is usually different from the CSI measurement time point. For example, the CSI fed back at time point t is usually the CSI measured before time point t or the CSI predicted before time point t.

[0372] 9, the feedback time points may include t0, t1, and t2, where t0 is earlier than t1 and t2 is later than t1, and t0, t1, and t2 may be adjacent or non-adjacent feedback time points.

[0373] The method 500 is described below by using the CSI fed back at time t1 as an example.

[0374] S81: At time t1′, the terminal device receives the CSI-RS (an example of Reference Signal #1) transmitted by the network device.

[0375] The terminal device may measure CSI based on the CSI-RS to obtain CSI measured at time t1 (an example of channel information measured based on reference signal #1). Time t1' is earlier than time t1. The CSI-RS is the CSI-RS indicated by a solid arrow in FIG. 9.

[0376] The CSI measured at time t1' may also be referred to as the CSI measurement result at time t1'.

[0377] S82: The terminal device compares the CSI measured at time t1′ (examples of n pieces of measured channel information) with the CSI at time t1″ predicted before time t1″ (examples of n pieces of predicted channel information). In this case, n may be 1.

[0378] The predicted CSI at time t1'' may also be referred to as the CSI prediction result at time t1''.

[0379] For a CSI measured at time t1', the time corresponding to the CSI is time t1'. For a CSI predicted at time t1'', ​​the time corresponding to the CSI is time t1''.

[0380] For example, as shown in FIG. 9, t1″=t0+t′. In this case, t′ may represent the time difference between the time point corresponding to the predicted CSI and the CSI feedback time point. If t0 and t1 are adjacent feedback time points, t′ is a value smaller than the feedback interval.

[0381] It should be understood that in FIG. 9, the predicted CSI at time t1" is the CSI fed back to the network device at time t0. In another possible implementation manner, the predicted CSI at time t1" may alternatively be the CSI fed back to the network device at another time point before time t1 and other than time t0. For example, the difference between t1' and t1" is less than or equal to threshold #1. For example, t1'=t1".

[0382] The predicted CSI at time t1'' is obtained through prediction by using a prediction model. The result of the comparison may be used to reflect the performance of the prediction model.

[0383] The terminal device may determine the accuracy of the prediction result based on the comparison result.

[0384] For example, the comparison between the CSI prediction and the CSI measurement may include a difference between the CSI prediction and the CSI measurement and / or a channel correlation.

[0385] For example, the difference between the predicted CSI and the measured CSI may include at least one of an MSE or an NMSE between the predicted CSI and the measured CSI.

[0386] For example, the channel correlation between the CSI prediction and the CSI measurement may include at least one of a GCS or a SGCS between the CSI prediction and the CSI measurement.

[0387] An example will be used below to describe a case where a terminal device determines whether the prediction of a prediction model is accurate based on a comparison result between a group of CSI prediction results and CSI measurement results. The CSI prediction results and CSI measurement results of the group are CSI prediction results and CSI measurement results that have a corresponding relationship, that is, n=1. Determining whether the prediction of a prediction model is accurate means determining whether p pieces of predicted channel information are valid.

[0388] For ease of understanding, an example in which the CSI measurement result at time t1' and the CSI prediction result at time t1'' are used as one group of CSI prediction results and CSI measurement results is used below for explanation.

[0389] For example, if one or more differences between the CSI measurement result at time t1' and the CSI prediction result at time t1'' are equal to or greater than thresholds corresponding to the one or more differences, the CSI prediction result is determined to be inaccurate.

[0390] Alternatively, if one or more channel correlations between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ are equal to or less than a threshold value corresponding to the one or more channel correlations, the CSI prediction result is determined to be inaccurate.

[0391] Alternatively, if one or more differences between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ are equal to or greater than a threshold corresponding to the one or more differences, or if one or more channel correlations between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ are equal to or less than a threshold corresponding to the one or more channel correlations, the CSI prediction result is determined to be inaccurate.

[0392] Alternatively, if one or more differences between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ are equal to or greater than thresholds corresponding to the one or more differences, and one or more channel correlations between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ are equal to or less than thresholds corresponding to the one or more channel correlations, the CSI prediction result is determined to be inaccurate.

[0393] Because n is 1 and the CSI prediction result is inaccurate, the terminal device may determine that the prediction of the prediction model is inaccurate, that is, that the p pieces of predicted channel information are invalid.

[0394] When the comparison result between the CSI measurement result at time t1′ and the CSI prediction result at time t1″ does not satisfy the above condition, it is determined that the CSI prediction result is accurate. The terminal device may determine that the prediction of the prediction model is accurate, that is, that the p pieces of predicted channel information are valid. To avoid repetition, the details will not be described again here.

[0395] It should be understood that only one group of CSI prediction results and CSI measurement results is used in the above example for explanation. In other possible implementations, n may be an integer greater than 1. In other words, the CSI prediction performance may be monitored at multiple time points.

[0396] The case where a terminal device determines whether the prediction of a prediction model is accurate based on the comparison results between the CSI prediction results and the CSI measurement results of multiple groups will be described below by using an example.

[0397] For example, based on the above-mentioned decision criteria for the CSI prediction results and CSI measurement results of the above-mentioned groups, a decision is made on the comparison results between the CSI prediction results and CSI measurement results of each of the multiple groups. If the ratio of the inaccurate CSI prediction results is equal to or greater than threshold #3, it is determined that the prediction of the prediction model is inaccurate.

[0398] Alternatively, if a statistical value (e.g., a weighted average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, the prediction of the prediction model is determined to be inaccurate.

[0399] Alternatively, if a statistical value (e.g., a weighted average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is below a threshold value corresponding to the channel correlation, the prediction of the prediction model is determined to be inaccurate.

[0400] Alternatively, if a statistical value (e.g., a weighted average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, and a statistical value (e.g., a weighted average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is equal to or less than a threshold value corresponding to the channel correlation, it is determined that the prediction of the prediction model is inaccurate.

[0401] Alternatively, if a statistical value (e.g., a weighted average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, or if a statistical value (e.g., a weighted average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is equal to or less than a threshold value corresponding to the channel correlation, it is determined that the prediction of the prediction model is inaccurate.

[0402] When the comparison result between the CSI measurement results and the CSI prediction results of multiple groups does not satisfy the above condition, the terminal device may determine that the prediction of the prediction model is accurate. To avoid repetition, the details will not be described again here.

[0403] It should be understood that the above determination methods are merely examples. For other determination methods, please refer to the description in the method 500. To avoid repetition, the details will not be described again here.

[0404] S83: The terminal device may send indication information #1 to the network device at time t1 to indicate at least one CSI.

[0405] In other words, the terminal device may feed back at least one CSI to the network device at time t1.

[0406] If it is determined that the prediction of the prediction model is accurate, the terminal device may report, at time t1, only the predicted CSI at time t2'', i.e., the CSI prediction result at time t2'' (example of p pieces of predicted channel information). For example, the CSI measured at time t1' and the CSI measured at m-1 time points before time t1' are input into the prediction model to obtain the predicted CSI at time t2''. Time t2'' is later than time t1''. For example, t2''=t1+t' as shown in FIG. 9.

[0407] If it is determined that the prediction of the prediction model is inaccurate, the terminal device may report, at time t1, the CSI measured at time t1', i.e., the CSI measurement result at time t1'. Alternatively, the terminal device may report, at time t1, the CSI measurement result at time t1' and the CSI prediction result at time t2''.

[0408] For example, the indication information #1 may further indicate the label of at least one fed back CSI.

[0409] For example, the indication information #1 may further indicate the time reference point of the p pieces of predicted channel information.

[0410] Optionally, the terminal device may further send indication information #2, which indicates the comparison result.

[0411] S84: The network device performs data transmission based on the instruction information #1.

[0412] For example, the indication information #1 may further indicate the label of at least one fed back CSI, in which case the network device may analyze the indication information #1 to determine whether the at least one CSI indicated by the indication information #1 is a measurement result or a prediction result.

[0413] If the at least one CSI includes a measurement result, ie, a CSI measurement result at time t1', the network device may perform data transmission by using the CSI measurement result at time t1'.

[0414] If at least one CSI does not include a measurement result but only includes a prediction result, i.e., a CSI prediction result at time t2'', the network device may perform data transmission by using the CSI prediction result at time t2''.

[0415] In some possible scenarios, the terminal device may predict CSI at multiple future points in time.

[0416] 10 is a diagram of another CSI feedback procedure. In the CSI feedback procedure shown in FIG. 10, a terminal device may predict CSI at multiple future time points and feed back the predicted CSI at multiple future time points to a network device by performing the CSI feedback procedure once. The terminal device may monitor the accuracy of a portion of the CSI prediction result.

[0417] 10, the feedback time points may include t0, t1, and t2, where t0 is earlier than t1 and t2 is later than t1, and t0, t1, and t2 may be adjacent or non-adjacent feedback time points.

[0418] The method 500 is described below by using the CSI fed back at time t1 as an example.

[0419] S91: At time t1′, the terminal device receives the CSI-RS (an example of Reference Signal #1) transmitted by the network device.

[0420] The terminal device may measure CSI based on the CSI-RS to obtain CSI measured at time t1 (an example of channel information measured based on reference information #1). Time t1' is earlier than time t1. The CSI-RS is the CSI-RS indicated by a solid arrow in FIG. 10.

[0421] The CSI measured at time t1' may also be referred to as the CSI measurement result at time t1'.

[0422] S92: The terminal device compares the CSI measured at time t1′ (examples of n pieces of measured channel information) with the CSI at time t1″ predicted before time t1″ (examples of n pieces of predicted channel information). In this case, n may be 1.

[0423] The predicted CSI at time t1'' may also be referred to as the CSI prediction result at time t1''.

[0424] For example, as shown in FIG. 10, t1″=t0+t′. In this case, t′ may represent the time difference between the time point corresponding to the predicted CSI and the CSI feedback time point. If t0 and t1 are adjacent feedback time points, t′ is a value smaller than the feedback interval.

[0425] It should be understood that in Figure 10, the predicted CSI at time t1" is the CSI fed back to the network device at time t0. In another possible implementation manner, the predicted CSI at time t1" may alternatively be CSI fed back to the network device at another time point before time t1 and other than time t0.

[0426] For a measured CSI at time t1', the time corresponding to the CSI is time t1'. For a predicted CSI at time t1'', ​​the time corresponding to the CSI is time t1''.

[0427] For example, the difference between t1' and t1'' is less than or equal to threshold #1. For example, t1' = t1''.

[0428] The predicted CSI at time point t1'' is obtained through prediction using a prediction model. The comparison result may be used to reflect the performance of the prediction model.

[0429] In the procedure shown in FIG. 10, the prediction model is used to predict the CSI at a plurality of future time points. The terminal device may monitor the accuracy of a part of the CSI prediction results in the predicted CSI at a plurality of future time points.

[0430] An example where the prediction model is used to predict the CSI at two future time points is used below for explanation. One or more measured CSIs before time point t1''' are input into the prediction model, and the prediction model may output the predicted CSI at time point t1''' and the predicted CSI at time point t1''. In other words, the CSI prediction result at time point t1''' and the CSI prediction result at time point t1'' may be obtained through prediction based on the same input. Time point t1''' is earlier than time point t1''. For example, as shown in FIG. 10, t1''' = t0 + t''. t'' may represent the time difference between the time point corresponding to the predicted CSI and the CSI feedback time point. t'' < t'. The terminal device may monitor the accuracy of a part of the CSI prediction results at time point t1''' and the CSI prediction result at time point t1'' (for example, the CSI prediction result at time point t1'').

[0431] The terminal device may determine the accuracy of the CSI prediction result based on the comparison result.

[0432] For the specific determination method, refer to the relevant description in FIG. 9. To avoid repetition, the details are not described again here.

[0433] S93: The terminal device may send indication information #1 to the network device at time t1 to indicate at least one CSI.

[0434] In other words, the terminal device may feed back at least one CSI to the network device at time t1.

[0435] If it is determined that the prediction of the prediction model is accurate, the terminal device may report, at time t1, only the predicted CSI at time t2″ and the predicted CSI at time t2′″, i.e., the CSI prediction result at time t2″ and the CSI prediction result at time t2′″ (examples of p pieces of predicted channel information), where p is 2.

[0436] For example, the CSI measured at time t1' and the CSI measured at m-1 time points before time t1' are input into the prediction model to obtain a CSI prediction result at time t2'' and a CSI prediction result at time t2'''. Time points t2''' and t2'' are later than time point t1'. For example, as shown in FIG. 10, t2''=t1+t' and t2'''=t1+t''.

[0437] If it is determined that the prediction of the prediction model is inaccurate, the terminal device may report, at time t1, the CSI measured at time t1', i.e., the CSI measurement result at time t1'. Alternatively, the terminal device may report, at time t1, the CSI measurement result at time t1', the CSI prediction result at time t2", and the CSI prediction result at time t2'".

[0438] The indication information #1 may further indicate the label and / or time reference point of at least one fed back CSI. For specific descriptions, please refer to the method 500 or the related descriptions in FIG.

[0439] Optionally, the terminal device may further send indication information #2, which indicates the comparison result.

[0440] S94: The network device performs data transmission based on the instruction information #1.

[0441] If the at least one CSI includes a measurement result, ie, a CSI measurement result at time t1', the network device may perform data transmission by using the CSI measurement result at time t1'.

[0442] If at least one CSI does not include a measurement result but only includes a prediction result, i.e., a CSI prediction result at time t2'' and a CSI prediction result at time t2''', the network device may perform data transmission by using the CSI prediction result at time t2'' or the CSI prediction result at time t2'''.

[0443] FIG. 11 is a diagram of yet another CSI feedback procedure. In the CSI feedback procedure shown in FIG. 11, a terminal device may predict CSI at multiple future time points and feed back the predicted CSI at multiple future time points to a network device by performing the CSI feedback procedure once. The main difference between the feedback procedure shown in FIG. 11 and the feedback procedure shown in FIG. 10 is that in the feedback procedure shown in FIG. 11, the terminal device monitors the accuracy of all CSI prediction results for the predicted CSI at multiple future time points. To avoid repetition, the following mainly describes the differences between FIG. 11 and FIG. 10. For other parts, please refer to the relevant description of FIG. 10.

[0444] The method 500 is described below by using the CSI fed back at time t1 as an example.

[0445] S11: The terminal device receives the CSI-RS (an example of Reference Signal #1) transmitted by the network device at time t1'. The terminal device receives the CSI-RS transmitted by the network device at time t1''''.

[0446] The terminal device may separately measure CSI based on the two CSI-RSs to obtain CSI measured at time t1' (an example of channel information measured based on reference information #1) and CSI measured at time t1''''. Time t1''''' and time t1' are earlier than time t1'. The two CSI-RSs are the two CSI-RSs indicated by solid arrows in FIG. 11.

[0447] The CSI measured at time t1' may also be referred to as a CSI measurement result at time t1'. The CSI measured at time t1'''' may also be referred to as a CSI measurement result at time t1''''.

[0448] S12: The terminal device compares the CSI measured at time t1' with the CSI at time t1'' predicted before time t1'', ​​and compares the CSI measured at time t1''' (examples of n measured channel information) with the CSI at time t1'' predicted before time t1''' (examples of n predicted channel information).

[0449] The CSI measured at time t1′ and the CSI measured at time t1″″ are examples of n pieces of measured channel information. The predicted CSI at time t1″ and the predicted CSI at time t1′″ are examples of n pieces of predicted channel information. In this case, n may be 2.

[0450] The predicted CSI at time point t1'' may also be referred to as the CSI prediction result at time point t1''. The predicted CSI at time point t1''' may also be referred to as the CSI prediction result at time point t1'''.

[0451] For example, as shown in FIG. 11, t1''=t0+t' and t1'''=t0+t''.

[0452] As shown in FIG. 11, the predicted CSI at time t1'' and the predicted CSI at time t1''' may be the CSI fed back to the network device at time t0. In other implementations, the predicted CSI at time t1'' and the predicted CSI at time t1''' may alternatively be fed back to the network device at other times.

[0453] For a measured CSI at time t1', the time corresponding to the CSI is time t1'. For a predicted CSI at time t1'', ​​the time corresponding to the CSI is time t1''. For a measured CSI at time t1'''', the time corresponding to the CSI is time t1''''. For a predicted CSI at time t1''', the time corresponding to the CSI is time t1'''.

[0454] For example, the difference between t1' and t1'' is less than or equal to threshold #1. The difference between t1''' and t1'''' is less than or equal to threshold #1. For example, t1'=t1'' and t1'''=t1''''.

[0455] For the manner of determining the predicted CSI at time t1" and the predicted CSI at time t1'", please refer to the related description in FIG. 10. The details will not be described again in this specification. The terminal device may monitor the accuracy of the CSI prediction result at time t1'" and the CSI prediction result at time t1".

[0456] The terminal device may determine the accuracy of the CSI prediction result based on the comparison result.

[0457] The case where a terminal device determines whether the prediction of a prediction model is accurate based on the comparison results between the CSI prediction results and the CSI measurement results of multiple groups will be described below by using an example.

[0458] For example, if a statistical value (e.g., minimum or average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, it is determined that the prediction of the prediction model is inaccurate.

[0459] Alternatively, if a statistical value (e.g., maximum or average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is less than or equal to a threshold value corresponding to the channel correlation, the prediction of the prediction model is determined to be inaccurate.

[0460] Alternatively, if a statistical value (e.g., minimum or average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, and a statistical value (e.g., maximum or average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is equal to or less than a threshold value corresponding to the channel correlation, it is determined that the prediction of the prediction model is inaccurate.

[0461] Alternatively, if a statistical value (e.g., a weighted average value) of the difference between the CSI prediction results and the CSI measurement results of multiple groups is equal to or greater than a threshold value corresponding to the difference, or if a statistical value (e.g., a weighted average value) of the channel correlation between the CSI prediction results and the CSI measurement results of multiple groups is equal to or less than a threshold value corresponding to the channel correlation, it is determined that the prediction of the prediction model is inaccurate.

[0462] It should be understood that the CSI prediction results and CSI measurement results of the multiple groups may be CSI measurement results corresponding to multiple CSI prediction results and multiple CSI prediction results obtained through one prediction. For example, the CSI prediction results and CSI measurement results of the multiple groups may be predicted CSI at time point t1", predicted CSI at time point t1'", and CSI measurement results corresponding to predicted CSI at time point t1" and predicted CSI at time point t1'", i.e., measured CSI at time point t1" and measured CSI at time point t1'". Alternatively, the CSI prediction results and CSI measurement results of the multiple groups may be CSI measurement results corresponding to multiple CSI prediction results and multiple CSI prediction results obtained through multiple predictions. For example, the CSI prediction results and CSI measurement results of the multiple groups may be a predicted CSI at time t1'', ​​a predicted CSI at time t1''', a predicted CSI at time t0'', a predicted CSI at time t0''', and a CSI measurement result corresponding to a predicted CSI at time t1'', ​​a predicted CSI at time t1''', a predicted CSI at time t0'', and a predicted CSI at time t0'''. The predicted CSI at time t0'' and the predicted CSI at time t0''' may be obtained by a prediction model through prediction based on the same input. For specific prediction methods, please refer to the above description. The details will not be described again in this specification.

[0463] For example, when the multiple groups of CSI prediction results and CSI measurement results correspond to multiple CSI prediction results and multiple CSI prediction results obtained through multiple predictions, the determination may be performed for the multiple CSI prediction results and CSI measurement results corresponding to the multiple CSI prediction results obtained through each prediction based on one of the above four determination methods. If the ratio of the number of incorrect predictions to the total number of predictions is equal to or greater than threshold #4, it is determined that the prediction of the prediction model is inaccurate.

[0464] When the comparison result between the CSI measurement results and the CSI prediction results of multiple groups does not satisfy the above condition, the terminal device may determine that the prediction of the prediction model is accurate. To avoid repetition, the details will not be described again here.

[0465] It should be understood that the above are just examples. For other determination methods, please refer to the relevant descriptions in the method 500. To avoid repetition, the details will not be described again here.

[0466] S13: The terminal device may send indication information #1 to the network device at time t1 to indicate at least one CSI.

[0467] For a description of at least one CSI, please refer to the related description in Figure 10. The details will not be described again here.

[0468] Optionally, the terminal device may further send indication information #2, which indicates the comparison result.

[0469] S14: The network device performs data transmission based on the instruction information #1.

[0470] For the specific implementation of step S14, please refer to the related description in Figure 10. The details will not be described again in this specification.

[0471] It should be understood that the methods shown in FIGS. 8 to 11 are merely examples and do not constitute limitations on the solutions in the embodiments of this application.

[0472] It can be further understood that the names of information used in some of the above embodiments are merely examples and do not constitute limitations on the protection scope of the embodiments of this application.

[0473] It can be further understood that the formulas used in the embodiments of this application are merely examples for explanation, and do not constitute limitations on the protection scope of the embodiments of this application. In the process of calculating the above related parameters, to satisfy the calculation results of the formulas, the calculations may be performed based on the above formulas, or the calculations may be performed based on modifications of the above formulas, or the calculations may be performed in other ways.

[0474] It may further be understood that some optional features in the embodiments of this application may be independent of other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0475] It can be further understood that the solutions in the embodiments of this application may be combined appropriately for use, and the explanations or descriptions of terms in the embodiments may be cross-referenced or explained in the embodiments. This is not limited thereto.

[0476] It may be further understood that the sequence numbers of various numerals in the embodiments of this application do not imply an order of execution, but are merely for ease of explanation, and therefore should not constitute any limitation on the implementation process of the embodiments of this application.

[0477] It may further be appreciated that in the method embodiments described above, the methods and operations implemented by a device may alternatively be implemented by a component (eg, a chip or circuit) of a device.

[0478] Corresponding to the methods provided in the above method embodiments, the embodiments of this application further provide corresponding apparatuses. The apparatuses include corresponding modules configured to perform the above method embodiments. The modules may be software, hardware, or a combination of software and hardware. It can be understood that the technical features described in the above method embodiments are also applicable to the following apparatus embodiments.

[0479] 12 is a diagram of a communication device 1700 according to an embodiment of the present application. The device 1700 includes a transceiver unit 1710 and a processing unit 1720. The transceiver unit 1710 may be configured to implement corresponding communication functions. The transceiver unit 1710 may also be referred to as a communication interface, a communication unit, etc. The processing unit 1720 may be configured, for example, to configure resources to implement corresponding processing functions. The processing unit 1720 may also be referred to as a processor, etc.

[0480] Optionally, the apparatus 1700 further includes a storage unit. The storage unit may be configured to store instructions and / or data. The processing unit 1720 may read the instructions and / or data in the storage unit, so that the apparatus implements the actions of the device or network element in the above method embodiments.

[0481] The communication apparatus 1700 may be a terminal device, or a communication apparatus used in or in cooperation with a terminal device and capable of implementing a communication method executed on the terminal device side. Alternatively, the communication apparatus 1700 may be an access network device, or a communication apparatus used in or in cooperation with a network device and capable of implementing a communication method executed on the network device side.

[0482] When the communication apparatus 1700 is used in a terminal device, the apparatus 1700 may implement steps or procedures performed by the terminal device (e.g., a first device or a second device) in the above method embodiments. The transceiver unit 1710 may be configured to perform transmission / reception-related operations of the terminal device in the above method embodiments. The processing unit 1720 may be configured to perform processing-related operations of the terminal device in the above method embodiments.

[0483] When the communication apparatus 1700 is used in a network device, the apparatus 1700 may implement steps or procedures performed by the network device (e.g., a first device or a second device) in the above method embodiments. The transceiver unit 1710 may be configured to perform transmission / reception-related operations of the network device in the above method embodiments. The processing unit 1720 may be configured to perform processing-related operations of the network device in the above method embodiments.

[0484] It should be understood that the specific processes by which the units perform the above corresponding steps are described in detail in the above method embodiments, and for the sake of brevity, the details will not be described herein.

[0485] It should be further understood that the apparatus 1700 herein may be embodied in the form of a functional unit. The term "unit" herein may refer to an application-specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a dedicated processor, or a group processor) configured to execute one or more software or firmware programs, a memory, a merge logic circuit, and / or other suitable components supporting the described functionality. In an optional example, those skilled in the art will understand that the apparatus 1700 may specifically be a terminal device in the above embodiments and may be configured to perform procedures and / or steps corresponding to the terminal device in the above method embodiments. Alternatively, the apparatus 1700 may specifically be a network device in the above embodiments and may be configured to perform procedures and / or steps corresponding to the network device in the above method embodiments. To avoid repetition, the details will not be described again here.

[0486] The apparatus 1700 in the above solution has functions for implementing corresponding steps performed by a device (e.g., a terminal device, or in other examples, a network device) in the above method. The functions may be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, to separately perform the receiving / transmitting operations and related processing operations in the method embodiments, a transceiver unit may be replaced with a transceiver (e.g., a transmitting unit in a transceiver unit may be replaced with a transmitting machine, and a receiving unit in a transceiver unit may be replaced with a receiving machine), and other units, such as a processing unit, may be replaced with a processor.

[0487] Furthermore, the transceiver unit 1710 may alternatively be transceiver circuitry (eg, may include receiver circuitry and transmitter circuitry), and the processing unit may alternatively be processing circuitry.

[0488] It should be noted that the apparatus in Fig. 12 may be a network element or device in the above embodiments, or may be a chip or a chip system, for example, a system on chip (SoC). The transceiver unit may be an input / output circuit or a communication interface. The processing unit is a processor, a microprocessor, or an integrated circuit integrated on a chip. This is not limited in this specification.

[0489] 13 is a diagram of another communication device 1800 according to an embodiment of the present application. The device 1800 includes a processor 1810. The processor 1810 is configured to execute computer programs or instructions stored in a memory 1820, or to read data or signaling stored in the memory 1820, to perform the method in the above method embodiments. Optionally, there are more than one processor 1810.

[0490] Optionally, as shown in Figure 13, the device 1800 further includes a memory 1820 configured to store computer programs or instructions and / or data. The memory 1820 may be integrated with the processor 1810 or may be located separately. Optionally, there are more than one memory 1820.

[0491] 13, the apparatus 1800 further includes a transceiver 1830, the transceiver 1830 configured to transmit and / or receive signals. For example, the processor 1810 is configured to control the transceiver 1830 to transmit and / or receive signals.

[0492] In the solution, the communication apparatus 1800 may be used in a terminal device. Specifically, the communication apparatus 1800 may be a terminal device, or may be an apparatus capable of supporting a terminal device in implementing the functions of the terminal device (e.g., the first device or the second device) in any one of the above examples. The apparatus 1800 is configured to implement the operations performed by the terminal device (e.g., the first device or the second device) in the above method embodiments.

[0493] For example, the processor 1810 is configured to execute computer programs or instructions stored in the memory 1820 to realize relevant operations of a terminal device (e.g., a first device or a second device) in the above-described method embodiments.

[0494] In another solution, the communication device 1800 may be used in a network device. Specifically, the communication device 1800 may be the network device or a device capable of supporting the network device in implementing the functions of the network device (e.g., the first device or the second device) in any one of the above examples. The device 1800 is configured to implement the operations performed by the network device (e.g., the first device or the second device) in the above method embodiments.

[0495] For example, the processor 1810 is configured to execute computer programs or instructions stored in the memory 1820 to implement relevant operations of a network device (e.g., a first device or a second device) in the above-described method embodiments.

[0496] It should be understood that the processor referred to in the embodiments of this application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSPs), ASICs, field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.

[0497] Furthermore, it should be understood that the memory referred to in the embodiments of this application may be volatile memory and / or nonvolatile memory. Nonvolatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). For example, RAM may be used as an external cache. By way of example and not limitation, RAM may include the following forms: static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchlink dynamic random access memory (synchlink DRAM, SLDRAM), and direct Rambus random access memory (direct Rambus RAM, DR RAM).

[0498] It should be noted that when the processor is a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, the memory (storage module) may be integrated into the processor.

[0499] It should be further noted that memory, as described herein, is intended to include, without being limited to, these and any other suitable types of memory.

[0500] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions for implementing a method performed by a communication device in the above method embodiment.

[0501] For example, when the computer program is executed by a computer, the computer is enabled to implement the method executed by the first device in the above-described method embodiments.

[0502] In another example, the computer program, when executed by a computer, enables the computer to implement the method performed by the second device in the method embodiments described above.

[0503] An embodiment of the present application further provides a computer program product including instructions, which, when executed by a computer, realize the method performed by a device (e.g., the first device or the second device) in the above-described method embodiments.

[0504] An embodiment of the present application further provides a communication system including the above-mentioned first device and second device, wherein the first device and the second device may implement a communication method shown in any one of the above examples of Figures 5 to 11.

[0505] Optionally, the system further comprises a device in communication with said first device and / or said second device.

[0506] For the relevant content description and beneficial effects of any one of the devices provided above, please refer to the corresponding method embodiments provided above, and the details will not be described again in this specification.

[0507] In some embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the described device embodiments are merely examples. For example, the division of units is merely a logical division of functions, and other divisions may occur in actual implementations. For example, multiple units or components may be combined or integrated into other systems, or some features may be omitted or not implemented. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be realized through some interfaces. Indirect couplings or communication connections between devices or units may be realized in electronic, mechanical, or other forms.

[0508] All or part of the above embodiments may be realized by using software, hardware, firmware, or any combination thereof. When software is used to realize the embodiments, all or part of the embodiments may be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the procedures or functions according to the embodiments of this application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. For example, the computer may be a personal computer, a server, a network device, etc. The computer instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, or digital subscriber line (DSL)) or wireless (e.g., infrared, radio, or microwave) method. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device that integrates one or more available media, such as a server or a data center. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), a semiconductor medium (e.g., a solid-state drive (SSD)), etc. For example, the available medium may include, but is not limited to, any medium that can store program code, such as a USB flash disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0509] The above description is merely a specific implementation of this application and is not intended to limit the scope of protection of this application. Any variations or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in this application shall fall within the scope of protection of this application. Therefore, the scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. 1. A communication method comprising: receiving a first reference signal from a first device; determining whether the p predicted channel information is valid; sending first indication information to the first device, the first indication information indicating at least one channel information; Including, When it is determined that the p pieces of predicted channel information are valid, the at least one piece of channel information includes the p pieces of predicted channel information; or When it is determined that the p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes channel information measured based on the first reference signal, where p is a positive integer, and a time point corresponding to the p pieces of predicted channel information is not earlier than a time point of transmission of the first indication information.

2. The step of determining whether the p pieces of predicted channel information are valid includes:

2. The method of claim 1, further comprising: determining whether the p pieces of predicted channel information are valid based on a comparison result between n pieces of predicted channel information and n pieces of measured channel information, wherein the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and a time corresponding to the n pieces of predicted channel information is earlier than the transmission time of the first indication information.

3. 3. The method of claim 2, wherein the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and a difference between a time point corresponding to the i-th predicted channel information and a time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .

4. The method according to claim 2 or 3, wherein the n pieces of measured channel information include the channel information measured based on the first reference signal.

5. The comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a difference between the n predicted channel information and the n measured channel information, or a channel correlation between the n predicted channel information and the n measured channel information; 5. The method according to claim 2, further comprising:

6. 6. The method of claim 5, wherein the differences between the n channel information prediction results and the n channel information measurement results include at least one of the following: a mean square error between the n channel information prediction results and the n channel information measurement results, or a normalized error between the n channel information prediction results and the n channel information measurement results.

7. 7. The method of claim 5 or 6, wherein the channel correlation between the n channel information prediction results and the n channel information measurement results comprises at least one of the following: a generalized cosine similarity between the n channel information prediction results and the n channel information measurement results, or a squared generalized cosine similarity between the n channel information prediction results and the n channel information measurement results.

8. n=1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference; the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is less than or equal to a threshold value corresponding to the channel correlation; the difference between the n pieces of predicted channel information and the n pieces of measured channel information is greater than or equal to a threshold corresponding to the difference, and the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is less than or equal to a threshold corresponding to the channel correlation; or The difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, or the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation. The method according to claim 5 , wherein the p pieces of predicted channel information are determined to be invalid when any one of the following conditions is met:

9. n>1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference; a statistic value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation; a statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference, and a statistical value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation; or The statistical value of the difference between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or greater than a threshold value corresponding to the difference, or the statistical value of the channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information is equal to or less than a threshold value corresponding to the channel correlation. The method according to claim 5 , wherein the p pieces of predicted channel information are determined to be invalid when any one of the following conditions is met:

10. n>1, and the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information is: a difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; a channel correlation between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; a difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, a channel correlation between the y pieces of predicted channel information and the y pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; or a difference between y pieces of predicted channel information among the n pieces of predicted channel information and y pieces of measured channel information among the n pieces of measured channel information is equal to or greater than a threshold corresponding to the difference, or a channel correlation between the y pieces of predicted channel information and the y pieces of measured channel information is equal to or less than a threshold corresponding to the channel correlation, a ratio of y to n is equal to or greater than a second threshold, y is an integer equal to or greater than 0, and the y pieces of predicted channel information correspond to the y pieces of measured channel information; The method according to claim 5 , wherein the p pieces of predicted channel information are determined to be invalid when any one of the following conditions is met:

11. The method of claim 2 , further comprising the step of: sending second indication information to the first device, the second indication information indicating the comparison result.

12. 12. The method according to claim 1, wherein the p predicted channel information items are obtained through prediction based on m measured channel information items, where the m measured channel information items include the channel information items measured based on the first reference signal, and m is a positive integer.

13. 13. The method of claim 1, wherein the first indication information further indicates a label of the at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

14. 14. The method according to claim 1, wherein when the at least one piece of channel information includes the p pieces of predicted channel information or the at least one piece of channel information includes the channel information measured based on the first reference signal and the p pieces of predicted channel information, the first indication information further indicates the time points corresponding to the p pieces of predicted channel information.

15. 1. A communication method comprising: receiving first indication information from a second device, the first indication information indicating at least one piece of channel information and a label of the at least one piece of channel information, the label of the at least one piece of channel information indicating that the at least one piece of channel information is a predicted result or a measured result, respectively; performing data transmission based on the at least one channel information; A method comprising:

16. transmitting a first reference signal to the second device; When p pieces of predicted channel information are valid, the at least one piece of channel information includes the p pieces of predicted channel information; or When the p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes the channel information measured based on the first reference signal; The method of claim 15 , wherein the time points corresponding to the p pieces of predicted channel information are not earlier than the time point at which the first indication information is transmitted, and p is a positive integer.

17. performing data transmission based on at least one channel information, 17. The method of claim 16, comprising: performing data transmission based on the channel information measured based on the first reference signal when the at least one piece of channel information includes the channel information measured based on the first reference signal; or performing data transmission based on the p pieces of predicted channel information when the at least one piece of channel information does not include the channel information measured based on the first reference signal.

18. performing data transmission based on at least one channel information, 17. The method of claim 16, comprising: determining, based on the label of the at least one piece of channel information, that the at least one piece of channel information includes the measurement result, and performing data transmission based on the channel information measured based on the first reference signal; or determining, based on the label of the at least one piece of channel information, that the at least one piece of channel information does not include the measurement result, and performing data transmission based on the p pieces of predicted channel information.

19. 19. The method according to claim 16, wherein when the at least one piece of channel information includes the p pieces of predicted channel information or the at least one piece of channel information includes the channel information measured based on the first reference signal and the p pieces of predicted channel information, the first indication information further indicates the time points corresponding to the p pieces of predicted channel information.

20. 20. The method of claim 16, wherein the p predicted channel information items are obtained through prediction based on m measured channel information items, where the m measured channel information items include the channel information items measured based on the first reference signal, and m is a positive integer.

21. 21. The method according to claim 16, wherein, based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, the p pieces of predicted channel information are valid or the p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and a time corresponding to the n pieces of predicted channel information is earlier than the transmission time of the first indication information.

22. 22. The method of claim 21, wherein the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and a difference between a time point corresponding to the i-th predicted channel information and a time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .

23. The method according to claim 21 or 22, wherein the n pieces of measured channel information include the channel information measured based on the first reference signal.

24. 24. The method according to claim 21, wherein the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information comprises one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

25. 25. The method of claim 21, further comprising receiving second indication information from the second device, the second indication information indicating the comparison result.

26. 1. A communication method comprising: transmitting a second reference signal to a second device; receiving third indication information from the second device, the third indication information indicating q pieces of predicted channel information, a time corresponding to the q pieces of predicted channel information not earlier than a time point of transmitting the third indication information, where q is a positive integer; transmitting a third reference signal to the second device; receiving fourth indication information from the second device, the fourth indication information indicating channel information measured based on the third reference signal, or the fourth indication information indicating the channel information measured based on the third reference signal and q' pieces of predicted channel information, where a time point corresponding to the q' pieces of predicted channel information is not earlier than a time point of transmitting the fourth indication information, and q' is a positive integer; A method comprising:

27. 27. The method of claim 26, wherein when the q pieces of predicted channel information are valid, the third indication indicates the q pieces of predicted channel information, or when the q′ pieces of predicted channel information are invalid, the fourth indication indicates the channel information measured based on the third reference signal, or the fourth indication indicates the channel information measured based on the third reference signal and the q′ pieces of predicted channel information.

28. 28. The method of claim 26 or 27, wherein based on a comparison result between r pieces of predicted channel information and r pieces of measured channel information, the q' pieces of predicted channel information are invalid, the r pieces of predicted channel information correspond to the r pieces of measured channel information, r is a positive integer, and a time point corresponding to the r pieces of predicted channel information is earlier than the transmission time point of the fourth indication information.

29. 1. A communication method comprising: transmitting a first reference signal to a second device; receiving first indication information from the second device, the first indication information indicating at least one channel information; Including, When p pieces of predicted channel information are valid, the at least one piece of channel information includes the p pieces of predicted channel information, or when the p pieces of predicted channel information are invalid, the at least one piece of channel information includes channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes the channel information measured based on the first reference signal, where p is a positive integer, and a time point corresponding to the p pieces of predicted channel information is not earlier than a time point of transmission of the first indication information.

30. 30. The method of claim 29, wherein the first indication information further indicates a label of the at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

31. 31. The method of claim 30, further comprising: determining, based on the label of the at least one piece of channel information, that the at least one piece of channel information includes the measurement result, and performing data transmission based on the channel information measured based on the first reference signal; or determining, based on the label of the at least one piece of channel information, that the at least one piece of channel information does not include the measurement result, and performing data transmission based on the p pieces of predicted channel information.

32. 31. The method of claim 29 or 30, further comprising: performing data transmission based on the channel information measured based on the first reference signal when the at least one piece of channel information includes the channel information measured based on the first reference signal; or performing data transmission based on the p pieces of predicted channel information when the at least one piece of channel information does not include the channel information measured based on the first reference signal.

33. 33. The method of claim 29, wherein when the at least one piece of channel information includes the p pieces of predicted channel information or the at least one piece of channel information includes the channel information measured based on the first reference signal and the p pieces of predicted channel information, the first indication information further indicates the time points corresponding to the p pieces of predicted channel information.

34. 34. The method of claim 29, wherein the p predicted channel information items are obtained through prediction based on m measured channel information items, where the m measured channel information items include the channel information measured based on the first reference signal, and m is a positive integer.

35. 35. The method of claim 29, wherein, based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, the p pieces of predicted channel information are valid or the p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n being a positive integer, and the time corresponding to the n pieces of predicted channel information is earlier than the transmission time of the first indication information.

36. 36. The method of claim 35, wherein the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and a difference between a time point corresponding to the i-th predicted channel information and a time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .

37. 37. The method of claim 35 or 36, wherein the n pieces of measured channel information include the channel information measured based on the first reference signal.

38. 38. The method of claim 35, wherein the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information comprises one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

39. 1. A communication method comprising: receiving a first reference signal from a first device; determining, based on whether p pieces of predicted channel information are valid, to perform data transmission by using at least one of the p pieces of predicted channel information or channel information measured based on the first reference signal, where a time point corresponding to the p pieces of predicted channel information is later than a measurement time point of the first reference signal, and p is a positive integer; A method comprising:

40. 40. The method of claim 39, wherein when the p pieces of predicted channel information are invalid, data transmission is performed based on the channel information measured based on the first reference signal, or when the p pieces of predicted channel information are valid, data transmission is performed based on the p pieces of predicted channel information.

41. sending first indication information to the first device, the first indication information indicating at least one channel information; When the p pieces of predicted channel information are valid, the at least one piece of channel information includes the p pieces of predicted channel information; or 41. The method of claim 39 or 40, wherein when the p pieces of predicted channel information are invalid, the at least one piece of channel information includes the channel information measured based on the first reference signal and the p pieces of predicted channel information, or the at least one piece of channel information includes the channel information measured based on the first reference signal.

42. 42. The method of claim 41, wherein, based on a comparison result between the n pieces of predicted channel information and the n pieces of measured channel information, the p pieces of predicted channel information are valid or the p pieces of predicted channel information are invalid, the n pieces of predicted channel information correspond to the n pieces of measured channel information, n is a positive integer, and a time corresponding to the n pieces of predicted channel information is earlier than a time of transmission of the first indication information.

43. 43. The method of claim 42, wherein the i-th predicted channel information among the n pieces of predicted channel information corresponds to the i-th measured channel information among the n pieces of measured channel information, and a difference between a time point corresponding to the i-th predicted channel information and a time point corresponding to the i-th measured channel information is less than or equal to a first threshold, where i=1, 2, .

44. 44. The method of claim 42 or 43, wherein the n pieces of measured channel information include the channel information measured based on the first reference signal.

45. 45. The method of claim 42, wherein the comparison result between the n pieces of predicted channel information and the n pieces of measured channel information comprises one of the following: a difference between the n pieces of predicted channel information and the n pieces of measured channel information, or a channel correlation between the n pieces of predicted channel information and the n pieces of measured channel information.

46. 46. ​​The method of any one of claims 39 to 45, wherein the p predicted channel information pieces are obtained through prediction based on m measured channel information pieces, where m is a positive integer.

47. 47. The method of claim 46, wherein the m pieces of measured channel information include the channel information measured based on the first reference signal.

48. 48. The method of claim 41, wherein the first indication information further indicates a label of the at least one channel information, and the label of the at least one channel information indicates that the at least one channel information is a predicted result or a measured result, respectively.

49. 49. The method of claim 41, wherein when the at least one piece of channel information includes the p pieces of predicted channel information or the at least one piece of channel information includes the channel information measured based on the first reference signal and the p pieces of predicted channel information, the first indication information further indicates the time points corresponding to the p pieces of predicted channel information.

50. 50. A communication device comprising a module for performing the method of any one of claims 1 to 14, a module for performing the method of any one of claims 15 to 25, a module for performing the method of any one of claims 26 to 28, a module for performing the method of any one of claims 29 to 38 or a module for performing the method of any one of claims 39 to 49.

51. 1. A computer-readable storage medium, comprising: The computer readable storage medium comprises instructions that, when executed by a processor, cause the method of any one of claims 1 to 14, the method of any one of claims 15 to 25, the method of any one of claims 26 to 28, the method of any one of claims 29 to 38, or the method of any one of claims 39 to 49 to be implemented.

52. A communication device, The communications device includes a processor and a storage medium, the storage medium storing instructions that, when executed by the processor, cause a method as claimed in any one of claims 1 to 14 to be implemented, a method as claimed in any one of claims 15 to 25 to be implemented, a method as claimed in any one of claims 26 to 28 to be implemented, a method as claimed in any one of claims 29 to 38 to be implemented, or a method as claimed in any one of claims 39 to 49 to be implemented.

53. 1. A communication device including a processor, 50. A communications device, wherein the processor is configured to process data and / or information to implement a method according to any one of claims 1 to 14, to implement a method according to any one of claims 15 to 25, to implement a method according to any one of claims 26 to 28, to implement a method according to any one of claims 29 to 38, or to implement a method according to any one of claims 39 to 49.

54. 10. A chip including a processor, the processor being configured to execute a program or instructions to implement a method according to any one of claims 1 to 14, to implement a method according to any one of claims 15 to 25, to implement a method according to any one of claims 26 to 28, to implement a method according to any one of claims 29 to 38, or to implement a method according to any one of claims 39 to 49.

55. 1. A computer program product comprising:

10. The computer program product comprises computer program code or instructions which, when executed by a processor, cause the method of any one of claims 1 to 14 to be implemented, or the method of any one of claims 15 to 25 to be implemented, or the method of any one of claims 26 to 28 to be implemented, or the method of any one of claims 29 to 38 to be implemented, or the method of any one of claims 39 to 49 to be implemented.

56. A communication system comprising a combination of one or more of the following apparatus: apparatus for performing the method according to any one of claims 1 to 14; apparatus for performing the method according to any one of claims 15 to 25; apparatus for performing the method according to any one of claims 26 to 28; apparatus for performing the method according to any one of claims 29 to 38; or apparatus for performing the method according to any one of claims 39 to 49.

Images