Communication method and communication device

Abstract

The embodiment of the invention provides a communication method and a communication device, and the method comprises the steps that terminal equipment sends CSI feedback information to network equipment, and the network equipment sends first indication information to the terminal equipment, so as to indicate the terminal equipment to report the CSI feedback information again. The scheme provided by the embodiment of the invention can be applied to a communication system with an AI / ML function, is beneficial to reducing adverse effects caused by CSI feedback information packet loss, and ensures CSI feedback performance.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communications, and more specifically, to a communication method and a communication device. Background Art

[0002] In the communication system, the network equipment needs to determine the downlink data channel resources, modulation and coding scheme (MCS), precoding and other downlink channel configuration information for scheduling terminal equipment based on the downlink channel state information (CSI). The terminal equipment can calculate the downlink CSI by measuring the downlink reference signal and generate a CSI report to feed back to the network equipment.

[0003] After artificial intelligence (AI) was introduced into wireless communications, an AI-based CSI feedback method emerged. The AI ​​model has stronger feature extraction capabilities, can compress channel information more effectively, reduce information loss during the compression process, and ensure the accuracy of the restored channel information.

[0004] Frequent packet loss of CSI feedback information will seriously affect the feedback performance. Taking CSI feedback based on time domain correlation as an example, the AI ​​model on the terminal device side outputs CSI feedback information based on the current channel measurement results and status information; the AI ​​model on the network device side restores the channel information based on the current CSI feedback information and status information. The status information on the terminal device side is determined based on the historical channel measurement results. The status information on the network device side is determined based on the CSI feedback information received at the historical moment. In order to ensure feedback performance, the status information on the terminal device side and the status information on the network device side need to be updated synchronously. If the feedback transmission fails, the status information on the network device side cannot be updated synchronously with the status information on the terminal device side, and the matching degree between the status information on the network device side and the status information on the terminal device side will increase with the increase in the number of packet losses, which may cause mismatches in the subsequent dual-end processing process, resulting in serious loss of feedback performance.

[0005] Therefore, how to ensure feedback performance when CSI feedback information is frequently lost becomes an urgent problem to be solved. Summary of the invention

[0006] The embodiments of the present application provide a communication method and a communication device, which are conducive to reducing the adverse effects caused by CSI feedback information packet loss and ensuring feedback performance.

[0007] In a first aspect, a communication method is provided. The method may be executed by a terminal device or by a chip or circuit configured in the terminal device, and the present application does not limit the method.

[0008] The method includes: sending first channel state information (CSI) feedback information to a network device; receiving first indication information from the network device; and sending one or more CSI feedback information to the network device according to the first indication information, wherein the one or more CSI feedback information includes the first CSI feedback information.

[0009] In the solution of the embodiment of the present application, a retransmission mechanism of CSI feedback information is introduced, that is, the network device can instruct the terminal device to return the CSI feedback information sent previously, which is helpful to avoid the problem of feedback performance degradation caused by failure to report CSI feedback information.

[0010] The first indication information is used to instruct the terminal device to send one or more CSI feedback information to the network device.

[0011] Exemplarily, the one or more CSI feedback information may be one or more CSI feedback information of reporting failure. In this way, the terminal device may transmit back the CSI feedback information of reporting failure.

[0012] In combination with the first aspect, in certain implementations of the first aspect, before sending one or more CSI feedback information to the network device according to the first indication information, the method also includes: receiving second indication information from the network device, the second indication information indicating to increase the uplink transmission power.

[0013] In the solution of the embodiment of the present application, the network device can instruct the terminal device to increase the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring the successful transmission of the one or more CSI feedback information.

[0014] In combination with the first aspect, in certain implementations of the first aspect, sending first channel state information CSI feedback information to a network device includes: sending the first CSI feedback information to the network device on a first uplink resource indicated by first uplink resource configuration information; and receiving first indication information from the network device includes: receiving the first indication information and second uplink resource configuration information from the network device, the second uplink resource configuration information indicating a second uplink resource for transmitting one or more CSI feedback information, the number of uplink resources in the second uplink resource for transmitting the first CSI feedback information being greater than the number of resources of the first uplink resource.

[0015] In the solution of the embodiment of the present application, the network device can adjust the configuration of time-frequency domain resources and increase uplink resources, thereby improving channel transmission conditions, which is conducive to ensuring the successful transmission of the one or more CSI feedback information.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the first indication information is used to determine one or more CSI feedback information.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the first indication information indicates at least one of the following: identifiers of one or more CSI feedback information, identifiers of reference signals corresponding to one or more CSI feedback information, a first time period, identifiers of K CSI feedback information including one or more CSI feedback information, or identifiers of reference signals corresponding to K CSI feedback information, wherein K is a positive integer, the first time period is before the moment of sending the first indication information, the moment of sending one or more CSI feedback information is within the first time period, or the moment of sending the K CSI feedback information is within the first time period.

[0018] Exemplarily, the one or more CSI feedback information may be one or more CSI feedback information closest to the current moment among the K CSI feedback information. Alternatively, the one or more CSI feedback information may be one or more CSI feedback information randomly selected from the K CSI feedback information.

[0019] In combination with the first aspect, in some implementations of the first aspect, the first CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the first reference signal, the output of the second AI model is related to the channel measurement result of the first reference signal and the first historical input of the second AI model, the first historical input of the second AI model includes the channel measurement result of the first historical reference signal, the sending time of the first historical reference signal is earlier than the sending time of the first reference signal, and when the first CSI feedback information is successfully reported, the channel information corresponding to the first reference signal is the output of the first AI model, the input of the first AI model includes the first CSI feedback information or is based on the first CSI feedback information, the output of the first AI model is related to the first CSI feedback information and the first historical input of the first AI model, the first historical input of the first AI model includes the first historical CSI feedback information or is based on the first historical CSI feedback information, and the receiving time of the first historical CSI feedback information is earlier than the receiving time of the first CSI feedback information.

[0020] Exemplarily, the first CSI feedback information may be obtained by processing the output of the second AI model. For example, the first CSI feedback information may be obtained by quantizing the output of the second AI model.

[0021] Exemplarily, the input of the first AI model may be obtained by processing the first CSI feedback information. For example, the first CSI feedback information is dequantized and then input into the first AI model.

[0022] In the solution of the embodiment of the present application, a retransmission mechanism for CSI feedback information is introduced, that is, the network device can instruct the terminal device to transmit back the CSI feedback information sent previously. In the CSI feedback scenario based on time domain correlation, it is helpful to avoid the problem of continuous degradation of feedback performance due to failure to report CSI feedback information.

[0023] In combination with the first aspect, in some implementations of the first aspect, the number of CSI feedback information reporting failures reaches a first threshold.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the transmission period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0025] In the case where the CSI feedback information #2 corresponding to the reference signal #2 is reported successfully, the input of the first AI model includes the CSI feedback information #2, and the output of the first AI model includes the channel information corresponding to the reference signal #2. In the case where the CSI feedback information #3 corresponding to the reference signal #3 is reported unsuccessfully, the input of the first AI model includes the CSI feedback information #2, and the output of the first AI model includes the channel information corresponding to the reference signal #3. Among them, the sending time of the reference signal #2 is earlier than the sending time of the reference signal #3. The tolerance interval of the first AI model is the maximum value of the difference between the moment when the first AI model generates the channel information corresponding to the reference signal #3 and the receiving time of the CSI feedback information #2. The degree of performance degradation of the first AI model when the input includes the CSI feedback information #2 when generating the reference information #3 is less than or equal to the threshold #3. The maximum value of the difference corresponds to the threshold #3.

[0026] In the scheme of the embodiment of the present application, the first threshold can be determined based on the ratio of the tolerance interval of the first AI model and the transmission period of the reference signal, which is helpful to avoid the network device using historical CSI feedback information that exceeds the tolerance interval to restore channel information, resulting in serious performance deterioration.

[0027] In a second aspect, a communication method is provided. The method may be executed by a terminal device or by a chip or circuit configured in the terminal device, and the present application does not limit the method.

[0028] The method includes: receiving third indication information from a network device, the third indication information indicating switching from a first CSI feedback mode to a second CSI feedback mode, wherein the number of CSI feedback information reporting failures reaches a first threshold; and performing CSI feedback with the network device based on the second CSI feedback mode.

[0029] According to the solution of the embodiment of the present application, the terminal device and the network device perform CSI feedback based on the first CSI feedback mode. When the number of CSI feedback information that fails to be reported reaches a certain threshold (i.e., the first threshold), the network device can instruct the terminal device to switch to the second CSI feedback mode. In this way, the network device and the terminal device can perform CSI feedback based on the second CSI feedback mode to avoid performance degradation caused by packet loss of CSI feedback information in the first CSI feedback mode, which is conducive to the network device obtaining more accurate channel information, thereby ensuring feedback performance to ensure user experience.

[0030] In combination with the second aspect, in certain implementations of the second aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the transmission period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0031] In combination with the second aspect, in certain implementations of the second aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, and the sending time of the second historical reference signal is earlier than the sending time of the second reference signal; in the second CSI feedback mode, the third CSI feedback information is the output of the third AI model or is based on the output of the third AI model, the input of the third AI model includes the channel measurement result of the third reference signal, the output of the third AI model is related to the channel measurement result of the third reference signal and the third historical input of the third AI model, the third historical input of the third AI model includes the channel measurement result of the third historical reference signal, and the sending time of the third historical reference signal is earlier than the sending time of the third reference signal, wherein the number of bits of the third CSI feedback information is less than the number of bits of the second CSI feedback information.

[0032] In other words, both the second AI model and the third AI model are AI models with time domain correlation, and the number of bits of the CSI feedback information generated based on the second AI model is greater than the number of bits of the CSI feedback information generated based on the third AI model.

[0033] In the first CSI feedback mode, the recovery of the channel information at the current moment is related to the recovery of the historical channel information. The accuracy of the channel recovery at the current moment will continue to decrease as the number of packet losses of the previous historical feedback information increases, which will lead to continuous performance deterioration. In the scheme of the embodiment of the present application, the second CSI feedback mode still adopts a feedback method based on time domain correlation, so that the time domain correlation can continue to be used to improve the accuracy of channel information recovery to improve feedback performance. In addition, the feedback mode is switched to a model with a smaller number of feedback bits, that is, the number of bits of the CSI feedback information is reduced, thereby reducing the requirements for the transmission conditions of the uplink feedback information sending channel, that is, it is conducive to making the CSI feedback process based on time domain correlation adapt to the current channel transmission conditions, which is conducive to reducing the packet loss of uplink feedback information, thereby helping to ensure user experience.

[0034] In combination with the second aspect, in certain implementations of the second aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, and the sending time of the second historical reference signal is earlier than the sending time of the second reference signal. In the second CSI feedback mode, the fourth CSI feedback information is the output of the fourth AI model or is based on the output of the fourth AI model, the input of the fourth AI model includes the channel measurement result of the fourth reference signal, and the output of the fourth AI model is related to the channel measurement result of the fourth reference signal.

[0035] In other words, the output of the fourth AI model is independent of the historical input of the fourth AI model. The fourth AI model is an AI model without time domain correlation.

[0036] In the solution of the embodiment of the present application, in the second CSI feedback mode, a model based on non-time domain correlation is adopted to realize the generation of CSI feedback information and the recovery of channel information. The determination of channel information is independent of historical data, so as to avoid the problem of continuous degradation of feedback performance caused by the failure of reporting CSI feedback information in the first CSI feedback mode, which is conducive to ensuring feedback performance and thus ensuring user experience.

[0037] In combination with the second aspect, in certain implementations of the second aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, the sending time of the second historical reference signal is earlier than the sending time of the second reference signal, and in the second CSI feedback mode, the fifth CSI feedback information is based on the predefined codebook and the channel measurement result of the fifth reference signal.

[0038] The predefined codebook can be understood as a non-AI model, that is, the fifth CSI feedback information is generated by a non-AI model.

[0039] In the scheme of the embodiment of the present application, in the second CSI feedback mode, CSI feedback is performed based on a predefined codebook feedback method, and the determination of the channel information is independent of the historical data, so as to avoid the problem of continuous degradation of feedback performance due to the failure to report CSI feedback information in the first CSI feedback mode, which is conducive to ensuring feedback performance and thus ensuring user experience.

[0040] In a third aspect, a communication method is provided. The method may be executed by a terminal device or by a chip or circuit configured in the terminal device, and the present application does not limit the method.

[0041] The method includes: receiving fourth indication information from a network device, wherein the number of CSI feedback information reporting failures reaches a threshold #1, the fourth indication information indicates resetting first state information of a second AI model to second state information, the second state information is before the CSI feedback information reporting failure occurs, the first state information is based on a fourth historical input of the second AI model, the fourth historical input of the second AI model includes a channel measurement result of a fourth historical reference signal, the second state information is initial state information of the second AI model or is based on a fifth historical input of the second AI model, the fifth historical input of the second AI model includes a channel measurement result of a fifth historical reference signal, and a sending time of the fourth historical reference signal is later than a sending time of the fifth historical reference signal; and sending sixth CSI feedback information to the network device, the sixth CSI feedback information is an output of the second AI model or is based on an output of the second AI model, the input of the second AI model includes a channel measurement result of a sixth reference signal, and the output of the second AI model is related to the channel measurement result of the sixth reference signal and the second state information.

[0042] In the scheme of the embodiment of the present application, when the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct to reset the status information of the model used to generate the CSI feedback information, reset the status information of the model to before the CSI feedback information packet loss occurs, and restore the consistency of the status information of the model on the network device and the terminal device, thereby facilitating improving the accuracy of the channel information recovered by the network device, thereby improving the feedback performance, and ensuring the user experience.

[0043] In combination with the third aspect, in certain implementations of the third aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the sending period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0044] In a fourth aspect, a communication method is provided. The method can be executed by a network device or by a chip or circuit configured in the network device, and the present application does not limit this method.

[0045] The method includes: sending first uplink resource configuration information to a terminal device, the first uplink resource configuration information indicating a first uplink resource used to transmit first channel state information CSI feedback information; sending first indication information and second uplink resource configuration information to the terminal device, the first indication information is used to instruct the terminal device to send one or more CSI feedback information, the second uplink resource configuration information indicates a second uplink resource used to transmit one or more CSI feedback information, the one or more CSI feedback information including the first CSI feedback information; receiving one or more CSI feedback information from the terminal device.

[0046] In combination with the fourth aspect, in certain implementations of the fourth aspect, before receiving one or more CSI feedback information from the terminal device, the method also includes: sending second indication information to the terminal device, the second indication information indicating to increase the uplink transmission power.

[0047] In combination with the fourth aspect, in certain implementations of the fourth aspect, the number of uplink resources in the second uplink resources used to transmit the first CSI feedback information is greater than the number of resources in the first uplink resources.

[0048] In combination with the fourth aspect, in certain implementations of the fourth aspect, the first indication information is used to determine one or more CSI feedback information.

[0049] In combination with the fourth aspect, in certain implementations of the fourth aspect, the first indication information indicates at least one of the following: an identifier of one or more CSI feedback information, an identifier of a reference signal corresponding to one or more CSI feedback information, a first time period, an identifier of K CSI feedback information including one or more CSI feedback information, or an identifier of a reference signal corresponding to K CSI feedback information, wherein K is a positive integer, the first time period is before the moment of sending the first indication information, the moment of sending one or more CSI feedback information is within the first time period, or the moment of sending the K CSI feedback information is within the first time period.

[0050] In combination with the fourth aspect, in certain implementations of the fourth aspect, the number of CSI feedback information reporting failures reaches a first threshold.

[0051] In combination with the fourth aspect, in certain implementations of the fourth aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the sending period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0052] In combination with the fourth aspect, in certain implementations of the fourth aspect, the first CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the first reference signal, the output of the second AI model is related to the channel measurement result of the first reference signal and the first historical input of the second AI model, the first historical input of the second AI model includes the channel measurement result of the first historical reference signal, the sending time of the first historical reference signal is earlier than the sending time of the first reference signal, and when the first CSI feedback information is successfully reported, the channel information corresponding to the first reference signal is the output of the first AI model, the input of the first AI model includes the first CSI feedback information or is based on the first CSI feedback information, the output of the first AI model is related to the first CSI feedback information and the first historical input of the first AI model, the first historical input of the first AI model includes the first historical CSI feedback information or is based on the first historical CSI feedback information, and the receiving time of the first historical CSI feedback information is earlier than the receiving time of the first CSI feedback information.

[0053] In a fifth aspect, a communication method is provided. The method can be executed by a network device or by a chip or circuit configured in the network device, and the present application does not limit this method.

[0054] The method includes: sending third indication information to a terminal device, wherein the number of CSI feedback information reporting failures reaches a first threshold, and the third indication information indicates switching from a first CSI feedback mode to a second CSI feedback mode; and performing CSI feedback with the terminal device based on the second CSI feedback mode.

[0055] In combination with the fifth aspect, in certain implementations of the fifth aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the sending period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0056] In combination with the fifth aspect, in certain implementations of the fifth aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, and the sending time of the second historical reference signal is earlier than the sending time of the second reference signal; in the second CSI feedback mode, the third CSI feedback information is the output of the third AI model or is based on the output of the third AI model, the input of the third AI model includes the channel measurement result of the third reference signal, the output of the third AI model is related to the channel measurement result of the third reference signal and the third historical input of the third AI model, the third historical input of the third AI model includes the channel measurement result of the third historical reference signal, and the sending time of the third historical reference signal is earlier than the sending time of the third reference signal, wherein the number of bits of the third CSI feedback information is less than the number of bits of the second CSI feedback information.

[0057] In combination with the fifth aspect, in certain implementations of the fifth aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, and the sending time of the second historical reference signal is earlier than the sending time of the second reference signal. In the second CSI feedback mode, the fourth CSI feedback information is the output of the fourth AI model or is based on the output of the fourth AI model, the input of the fourth AI model includes the channel measurement result of the fourth reference signal, and the output of the fourth AI model is related to the channel measurement result of the fourth reference signal.

[0058] In combination with the fifth aspect, in certain implementations of the fifth aspect, in the first CSI feedback mode, the second CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes the channel measurement result of the second reference signal, the output of the second AI model is related to the channel measurement result of the second reference signal and the second historical input of the second AI model, the second historical input of the second AI model includes the channel measurement result of the second historical reference signal, the sending time of the second historical reference signal is earlier than the sending time of the second reference signal, and in the second CSI feedback mode, the fifth CSI feedback information is based on the predefined codebook and the channel measurement result of the fifth reference signal.

[0059] In a sixth aspect, a communication method is provided. The method can be executed by a network device or by a chip or circuit configured in the network device, and the present application does not limit this method.

[0060] The method includes: sending fourth indication information to a terminal device, wherein the number of times that CSI feedback information reporting fails reaches a first threshold, the fourth indication information indicates that first state information of a second AI model is reset to second state information, the second state information is before the CSI feedback information reporting failure occurs, the first state information is based on a fourth historical input of the second AI model, the fourth historical input of the second AI model includes a channel measurement result of a fourth historical reference signal, the second state information is initial state information of the second AI model or is based on a fifth historical input of the second AI model, the fifth historical input of the second AI model includes a channel measurement result of a fifth historical reference signal, and a sending time of the fourth historical reference signal is later than a sending time of the fifth historical reference signal; receiving sixth CSI feedback information from the terminal device, the sixth CSI feedback information is an output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes a channel measurement result of a sixth reference signal, and the output of the second AI model is related to the channel measurement result of the sixth reference signal and the second state information.

[0061] In combination with the sixth aspect, in certain implementations of the sixth aspect, the first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first AI model to the sending period of the reference signal, and the tolerance interval is predefined or preconfigured.

[0062] In a seventh aspect, a communication device is provided, which may be a terminal device, or a device, module, circuit or chip configured in the terminal device, or a device that can be used in conjunction with the terminal device. In one design, the communication device may include a module corresponding to the method / operation / step / action described in any one of the first to third aspects, and the module may be a hardware circuit, or software, or a combination of a hardware circuit and software. In one design, the communication device may include a processing module and a communication module.

[0063] Among them, the sending module is used to execute the sending action in the method described in any aspect of the first to third aspects above, the processing module is used to execute the processing-related actions in the method described in any aspect of the first to third aspects above, and the receiving module is used to execute the receiving-related actions in the method described in any aspect of the first to third aspects above.

[0064] In an eighth aspect, a communication device is provided, which may be a network device, or a device, module, circuit or chip configured in a network device, or a device that can be used in conjunction with a network device. In one design, the communication device may include a module corresponding to the method / operation / step / action described in any one of aspects 4 to 6, and the module may be a hardware circuit, or software, or a combination of a hardware circuit and software. In one design, the communication device may include a processing module and a communication module.

[0065] Among them, the receiving module is used to execute the receiving action in the method described in any aspect of the fourth to sixth aspects above, the processing module is used to execute the processing-related actions in the method described in any aspect of the fourth to sixth aspects above, and the sending module is used to execute the sending action in the method described in any aspect of the fourth to sixth aspects above.

[0066] In a ninth aspect, a communication device is provided, comprising a processor and a storage medium, wherein the storage medium stores instructions, which, when executed by the processor, enable the method in the first aspect or any possible implementation of the first aspect to be implemented, enable the method in the second aspect or any possible implementation of the second aspect to be implemented, enable the method in the third aspect or any possible implementation of the third aspect to be implemented, enable the method in the fourth aspect or any possible implementation of the fourth aspect to be implemented, enable the method in the fifth aspect or any possible implementation of the fifth aspect to be implemented, or enable the method in the sixth aspect or any possible implementation of the sixth aspect to be implemented.

[0067] In a tenth aspect, a communication device is provided, comprising a processor, wherein the processor is used to process data and / or information so that the method in the first aspect or any possible implementation of the first aspect is implemented, the method in the second aspect or any possible implementation of the second aspect is implemented, the method in the third aspect or any possible implementation of the third aspect is implemented, the method in the fourth aspect or any possible implementation of the fourth aspect is implemented, the method in the fifth aspect or any possible implementation of the fifth aspect is implemented, or the method in the sixth aspect or any possible implementation of the sixth aspect is implemented.

[0068] Optionally, the communication device may further include a communication interface, the communication interface being used to receive data and / or information and transmit the received data and / or information to the processor. Optionally, the communication interface is also used to output the data and / or information processed by the processor.

[0069] In an eleventh aspect, a chip is provided, comprising a processor, wherein the processor is used to run a program or instruction so that the method in the first aspect or any possible implementation of the first aspect is implemented, the method in the second aspect or any possible implementation of the second aspect is implemented, the method in the third aspect or any possible implementation of the third aspect is implemented, the method in the fourth aspect or any possible implementation of the fourth aspect is implemented, the method in the fifth aspect or any possible implementation of the fifth aspect is implemented, or the method in the sixth aspect or any possible implementation of the sixth aspect is implemented.

[0070] Optionally, the chip may further include a memory, wherein the memory is used to store programs or instructions. Optionally, the chip may further include the transceiver.

[0071] In the twelfth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes instructions, which, when executed by a processor, enables the method in the first aspect or any possible implementation of the first aspect to be implemented, enables the method in the second aspect or any possible implementation of the second aspect to be implemented, enables the method in the third aspect or any possible implementation of the third aspect to be implemented, enables the method in the fourth aspect or any possible implementation of the fourth aspect to be implemented, enables the method in the fifth aspect or any possible implementation of the fifth aspect to be implemented, or enables the method in the sixth aspect or any possible implementation of the sixth aspect to be implemented.

[0072] In the thirteenth aspect, a computer program product is provided, comprising computer program codes or instructions, which, when executed, implement the method in the first aspect or any possible implementation of the first aspect, implement the method in the second aspect or any possible implementation of the second aspect, implement the method in the third aspect or any possible implementation of the third aspect, implement the method in the fourth aspect or any possible implementation of the fourth aspect, implement the method in the fifth aspect or any possible implementation of the fifth aspect, or implement the method in the sixth aspect or any possible implementation of the sixth aspect.

[0073] In a fourteenth aspect, a communication system is provided, comprising a combination of one or more of the following devices: a communication device for executing the first aspect or any possible implementation of the first aspect, a communication device for executing the second aspect or any possible implementation of the second aspect, a communication device for executing the third aspect or any possible implementation of the third aspect, a communication device for executing the fourth aspect or any possible implementation of the fourth aspect, a communication device for executing the fifth aspect or any possible implementation of the fifth aspect, or a communication device for executing the sixth aspect or any possible implementation of the sixth aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of the present application;

[0075] Figure 2 is a schematic diagram of another communication system applicable to an embodiment of the present application;

[0076] Figure 3 is a schematic block diagram of an autoencoder;

[0077] Figure 4 It is a schematic diagram of an AI application framework;

[0078] Figure 5 It is a schematic diagram of a CSI feedback process based on time domain correlation;

[0079] Figure 6 It is a schematic diagram of another CSI feedback process based on time domain correlation;

[0080] Figure 7 is a schematic flow chart of a communication method provided in an embodiment of the present application;

[0081] Figure 8 is a schematic diagram of an uplink resource provided in an embodiment of the present application;

[0082] Fig. 9 is a schematic diagram of the performance under different conditions;

[0083] Fig.10 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0084] Fig.11 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0085] Fig.12 It is a schematic diagram of a CSI feedback process based on time domain correlation provided in an embodiment of the present application;

[0086] Fig.13 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0087] Fig.14 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0088] Fig.15 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0089] Fig.16 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0090] Fig.17 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0091] Fig.18 is a schematic flow chart of another communication method provided in an embodiment of the present application;

[0092] Fig.19 is a schematic block diagram of a communication device provided in an embodiment of the present application;

[0093] Fig. 20 It is a schematic block diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0094] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0095] The technical solution provided in the present application can be applied to various communication systems, such as: the fifth generation (5th generation, 5G) or new radio (new radio, NR) system, long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD) system, wireless local area network (wireless local area network, WLAN) system, satellite communication system, future communication system, such as the sixth generation (6th generation, 6G) mobile communication system, or a fusion system of multiple systems, etc. The technical solution provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of things (IoT) communication system or other communication systems.

[0096] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling or data, etc. The network element may also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc., and the network element is used as an example for description in the present disclosure. For example, the communication system may include at least one terminal device and at least one network device. The network device may send a downlink signal to the terminal device, and / or the terminal device may send an uplink signal to the network device. It is understandable that the terminal device in the present disclosure may be replaced by a first network element, and the network device may be replaced by a second network element, and the two perform the corresponding communication method in the present disclosure.

[0097] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0098] The terminal device may be a device that provides voice / data, such as a handheld device or a vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (public land mobile The embodiments of the present application do not limit this.

[0099] As an example but not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.

[0100] In the embodiment of the present application, the device for realizing the function of the terminal device may be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which may be installed in the terminal device or used in combination with the terminal device. In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices. In the embodiment of the present application, only the device for realizing the function of the terminal device is used as an example for explanation, and the scheme of the embodiment of the present application is not limited.

[0101] The network device in the embodiment of the present application may be a device for communicating with a terminal device, and the network device may also be referred to as an access network device or a wireless access network device, such as a base station. The network device in the embodiment of the present application may refer to a wireless access network (RAN) node (or device) that connects a terminal device to a wireless network. Base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station, auxiliary station, multi-standard wireless (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip used to be set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, and a device that performs the base station function in future communication systems. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the V2X technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0102] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0103] In some deployments, the network device mentioned in the embodiments of the present application may be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit control plane (central unit-control plane, CU-CP)) and a user plane CU node (central unit user plane (central unit-user plane, CU-UP)) and a DU node. For example, the network device may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0104] In some deployments, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes implement part of the functions of the base station. For example, the RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be set separately, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, AAU, or RRH.

[0105] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit in the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0106] In the embodiments of the present application, the device for realizing the function of the network device may be a network device; or it may be a device capable of supporting the network device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device may be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the device for realizing the function of the network device is a network device as an example for explanation, and the scheme of the embodiments of the present application is not limited.

[0107] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The scenarios in which the network device and the terminal device are located are not limited in the embodiments of the present application. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the network device.

[0108] In wireless communication networks, such as mobile communication networks, the services supported by the network are becoming more and more diverse, so the demands that need to be met are becoming more and more diverse. For example, the network needs to be able to support ultra-high speed, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling more and more complicated. In addition, as the network becomes more and more powerful, such as supporting higher and higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new requirements, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. In order to meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0109] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0110] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment, etc., or the AI ​​node can also be deployed separately, for example, deployed in a location other than any of the above devices, such as a host or cloud server in an over the top (OTT) system. The AI ​​node can communicate with other devices in the communication system, and the other devices can be, for example, one or more of the following: network equipment, terminal equipment, or network elements of the core network, etc.

[0111] It is understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes are responsible for different functions.

[0112] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0113] The AI ​​node can be an AI network element or an AI module. The AI ​​node is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements can be the same or different. The AI ​​model in the AI ​​node can implement different functions according to different parameter configurations. The AI ​​model in the AI ​​node can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the biases in the activation function), input parameters (such as the type of input parameters and / or the dimension of input parameters), or output parameters (such as the type of output parameters and / or the dimension of output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0114] An AI node can have one or more models. The learning process, training process, or reasoning process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0115] Figure 1 Schematic diagram of a communication system applicable to the communication method of the embodiment of the present application. Figure 1 As shown, the communication system 100 may include at least one network device, such as Figure 1 The network device 110 shown; the communication system 100 may also include at least one terminal device, such as Figure 1 The terminal device 120 and the terminal device 130 are shown. The network device 110 and the terminal devices (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via a multi-antenna technology.

[0116] Figure 2 is a schematic diagram of another communication system applicable to the communication method of the embodiment of the present application. Figure 1 For the communication system 100 shown, Figure 2 The communication system 200 shown also includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building a training data set or training an AI model.

[0117] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a part of the trained AI model may be deployed on the network device 110, and another part may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0118] It should be understood that Figure 2 Only the example of the AI ​​network element 140 being directly connected to the network device 110 is used for illustration. In other scenarios, the AI ​​network element 140 may also be connected to the terminal device. Alternatively, the AI ​​network element 140 may be connected to the network device 110 and the terminal device at the same time. Alternatively, the AI ​​network element 140 may also be connected to the network device 110 through a third-party network element. The embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0119] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, Figure 1 In the network device 110 or terminal device shown in FIG. 1 , one or more AI modules may be deployed in the network device 110 or one or more AI modules may be deployed in the terminal device.

[0120] It should be noted that Figure 1 and Figure 2 This is a simplified schematic diagram for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices. Figure 1 and Figure 2 In practical applications, the communication system may include multiple network devices and multiple terminal devices. The embodiment of the present application does not limit the number of network devices and terminal devices included in the communication system.

[0121] In order to facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0122] (1) AI Model:

[0123] An AI model is an algorithm or computer program that can implement AI functions. The AI ​​model represents the mapping relationship between the input and output of the model. The type of AI model can be a neural network, linear regression model, decision tree model, support vector machine (SVM), Bayesian network, Q learning model or other machine learning (ML) model.

[0124] (2) Two-terminal model:

[0125] The two-end model can also be called a bilateral model, a collaborative model, a dual model, or a two-side model. The two-end model refers to a model composed of multiple sub-models. The multiple sub-models that constitute the model need to match each other. The multiple sub-models can be deployed in different nodes.

[0126] The embodiments of the present application involve an encoder for compressing CSI and a decoder for recovering compressed CSI. The encoder and the decoder are used in matching manner, and it can be understood that the encoder and the decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched by the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and corresponds one to one.

[0127] In one possible design, a set of matched encoders and decoders can be two parts of the same auto-encoder (AE). The AE model in which the encoder and decoder are deployed on different nodes is a typical bilateral model. The encoder and decoder of the AE model are usually matched with the encoder and decoder trained together. An autoencoder is an unsupervised learning neural network, which is characterized by taking the input data as label data, so the autoencoder can also be understood as a self-supervised learning neural network. The autoencoder can be used for data compression and recovery. For example, the encoder in the autoencoder can compress (encode) data A to obtain data B; the decoder in the autoencoder can decompress (decode) data B to restore data A. Or it can be understood that the decoder is the inverse operation of the encoder.

[0128] For example, Figure 3 As shown, the encoder processes the input V to obtain a processed result z, and the decoder can decode the encoder output z into the desired output V'.

[0129] The AI ​​model in the embodiment of the present application may include an encoder deployed on a terminal device and a decoder deployed on a network device.

[0130] (3) Neural network (NN):

[0131] 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, thus enabling neural networks to learn any mapping.

[0132] A neural network can be composed of neural units. A neural unit can be a s and intercept 1 as input. A neural network is a network formed by connecting many of the above single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0133] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in the present disclosure may be a deep neural network (DNN). Depending on how the network is constructed, DNN may include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0134] CNN is a neural network that is specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling on the time axis) and image data (discrete sampling on two dimensions) can be considered to be data with a grid-like structure. CNN does not use all the input information for calculations at once, but uses a fixed-size window to intercept part of the information for convolution operations, which greatly reduces the amount of calculation of model parameters. In addition, depending on the type of information intercepted by the window (for example, people and objects in a picture are different types of information), each window can use different convolution kernel operations, which enables CNN to better extract the features of the input data.

[0135] RNN is a type of DNN network that uses feedback time series information. Its input includes the new input value at the current moment and its own output value at the previous moment. RNN is suitable for obtaining sequence features that are correlated in time, and is particularly suitable for applications such as speech recognition and channel coding.

[0136] The characteristic of FNN network is that neurons in adjacent layers are fully connected to each other, which usually requires a large amount of storage space and leads to high computational complexity.

[0137] The above FNN, CNN, and RNN are all constructed based on neurons. As mentioned above, each neuron performs a weighted sum operation on its input value, and the weighted sum result generates an output through a nonlinear function. The weights of the weighted sum operation of neurons in the neural network and the nonlinear function are called the parameters of the neural network. The parameters of all neurons in a neural network constitute the parameters of this neural network.

[0138] (4) Training data set and inference data:

[0139] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0140] The training data set is used for training the AI ​​model. The training data set may include the input of the AI ​​model, or the input and target output of the AI ​​model. The training data set includes one or more training data. The training data may include training samples input to the AI ​​model, or may include the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or label sample. The label is the true value.

[0141] In the field of communications, training data sets can include simulation data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Due to differences in the geographical environment and channel conditions in which the data is generated, such as indoor and outdoor conditions, mobile speeds, frequency bands, or antenna configurations, the collected data can be classified when acquiring the data. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0142] Model training is essentially learning some of its features from the training data. In the process of training AI models (such as neural network models), because we hope that the output of the AI ​​model is as close as possible to the value we really want to predict, we can compare the current network's predicted value with the target value we really want, and then update the weight vector of each layer of the AI ​​model according to the difference between the two (of course, there is usually an initialization process before the first update, that is, pre-configuring parameters for each layer in the AI ​​model). For example, if the network's predicted value is high, adjust the weight vector to make it predict lower, and keep adjusting until the AI ​​model can predict the target value we really want or a value very close to the target value we really want. Therefore, it is necessary to predefine "how to compare the difference between the predicted value and the target value", which is the loss function or objective function, which are important equations used to measure the difference between the predicted value and the target value. Among them, taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference, so the training of the AI ​​model becomes a process of minimizing this loss as much as possible, so that the value of the loss function is less than the threshold, or the value of the loss function meets the target requirements. 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 of layers, width, weights of neurons, or parameters in the activation function of the neurons of the neural network.

[0143] Inference data can be used as input to the trained AI model for inference of the AI ​​model. During the model inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0144] (5) Design of AI model:

[0145] The design of AI models mainly includes data collection (such as collecting training data and / or inference data), model training, and model inference. It can also include the application of inference results.

[0146] Figure 4 An AI application framework is shown.

[0147] In the aforementioned data collection link, the data source is used to provide training data sets and reasoning data. In the model training link, the AI ​​model is obtained by analyzing or training the training data provided by the data source. Among them, the AI ​​model represents the mapping relationship between the input and output of the model. Learning the AI ​​model through the model training node is equivalent to using the training data to learn the mapping relationship between the input and output of the model. In the model reasoning link, the AI ​​model trained through the model training link is used to reason based on the reasoning data provided by the data source to obtain the reasoning result. This link can also be understood as: inputting the reasoning data into the AI ​​model, and obtaining the output through the AI ​​model, which is the reasoning result. The reasoning result can indicate: the configuration parameters used (executed) by the execution object, and / or the operation performed by the execution object. The reasoning result is published in the reasoning result application link, for example, the reasoning result can be uniformly planned by the execution (actor) entity, for example, the execution entity can send the reasoning result to one or more execution objects (for example, network devices or terminal devices, etc.) for execution. For example, the execution entity can also feedback the performance of the model to the data source to facilitate the subsequent implementation of the model update training.

[0148] It is understandable that a network element with AI function may be included in the communication system. The above-mentioned AI model design-related links may be performed by one or more network elements with artificial intelligence functions. In one possible design, an AI function (such as an AI module or an AI entity) may be configured in an existing network element in the communication system to implement AI-related operations, such as training and / or reasoning of an AI model. For example, the existing network element may be a network device or a terminal device, etc. Or in another possible design, an independent network element may also be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element may be referred to as an AI network element or an AI node, etc., and the embodiment of the present application does not limit this name. Exemplarily, the AI ​​network element may be directly connected to the network device in the communication system, or indirectly connected through a third-party network element and the network device. Among them, the third-party network element may be a core network element such as an authentication management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM), a cloud server or other network element, without limitation. Exemplarily, the independent network element may be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, it may be deployed on a cloud server. Exemplarily, Figure 2An AI network element 140 is introduced into the communication system shown.

[0149] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The reasoning process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training link of the terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training link of the network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training link of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device, and send the model parameters of the decoder to the network device. Then, the model reasoning link corresponding to the encoder is performed in the terminal device, and the model reasoning link corresponding to the decoder is performed in the network device.

[0150] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers of the model, and / or weights, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0151] (6) Channel state information:

[0152] In a communication system (e.g., an LTE communication system or an NR communication system), network equipment needs to decide on the resource, MCS, and precoding configuration of the downlink data channel of the terminal device based on CSI. It can be understood that CSI is a type of channel information, which is information that can reflect channel characteristics and channel quality.

[0153] CSI measurement refers to the receiving end solving the channel information based on the reference signal sent by the transmitting end, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of the channel state information reference signal (CSI-RS), synchronization signal / physical broadcast channel block (SSB), channel sounding reference signal (SRS) or demodulation reference signal (DMRS). CSI-RS, SSB and DMRS can be used to measure downlink CSI. SRS and DMRS can be used to measure uplink CSI.

[0154] Taking the FDD communication scenario as an example, in the FDD communication scenario, since the uplink and downlink channels are not reciprocal or cannot be guaranteed, the network equipment usually sends a downlink reference signal to the terminal device, and the terminal device performs channel measurement and interference measurement based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report according to the protocol predefined method or the network device configuration method, and feeds it back to the network device so that it can obtain the downlink CSI.

[0155] Exemplarily, CSI may include at least one of the following: channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal receiving power (RSRP) or signal to interference plus noise ratio (SINR), etc. The signal to interference plus noise ratio may also be referred to as signal to interference plus noise ratio.

[0156] Among them, RI is used to indicate the number of downlink transmission layers recommended by the terminal device, CQI is used to indicate the modulation and coding mode supported by the current channel conditions determined by the terminal device, and PMI is used to indicate the precoding recommended by the terminal device. The number of precoding layers indicated by PMI corresponds to RI.

[0157] As the size of the MIMO system antenna array continues to increase, the number of supported antenna ports increases, and the corresponding channel matrix and precoding matrix dimensions grow. In order to enable the terminal device to estimate (measure) the downlink channel, the overhead of the network device sending the reference signal increases. At the same time, the error of approximating the large-scale channel matrix and precoding matrix with a limited number of predefined codewords will increase. One way to improve the accuracy of channel recovery is to increase the number of codewords in the codebook, but this will also lead to an increase in the overhead of CSI feedback (including the corresponding codeword number and one or more of the weighting coefficients), thereby reducing the available resources for data transmission and causing system capacity loss.

[0158] The introduction of AI technology into wireless communication networks has resulted in a CSI feedback method based on the AI ​​model. The terminal device uses the AI ​​model to compress and feedback the CSI, and the network device uses the AI ​​model to recover the compressed CSI. In the AI-based CSI feedback, a sequence (such as a bit sequence) is transmitted, and the overhead is lower than that of traditional CSI feedback CSI. Moreover, the AI ​​model has a stronger nonlinear feature extraction capability, and can more effectively compress and represent channel information and recover the channel more effectively based on the feedback information than traditional solutions.

[0159] by Figure 3 For example, Figure 3 The encoder in may be a CSI generator, and the decoder may be a CSI reconstructor. The encoder may be deployed in a terminal device, and the decoder may be deployed in a network device. The terminal device may generate CSI feedback information z from the CSI original information V through the encoder. The terminal device reports a CSI report, and the CSI report may include the CSI feedback information z. The network device may reconstruct the CSI information through the decoder, that is, obtain CSI recovery information V'.

[0160] The CSI original information V may be obtained by the terminal device through CSI measurement. For example, the CSI original information V may include the channel response of the downlink channel or the eigenvector matrix (a matrix composed of eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and / or quantization operation of the characteristic matrix according to the codebook in the related scheme is replaced by the operation of processing the characteristic matrix by the encoder to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through a decoder to obtain CSI recovery information V'.

[0161] The following further illustrates the training process and reasoning process of the AI ​​model in the embodiment of the present application.

[0162] The training data used to train the AI ​​model includes training samples and sample labels. For example, the training samples are the channel information measured by the terminal device, and the sample labels are the real channel information, that is, the true value CSI. In the case where the encoder and decoder belong to the same autoencoder, the training data may only include training samples, or the training samples are sample labels.

[0163] In the field of wireless communications, the true CSI may be a high-precision CSI.

[0164] The specific training process is as follows: the model training node uses the encoder to process the channel information, that is, the training sample, to obtain CSI feedback information, and uses the decoder to process the feedback information to obtain the recovered channel information, that is, the CSI recovery information. Then calculate the difference between the CSI recovery information and the corresponding sample label, that is, the value of the loss function, and update the parameters of the encoder and decoder according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, that is, minimize the loss function. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeat the above operations to obtain an encoder and decoder that meet the target requirements. The above model training node can be a terminal device, a network device, or other network elements with AI functions in a communication system.

[0165] Frequent packet loss of CSI feedback information will seriously affect the feedback performance, that is, affect the accuracy of channel information recovery on the network device side. The following takes CSI feedback based on time domain correlation as an example for explanation.

[0166] In wireless communication links, the channels of medium and low-speed users change continuously in time, and the feedback performance can be improved by mining the time domain correlation of the channel. For example, channel information compression can be achieved by mining the time domain correlation between historical channel measurement results and current channel measurement results, which is beneficial to reduce the overhead of feedback channel information while reducing information loss during the compression process. Terminal devices and network devices can use time domain correlation to perform compressed feedback and recovery of channel information respectively.

[0167] Figure 5 A schematic diagram of a CSI feedback process based on time domain correlation is shown. In a CSI feedback scenario based on time domain correlation, when CSI feedback information is generated on the terminal device side, the CSI feedback information is not only related to the current channel measurement result, but also to the channel measurement result at a historical moment. When channel information is restored on the network device side, the restored channel information is not only related to the current CSI feedback information, but also to the CSI feedback information at a historical moment.

[0168] A dual-end model based on time domain correlation is deployed on terminal devices and network devices to implement CSI feedback based on time domain correlation. Figure 3 For example, the AI ​​model deployed on the terminal device can be an encoder, and the AI ​​model deployed on the network device can be a decoder. Figure 5 The feedback process shown is explained.

[0169] The terminal device performs channel measurement on the reference signal Rt to obtain the channel measurement result at the current moment. Figure 5 As shown, taking the original CSI information as the channel measurement result as an example, the original CSI information at the current moment is the channel measurement result H at the current moment. t The channel measurement result H at the current moment t Input to the encoder, the encoder outputs CSI feedback information c t The output of the encoder is consistent with the channel measurement result H at the current moment t and encoder status information t-1 Among them, the status information of the encoder is t-1 is determined based on the historical input of the encoder, such as Figure 5 As shown, the historical input of the encoder may include the channel measurement results at the historical moment. t and e t-1 Mining the time domain correlation of channel information. Figure 5 As shown, t = 1, 2, 3, 4. On the network device side, the CSI feedback information c at the current moment is t Input to the decoder, the decoder outputs CSI recovery information H' t , that is, the channel information corresponding to the reference signal Rt. The decoder output is consistent with the CSI feedback information c at the current moment. t Input and decoder status information d t-1 Among them, the state information of the decoder d t-1 is determined based on the historical input of the decoder, such as Figure 5 As shown, the historical input of the decoder may include CSI feedback information at historical moments. t and d t-1 Mining the time domain correlation of channel information. In order to ensure feedback performance, the status information on the network device side and the status information on the terminal device side need to be updated synchronously. Figure 5 As shown, the encoder outputs CSI feedback information c t In addition, the status information on the terminal device side is also updated. In addition to outputting the CSI recovery information H' t In addition, the status information of the network device side is also updated. In this way, the status information of the network device side and the terminal device side are updated synchronously.

[0170] The following is an example. The network device sends a reference signal R3 to the terminal device. The terminal device performs channel measurement on the reference signal R3 to obtain a channel measurement result H3. The channel measurement result H3 is input into the encoder of the terminal device, and the encoder obtains CSI feedback information c3 based on the channel measurement result H3 and the state information e2 of the encoder, and updates the state information of the encoder to obtain state information e3. The reference signal R3 is the reference signal corresponding to the CSI feedback information c3. The network device receives the CSI feedback information c3 and inputs the CSI feedback information c3 into the decoder of the network device. The decoder obtains CSI recovery information H'3 based on the CSI feedback information c3 and the state information d2 of the decoder, and updates the state information of the decoder to obtain state information d3. The CSI recovery information H'3 is the channel information corresponding to the CSI feedback information c3, or in other words, the CSI recovery information H'3 is the channel information corresponding to the reference signal R3. The network device sends a reference signal R4 to the terminal device. The terminal device performs channel measurement on the reference signal R4 to obtain a channel measurement result H4. The channel measurement result H4 is input into the encoder of the terminal device. The encoder obtains CSI feedback information c4 according to the channel measurement result H4 and the state information e3, and updates the state information to obtain the state information e4. The reference signal R4 is the reference signal corresponding to the CSI feedback information c4. The network device receives the CSI feedback information c4 and inputs the CSI feedback information c4 into the decoder of the network device. The decoder obtains CSI recovery information H'4 according to the CSI feedback information c4 and the state information d3 of the decoder, and updates the state information of the decoder to obtain the state information d4. The CSI recovery information H'4 is the channel information corresponding to the CSI feedback information c4, or in other words, the CSI recovery information H'4 is the channel information corresponding to the reference signal R4.

[0171] Taking reference signal R3 as a reference, the reference signal received by the terminal device before receiving reference signal R3 is the historical reference signal. Taking reference signal R4 as a reference, the reference signal received by the terminal device before receiving reference signal R4 is the historical reference signal, for example, R3. The state information of the encoder is determined based on the historical input of the encoder, and the historical input of the encoder may include the channel measurement result of the historical reference signal. For example, Figure 5As shown, the state information e4 is updated based on the channel measurement result H3. Taking the CSI feedback information c3 as a reference, the CSI feedback information received by the network device before receiving the CSI feedback information c3 is the historical CSI feedback information. Taking the CSI feedback information c4 as a reference, the CSI feedback information received by the network device before receiving the CSI feedback information c4 is the historical CSI feedback information, for example, c3. The state information of the decoder is determined based on the historical input of the decoder, and the historical input of the decoder may include the historical CSI feedback information. For example, Figure 5 As shown, the state information d4 is updated based on the CSI feedback information c3.

[0172] When the CSI feedback information fails to be transmitted due to poor channel transmission conditions or other reasons, the network device cannot synchronously update the status information on the network device side.

[0173] Figure 6 FIG. 4 is a schematic diagram showing another CSI feedback process based on time domain correlation. Figure 6 As shown, when the feedback transmission fails, the decoder can process based on the CSI feedback information received last time. For example, the terminal device inputs the channel measurement result H3 into the encoder. The encoder outputs CSI feedback information c3 based on the channel measurement result H3 and the state information e2, and updates the state information to obtain the state information e3. The state information e3 can be used in the next CSI feedback process. When the CSI feedback information c3 fails to be reported, the network device inputs the CSI feedback information c2 received last time into the decoder. The decoder outputs CSI recovery information H'3 based on the CSI feedback information c2 and the state information d2. Since the CSI feedback information c3 is not received, the network device cannot update the state information normally. Figure 6 The status information d3 in and the status information of the decoder thereafter are the same as Figure 5 The state information d3 obtained after updating based on the CSI feedback information c3 is different from the subsequent state information of the decoder. Figure 6 The decoded CSI recovery information H'3 and the subsequent CSI recovery information are Figure 5 The CSI recovery information H'3 and subsequent CSI recovery information are different. Figure 6 The accuracy of the decoded CSI recovery information H'3 and the subsequent CSI recovery information is lower than Figure 5 The CSI recovery information H'3 and subsequent CSI recovery information are different.

[0174] After packet loss occurs, the status information on the network device side cannot be updated synchronously with the status information on the terminal device side, and there is a difference between the status information on the terminal device side and the status information on the network device side, that is, the matching degree of the encoder and the decoder decreases. In other words, when the feedback transmission fails, the terminal device updates the status information on the terminal device side, while the network device cannot update the status information on the network device side, resulting in the inconsistency between the update times of the status information on the network device side and the update times of the status information on the terminal device side, which in turn results in a difference between the status information on the terminal device side and the status information on the network device side, that is, the matching degree of the encoder and the decoder decreases.

[0175] The difference between the state information on the terminal device side and the state information on the network device side will make it impossible for the decoder to recover the accurate channel information, resulting in performance loss. In addition, the difference between the state information on the terminal device side and the state information on the network device side will increase with the increase in the number of packet losses, which may cause mismatch in the subsequent dual-end processing process, and thus lead to a continuous decline in feedback performance.

[0176] In view of this, the present application provides a communication method and a communication device, which are conducive to ensuring feedback performance when CSI feedback information is frequently lost. The communication method can be applied to the above communication system, such as an FDD communication scenario. In addition, optionally, the communication method can also be used in a TDD communication scenario, which is not limited by the present disclosure.

[0177] It should be understood that in the present application, indication includes direct indication (also called explicit indication) and implicit indication. Wherein, direct indication of information A means including the information A; implicit indication of information A means indicating information A through the correspondence between information A and information B and direct indication of information B. Wherein, the correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0178] It should be understood that in the present application, information C is used to determine information D, which includes information D being determined based only on information C, and information D being determined based on information C and other information. In addition, information C is used to determine information D, and it can also be indirectly determined, for example, information D is determined based on information E, and information E is determined based on information C.

[0179] In addition, "network element A sends information A to network element B" in each embodiment of the present application can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in the present application can be understood similarly and will not be repeated here.

[0180] Figure 7 It is a schematic flow chart of a communication method provided by the present application.

[0181] like Figure 7 As shown, the method 700 may include the following steps.

[0182] 710. The terminal device sends CSI feedback information #1 (an example of the first CSI feedback information) to the network device.

[0183] 720. The network device sends indication information #1 (an example of the first indication information) to the terminal device.

[0184] Indication information #1 instructs the terminal device to send one or more CSI feedback information to the network device, and the one or more CSI feedback information include CSI feedback information #1.

[0185] 730. The terminal device sends one or more CSI feedback information to the network device according to indication information #1.

[0186] The one or more CSI feedback information include CSI feedback information previously sent by the terminal device, for example, CSI feedback information #1.

[0187] In other words, in method 700, the network device sends indication information #1 to the terminal device to instruct the terminal device to resend the CSI feedback information that was previously sent.

[0188] The CSI feedback information previously sent by the terminal device may include at least one of the following: CSI feedback information of failed reporting or CSI feedback information of successful reporting.

[0189] The one or more CSI feedback information may only include CSI feedback information previously sent by the terminal device. Alternatively, the one or more CSI feedback information may also include CSI feedback information not yet sent by the terminal device.

[0190] Failure to report CSI feedback information means that the CSI feedback information is lost, and the network device does not obtain the CSI feedback information sent by the terminal device. The number of CSI feedback information that failed to report is the number of times the CSI feedback information is lost. One or more CSI feedback information can be referred to as one or more packets. CSI feedback information can also be referred to as CSI feedback bits. CSI feedback information is indicated by a CSI report. One feedback information corresponds to one CSI report. For the convenience of description, in the embodiment of the present application, CSI feedback information can also be referred to as feedback information.

[0191] Exemplarily, the CSI feedback information may be sent via uplink control information (UCI), that is, the UCI includes the content of the CSI feedback information.

[0192] Optionally, method 700 may further include step 701 (not shown in the figure).

[0193] 701. The network device sends uplink resource configuration information #1 (an example of the first uplink resource configuration information) to the terminal device, where the uplink resource configuration information #1 indicates the uplink resource #1 (an example of the first uplink resource) used to transmit the CSI feedback information #1.

[0194] In this case, step 710 may include: the terminal device sends CSI feedback information #1 to the network device on uplink resource #1.

[0195] Step 720 may include: the network device sends indication information #1 and uplink resource configuration information #2 (an example of second uplink resource configuration information) to the terminal device, and the uplink resource configuration information #2 indicates the uplink resource #2 (an example of the second uplink resource) used to transmit the one or more CSI feedback information.

[0196] In this case, step 730 may include: the terminal device sends the one or more CSI feedback information on uplink resource #2.

[0197] In the solution of the embodiment of the present application, a retransmission mechanism of CSI feedback information is introduced, that is, the network device can instruct the terminal device to return the CSI feedback information sent previously, which is helpful to avoid the problem of feedback performance degradation caused by failure to report CSI feedback information.

[0198] The following is an exemplary description of indication information #1.

[0199] In a possible implementation, indication information #1 may be used to determine the one or more CSI feedback information.

[0200] Exemplarily, the indication information #1 may be carried in downlink control information (DCI).

[0201] As an example, indication information #1 may indicate the one or more CSI feedback information.

[0202] For example, which CSI feedback information the one or more CSI feedback information specifically includes may be determined by the network device and notified to the terminal device.

[0203] Optionally, the indication information #1 may indicate at least one of the following:

[0204] One or more identifiers of CSI feedback information;

[0205] An identifier of a reference signal corresponding to one or more CSI feedback information; or

[0206] Time period #1 (an example of the first time period), time period #1 is before the sending time of indication information #1. The sending time of the one or more CSI feedback information is within time period #1.

[0207] Indication information #1 can notify the terminal device which CSI feedback information needs to be sent by indicating at least one of the above items.

[0208] Exemplarily, the identifier of the CSI feedback information may be an index of the CSI feedback information.

[0209] Exemplarily, the identifier of the reference signal may be an index of the reference signal.

[0210] Time period #1 is before the sending time of indication information #1, and the end time of time period #1 may be before the sending time of indication information #1. In this case, the one or more CSI feedback information is the one or more CSI feedback information previously sent by the terminal device. The network device may instruct the terminal device to resend all CSI feedback information sent in time period #1 through indication information #1.

[0211] Exemplarily, the one or more CSI feedback information indicated by indication information #1 may be CSI feedback information that fails to be reported.

[0212] In this way, the terminal device can send back CSI feedback information of reporting failure.

[0213] As an example, indication information #1 may indicate K CSI feedback information including the one or more CSI feedback information, where K is a positive integer.

[0214] For example, which CSI feedback information is specifically included in the one or more CSI feedback information may be determined by the terminal device. The network device may indicate K CSI feedback information, and the terminal device may determine which CSI feedback information to report.

[0215] Optionally, the indication information #1 may indicate at least one of the following:

[0216] Identifiers of K CSI feedback information;

[0217] Identifiers of reference signals corresponding to the K CSI feedback information; or

[0218] Time period #2 (an example of the first time period), the sending time of K CSI feedback information is within time period #2, and time period #2 is before the sending time of indication information #1.

[0219] Indication information #1 may notify the terminal device of a set of CSI feedback information that can be sent by indicating at least one of the above items, and the terminal device may select which CSI feedback information needs to be sent.

[0220] Time period #2 is before the sending time of indication information #1, and the end time of time period #2 is before the sending time of indication information #1. In this case, the K CSI feedback information is the K CSI feedback information previously sent by the terminal device. The number of all CSI feedback information sent by the terminal device in time period #2 is K.

[0221] Exemplarily, the K CSI feedback information indicated by indication information #1 may be CSI feedback information that fails to be reported.

[0222] In this way, the terminal device can send back CSI feedback information of reporting failure.

[0223] Exemplarily, the number of the one or more CSI feedback information may be determined by the network device. For example, indication information #1 may also indicate the number of the one or more CSI feedback information.

[0224] Exemplarily, the quantity of the one or more CSI feedback information may be determined by the terminal device itself.

[0225] Exemplarily, the number of the one or more CSI feedback information may be predefined. For example, the number of the one or more CSI feedback information may be predefined by predefining a calculation rule for the number of the one or more CSI feedback information. For example, the number of the one or more CSI feedback information may be predefined as a minimum integer whose ratio to K is greater than or equal to threshold #2. For another example, a specific value of the number of the one or more CSI feedback information may be predefined.

[0226] The one or more CSI feedback information may be determined in various ways.

[0227] Exemplarily, the one or more CSI feedback information may be one or more CSI feedback information closest to the current moment among the K CSI feedback information, or the one or more CSI feedback information may be one or more CSI feedback information farthest from the current moment among the K CSI feedback information.

[0228] For example, the reporting times of the K CSI feedback information may be represented as CSI feedback information 1, CSI feedback information 2, ... CSI feedback information K in order from far to near from the current time. The k CSI feedback information closest to the current time may include: CSI feedback information K-k+1, CSI feedback information K-k+2, ... CSI feedback information K. The k CSI feedback information farthest from the current time may include: CSI feedback information 1, CSI feedback information 2, ... CSI feedback information k. k is a positive integer less than or equal to K.

[0229] Exemplarily, the one or more CSI feedback information may be one or more CSI feedback information randomly selected from the K CSI feedback information.

[0230] It should be understood that the above is only an example, and one or more CSI feedback information may also be determined in other ways, which is not limited in the embodiments of the present application.

[0231] In the case that the one or more CSI feedback information are determined by the terminal device itself, the terminal device may notify the network device of which CSI feedback information the one or more CSI feedback information include.

[0232] Exemplarily, method 700 may further include: the terminal device sends indication information #2 to the network device, where the indication information #2 indicates the one or more CSI feedback information.

[0233] For example, the indication information #2 may include the identifiers of the one or more CSI feedback information. For example, the identifiers of the one or more CSI feedback information are respectively carried in one or more CSI reports.

[0234] For another example, the one or more CSI feedback information may be a plurality of consecutive CSI feedback information in the one or more CSI feedback information, and the indication information #2 may include one or more of the following information: the starting number of the one or more CSI feedback information, the number of the one or more CSI feedback information, or the ending number. The part of the one or more items not indicated by the indication information #2 may be obtained through other means, such as based on protocol pre-definition. The number of each CSI feedback information in the one or more CSI feedback information may be used to indicate the position of the CSI feedback information in the K CSI feedback information.

[0235] For another example, indication information #2 may include an identifier of a reference signal corresponding to the one or more CSI feedback information.

[0236] For another example, indication information #2 may include a bitmap of the one or more CSI feedback information. For example, the one or more CSI feedback information is transmitted via UCI, and a bitmap is reserved at the start position of the UCI to indicate one or more CSI feedback information among the K feedback information.

[0237] For another example, indication information #2 may indicate time period #1.

[0238] It should be understood that the above is only an example, and the indication information #2 can also indicate the one or more CSI feedback information in other ways, which is not limited in this embodiment of the present application.

[0239] In another possible implementation, indication information #1 is used to trigger the terminal device to send one or more CSI feedback information to the network device. That is, indication information #1 may only be used to trigger step 730, but not to determine the one or more CSI feedback information.

[0240] In this case, the one or more CSI feedback information may be predefined.

[0241] For example, the one or more CSI feedback information may be one or more CSI feedback information that has been sent most recently to the current moment. That is, after receiving indication information #1, the terminal device may resend one or more CSI feedback information that is most recently to the current moment.

[0242] The CSI feedback information is determined based on the channel measurement result of the reference signal.

[0243] Exemplarily, the reference signal may be any one of CSI-RS, SSB or DMRS.

[0244] Exemplarily, the reference signal may be a reference signal sent periodically, or may be a reference signal sent aperiodically.

[0245] Exemplarily, the uplink resource configuration information #1 may indicate the periodic uplink resources configured by the network device.

[0246] The periodic uplink resource may be used to transmit CSI feedback information, that is, the periodic uplink resource includes uplink resource #1 used to transmit CSI feedback information #1.

[0247] Exemplarily, the uplink resource configuration information #1 may indicate the uplink resource scheduled by the network device. The uplink resource is a non-periodic uplink resource. The uplink resource includes an uplink resource #1 for transmitting CSI feedback information #1.

[0248] Exemplarily, the uplink resource configuration information #2 may indicate the uplink resource scheduled by the network device. The uplink resource may include the uplink resource #2 used to transmit the one or more CSI feedback information.

[0249] For example, the one or more CSI feedback information may include CSI feedback information #A and CSI feedback information #B that have been sent by the terminal device. The terminal device may send CSI feedback information #A and CSI feedback information #B on the uplink resource #2.

[0250] For another example, the one or more CSI feedback information may include CSI feedback information #A that has been sent by the terminal device and CSI feedback information #C that has not been fed back. The terminal device may send CSI feedback information #A and CSI feedback information #C on the uplink resource #2.

[0251] Optionally, the number of uplink resources used to transmit CSI feedback information #1 in the uplink resource #2 is greater than the number of uplink resources #1.

[0252] That is, the network device instructs to increase uplink resources to send the one or more CSI feedback information.

[0253] For example, the network device may give priority to increasing uplink control channel element (CCE) resources of the terminal device.

[0254] Figure 8 A schematic diagram of uplink resources is shown.

[0255] For example, Figure 8As shown, uplink resource configuration information #1 may indicate the periodic uplink resources configured by the network device. The terminal device sends CSI feedback information #A on resource #1-1 on the periodic uplink resource, and sends CSI feedback information #B on resource #1-2. The one or more CSI feedback information may include CSI feedback information #A and CSI feedback information #B. The terminal device sends CSI feedback information #A on resource #2-1 on the uplink resource #2 indicated by the uplink resource configuration information #2, and sends CSI feedback information #B on resource #2-2. Among them, the number of resources used for resource #1-1 is less than the number of resources for resource #2-1. The number of resources for resource #1-2 is less than the number of resources for resource #2-2. In addition, the terminal device may continue to send CSI feedback information on the periodic uplink resources configured by the network device, for example, reporting CSI feedback information #C.

[0256] Packet loss is usually caused by the current uplink channel conditions being insufficient to support the transmission of CSI feedback information. In the solution of the embodiment of the present application, the network device can adjust the configuration of time-frequency domain resources and increase uplink resources, thereby improving channel transmission conditions, which is conducive to ensuring the successful transmission of the one or more CSI feedback information. For example, the one or more CSI feedback information can be CSI feedback information that has been sent before, and the network device can instruct the terminal device to increase uplink resources, which is conducive to ensuring that the terminal device can successfully transmit the one or more CSI feedback information.

[0257] Optionally, before step 720, method 700 may further include step 711 (not shown in the figure).

[0258] Step 711: The network device sends indication information #3 (an example of second indication information) to the terminal device, where indication information #3 indicates to increase the uplink transmission power.

[0259] In the solution of the embodiment of the present application, the network device may instruct the terminal device to increase the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring the successful transmission of the one or more CSI feedback information. For example, the one or more CSI feedback information may be the CSI feedback information sent before, and the network device may instruct the terminal device to increase the uplink transmission power, which is conducive to ensuring that the terminal device can successfully transmit the one or more CSI feedback information.

[0260] The application scenario of method 700 is exemplarily described below.

[0261] Exemplarily, the method 700 may be applied to a CSI feedback scenario based on time domain correlation.

[0262] In a feedback scenario based on time domain correlation, CSI feedback information corresponding to a reference signal is determined based on a channel measurement result with respect to the reference signal and a channel measurement result of a historical reference signal with respect to the reference signal.

[0263] The historical reference signals relative to a reference signal include reference signals received before the terminal device receives the reference signal.

[0264] In other words, the CSI feedback information generated by the terminal device for a certain reference signal is not only related to the channel measurement result at the current moment (ie, the measurement result of the reference signal), but also related to the channel measurement result at the past moment.

[0265] In a feedback scenario based on time domain correlation, channel information corresponding to the CSI feedback information is determined based on the CSI feedback information and historical CSI feedback information relative to the CSI feedback information.

[0266] The historical CSI feedback information relative to one CSI feedback information includes CSI feedback information received before the network device receives the CSI feedback information.

[0267] In other words, the channel information for a certain reference signal recovered by the network device is not only related to the currently received CSI feedback information (ie, the CSI feedback information corresponding to the reference signal), but also related to the CSI feedback information received at a past moment.

[0268] CSI feedback based on time domain correlation can be achieved through AI CSI dual-end compression feedback. Specifically, a dual-end model based on time domain correlation is deployed on the terminal device and the network device to achieve CSI feedback. The dual-end model based on time domain correlation includes an AI model deployed on the terminal device and an AI model deployed on the network device. The AI ​​model deployed on the terminal device and the AI ​​model deployed on the network device are matched. For example, the AI ​​model deployed on the terminal device may be an encoder, and the AI ​​model deployed on the network device may be a decoder. The output of the encoder is related to the current input of the encoder and the historical input of the encoder. The output of the decoder is related to the current input of the decoder and the historical input of the decoder.

[0269] The encoder may be referred to as an enhanced space-frequency joint CSI compression encoder model. The decoder may be referred to as an enhanced space-frequency joint CSI compression decoder model. For example, the dual-end model may be an enhanced space-frequency joint CSI compression model. For example, the architecture design of the dual-end model may adopt any one of a transformer, RNN, CNN, or a long short-term memory (LSTM) network. Alternatively, the dual-end model may also be other self-constructed AI models.

[0270] Exemplarily, the dual-end model based on time domain correlation includes a decoder #1 (an example of the first AI model) deployed on a network device and an encoder #1 (an example of the second AI model) deployed on a terminal device. Encoder #1 and decoder #1 are matched. The following example illustrates the CSI feedback process based on time domain correlation.

[0271] For a reference signal, the input of encoder #1 includes CSI original information. The CSI original information may be a channel measurement result of the reference signal.

[0272] For example, the type of the original CSI information may be any of the following: channel response, channel eigenvector matrix or precoding matrix, etc.

[0273] The channel response can also be called a channel matrix. The eigenvector matrix of a channel is a matrix composed of the eigenvectors of the channel.

[0274] The output of encoder #1 includes CSI feedback information corresponding to the reference signal. Alternatively, the CSI feedback information corresponding to the reference signal may be obtained based on the output of encoder #1. For example, the output result of encoder #1 is quantized to obtain the CSI feedback information corresponding to the reference signal. For ease of description, the embodiment of the present application is mainly described by taking the output of the encoder including CSI feedback information as an example, and does not limit the solution of the embodiment of the present application.

[0275] The output of encoder #1 is related to the current input and historical input of encoder #1. The current input includes the channel measurement result of the reference signal. The historical input includes the channel measurement result of the historical reference signal received before the reception time of the reference signal.

[0276] When the network device receives CSI feedback information, the input of decoder #1 includes CSI feedback information. Alternatively, the input of decoder #1 is determined based on the CSI feedback information. For example, the CSI feedback information may be obtained by quantizing the output result of encoder #1, and the CSI feedback information may be dequantized before being input to decoder #1. For ease of description, the embodiment of the present application is mainly described by taking the input of the decoder including CSI feedback information as an example, and does not limit the solution of the embodiment of the present application.

[0277] The output of decoder #1 includes the channel information corresponding to the CSI feedback information. The output of decoder #1 is related to the current input and historical input of decoder #1. The current input includes the CSI feedback information. The historical input includes the historical CSI feedback information received before the reception time of the CSI feedback information.

[0278] When the network device does not receive the CSI feedback information at the expected reception time of the CSI feedback information, the current CSI feedback information reporting fails. The input of decoder #1 may include the last historical CSI feedback information received before the expected reception time of the CSI feedback information, that is, the CSI feedback information received last time. The output of decoder #1 includes the channel information corresponding to the CSI feedback information that failed to be reported. The output of decoder #1 is related to the current input and historical input of decoder #1. The current input includes the last historical CSI feedback information received before the expected reception time of the CSI feedback information. The historical input includes the historical CSI feedback information received before the expected reception time of the CSI feedback information.

[0279] The following description is made by taking CSI feedback information #1 as an example.

[0280] The network device sends reference signal #1 to the terminal device. The terminal device performs channel measurement on reference signal #1 to obtain the channel measurement result of reference signal #1. The channel measurement result of reference signal #1 (an example of the first reference signal) is input into encoder #1. Encoder #1 outputs CSI feedback information #1. Alternatively, the output of encoder #1 is processed to obtain CSI feedback information #1. Among them, the output of encoder #1 is related to the channel measurement result of reference signal #1 and the historical input #1 of encoder #1 (an example of the first historical input of the second AI model). The historical input #1 of encoder #1 includes the channel measurement result of historical reference signal #1 (an example of the first historical reference signal). The reception time of historical reference signal #1 is earlier than the reception time of reference signal #1. In other words, the sending time of historical reference signal #1 is earlier than the sending time of reference signal #1. The terminal device sends the CSI feedback information #1 to the network device.

[0281] When the network device receives the CSI feedback information #1, the CSI feedback information #1 is input into the decoder #1. Alternatively, the CSI feedback information #1 is processed and then input into the decoder #1. Decoder #1 outputs the channel information corresponding to the CSI feedback information #1, that is, the channel information corresponding to the reference signal #1. The output of decoder #1 is related to the CSI feedback information #1 and the historical input #1 of decoder #1 (an example of the first historical input of the first AI model). The historical input #1 of decoder #1 includes historical CSI feedback information #1 (an example of the first historical CSI feedback information) or is based on historical CSI feedback information #1. The reception time of historical CSI feedback information #1 is earlier than the reception time of CSI feedback information #1. In other words, the sending time of historical CSI feedback information #1 is earlier than the sending time of CSI feedback information #1. In other words, the sending time of the reference signal corresponding to the historical CSI feedback information #1 is earlier than the sending time of reference signal #1.

[0282] In the case where the network device fails to successfully receive the CSI feedback information #1, the CSI feedback information received before the expected reception time of the CSI feedback information #1 is input into the decoder. For example, the historical CSI feedback information #1 is input into the decoder #1. The decoder #1 outputs the channel information corresponding to the CSI feedback information #1, that is, the channel information corresponding to the reference signal #1.

[0283] Alternatively, the CSI feedback process based on time domain correlation can be understood as follows.

[0284] The output of encoder #1 is related to the input of encoder #1 and the state information of encoder #1. The output of decoder #1 is related to the input of decoder #1 and the state information of decoder #1.

[0285] That is, the CSI feedback information may be determined according to the input of encoder #1 and the state information of encoder #1, and the channel information corresponding to the CSI feedback information may be determined according to the input of decoder #1 and the state information of decoder #1.

[0286] The state information of encoder #1 is determined based on the historical input of encoder #1. Alternatively, the state information of encoder #1 is the initial state information of encoder #1. For example, there is no historical input for the current encoder #1, and the state information of the current encoder #1 may be the initial state information. The state information of decoder #1 is determined based on the historical input of decoder #1. Alternatively, the state information of decoder #1 is the initial state information of decoder #1. For example, there is no historical input for the current decoder #1, and the state information of the current decoder #1 may be the initial state information.

[0287] The input of encoder #1 includes the channel measurement result of the reference signal. The output of encoder #1 includes the CSI feedback information corresponding to the reference signal, or based on the output of encoder #1. The output of encoder #1 is related to the current input and current state information of encoder #1. The current input includes the channel measurement result of the reference signal. The current state information of encoder #1 is determined based on the historical input of encoder #1. The historical input includes the channel measurement results of the historical reference signals received before the reception time of the reference signal. Alternatively, the current state information of encoder #1 may also be the initial state information. For example, the reference signal is the first reference signal sent by the network device to the terminal device, there is no historical input to encoder #1, and the current state information is the initial state information.

[0288] In the case where the network device receives CSI feedback information, the input of decoder #1 includes the CSI feedback information, or is based on the CSI feedback information. The output of decoder #1 includes the channel information corresponding to the CSI feedback information. The output of decoder #1 is related to the current input and current state information of decoder #1. The current input includes the CSI feedback information. The current state information of decoder #1 is determined based on the historical input of decoder #1. The historical input includes the historical CSI feedback information received before the reception time of the CSI feedback information. Alternatively, the current state information of decoder #1 may also be the initial state information. For example, the reference signal is the first reference signal sent by the network device to the terminal device, there is no historical input to decoder #1, and the current state information is the initial state information.

[0289] When the network device does not receive the CSI feedback information at the expected reception time of the CSI feedback information, the current CSI feedback information reporting fails. The input of decoder #1 may include the last historical CSI feedback information received before the expected reception time of the CSI feedback information, that is, the CSI feedback information received last time. The output of decoder #1 includes the channel information corresponding to the CSI feedback information that failed to be reported. The output of decoder #1 is related to the current input and current state information of decoder #1. The current input includes the last historical CSI feedback information received before the expected reception time of the CSI feedback information. The current state information is determined based on the historical input of decoder #1. The historical input includes the historical CSI feedback information received before the expected reception time of the CSI feedback information.

[0290] The following description is made by taking CSI feedback information #1 as an example.

[0291] The channel measurement result of the reference signal #1 is input into the encoder #1. The encoder #1 outputs the CSI feedback information #1 according to the channel measurement result of the reference signal #1 and the state information #1 of the encoder #1. Alternatively, the output of the encoder #1 is processed to obtain the CSI feedback information #1. The state information #1 of the encoder #1 is determined according to the historical input #1 of the encoder #1. Alternatively, the state information #1 of the encoder #1 may be the initial state information of the encoder #1.

[0292] When the network device receives the CSI feedback information #1, the CSI feedback information #1 is input into the decoder #1. Alternatively, the CSI feedback information #1 is processed and then input into the decoder #1. The decoder #1 outputs the channel information corresponding to the CSI feedback information #1, i.e., the channel information corresponding to the reference signal #1, according to the CSI feedback information #1 and the state information #1 of the decoder #1. The state information #1 of the decoder #1 is determined according to the historical input #1 of the decoder #1. Alternatively, the state information #1 of the decoder #1 may be the initial state information of the decoder #1.

[0293] The relevant description of the historical input #1 of encoder #1 and the historical input #1 of decoder can be found in the previous text and will not be repeated here.

[0294] In the case where the network device fails to successfully receive the CSI feedback information #1, the CSI feedback information received before the expected reception time of the CSI feedback information #1 is input into the decoder. For example, the historical CSI feedback information #1 is input into the decoder #1. The decoder #1 outputs the channel information corresponding to the CSI feedback information #1, that is, the channel information corresponding to the reference signal #1.

[0295] An example of the CSI feedback process based on time domain correlation can be found in Figure 5 , I will not go into details here.

[0296] The state information of the encoder can also be referred to as the state information of the terminal device side. The state information of the decoder can also be referred to as the state information of the network device side.

[0297] In the CSI feedback scenario based on time domain correlation, failure to report CSI feedback information will affect the accuracy of the channel information decoded by the network device, that is, affect the feedback performance, and the accuracy of the channel information decoded by the network device will continue to decrease with the increase in the number of packet losses, which will lead to a continuous decline in feedback performance.

[0298] Exemplarily, the feedback performance can be evaluated by the similarity or difference between the channel information recovered by the network device side and the channel measurement result. For example, the square generalized cosine similarity (SGCS) performance is a feedback performance indicator of the CSI feedback process based on time domain correlation. That is, the feedback performance is evaluated by the SGCS between the channel information recovered by the network device side and the channel measurement result.

[0299] Fig. 9 Figure 2 shows a schematic diagram of SGCS performance under different conditions. Fig. 9As shown in the figure, the horizontal axis is time t and the vertical axis is SGCS. When no packet loss occurs, SGCS remains stable and lossless. When the last received CSI feedback information is used after packet loss occurs, SGCS decreases, and SGCS decreases after each packet loss, that is, each packet loss will cause performance loss.

[0300] In the scheme of the embodiment of the present application, a retransmission mechanism of CSI feedback information is introduced, that is, the network device can instruct the terminal device to return the CSI feedback information sent before. In the CSI feedback scenario based on time domain correlation, this is conducive to avoiding the problem of continuous degradation of feedback performance due to the failure to report CSI feedback information. Exemplarily, the CSI feedback information retransmitted by the terminal device may include CSI feedback information that failed to report. In this way, the network device side can realize the recovery of subsequent channel information based on the returned CSI feedback information that failed to report, which is conducive to improving the accuracy of the channel information. For example, the decoder can update the state information of the decoder based on the returned CSI feedback information that failed to report, so as to better match the state information of the encoder, that is, to achieve alignment of the state information on both sides, thereby improving the accuracy of the recovered channel information, thereby ensuring the feedback performance.

[0301] Optionally, when the number of failed CSI feedback information reporting attempts reaches threshold #1 (an example of a first threshold), the network device sends indication information #1 to the terminal device.

[0302] The network device counts the number of times cnt when CSI feedback information packet loss occurs. When the number of times cnt when CSI feedback information packet loss reaches a threshold #1, the network device instructs the terminal device to resend the CSI feedback information.

[0303] The starting time of statistics can be set as needed.

[0304] Exemplarily, the network device may count the number of CSI feedback information packet losses after the terminal device accesses. For example, a counter #1 is started at the time of terminal device access to count the number of CSI feedback information packet losses, and step 720 is triggered when the value cnt of counter #1 is equal to threshold #1.

[0305] Exemplarily, method 700 may be repeatedly executed. The starting time of the statistics may be the time of receiving the one or more CSI feedback information. That is, the network device may re-count the number of times the CSI feedback information packet is lost after receiving the one or more CSI feedback information. For example, after receiving the one or more CSI feedback information, counter #1 is reset.

[0306] The above is only an example, and the starting time of the statistics can also be other times, which is not limited in the embodiments of the present application.

[0307] In a possible implementation, when cnt=N, the network device may send indication information #1 to instruct the terminal device to resend part or all of the CSI feedback information that failed to be reported. N represents threshold #1. The number of CSI feedback information that failed to be reported is N.

[0308] As mentioned above, indication information #1 may indicate K CSI feedback information, from which the terminal device may select one or more CSI feedback information for reporting. Exemplarily, the K CSI feedback information may be part or all of the N CSI feedback information that failed to be reported.

[0309] For example, the K pieces of CSI feedback information may be the N pieces of CSI feedback information that failed to be reported. In this case, K=N. That is, indication information #1 indicates N pieces of CSI feedback information that failed to be reported.

[0310] Alternatively, as mentioned above, the indication information #1 may indicate one or more CSI feedback information. Exemplarily, the one or more CSI feedback information may be part or all of the N CSI feedback information that failed to be reported.

[0311] In the scheme of the embodiment of the present application, the packet loss situation can be monitored. When the number of CSI feedback information that fails to be reported reaches a certain threshold (i.e., threshold #1), the terminal device will retransmit part or all of the CSI feedback information that fails to be reported to the network device to avoid continuous degradation of feedback performance due to frequent packet loss.

[0312] The following is an exemplary description of threshold #1.

[0313] Exemplarily, threshold #1 may be predefined. Alternatively, threshold #1 may be preconfigured.

[0314] Exemplarily, threshold #1 may be determined according to the characteristics of a two-terminal model based on time-domain correlation.

[0315] The characteristics of the two-ended model may include a tolerance interval of the two-ended model, ie, a tolerance interval of decoder #1.

[0316] Exemplarily, the reference signal may be sent periodically. Threshold #1 may be based on a ratio of a tolerance interval of decoder #1 to a transmission period of the reference signal. For example, threshold #1 may be a maximum integer less than or equal to a ratio of a tolerance interval of decoder #1 to a transmission period of the reference signal.

[0317] The tolerance intervals of different double-ended models can be different or the same.

[0318] Exemplarily, the tolerance interval of the double-ended model may be predefined or preconfigured.

[0319] For example, the model library includes 6 different levels of dual-end models, that is, the model library of the terminal device includes 6 different levels of encoders of the dual-end model, and the model library of the network device includes 6 different levels of decoders of the dual-end model. The level of the encoder used by the terminal device is the same as the level of the decoder used by the network device. The dual-end model is a dual-end model based on time correlation. The periodic intervals of CSI feedback corresponding to the dual-end models of levels 1-6 are: 5 / 10 / 20 / 40 / 80ms respectively.

[0320] The tolerance intervals of the two-ended model corresponding to levels 1-6 are 20 / 30 / 40 / 80 / 100 ms, respectively. Accordingly, N is (20 / 5) / (30 / 10) / (40 / 20) / (80 / 40) / (100 / 80)=4 / 3 / 2 / 2 / 1, respectively.

[0321] As mentioned above, in the CSI feedback scenario based on time domain correlation, when the CSI feedback information that the network device currently needs to receive fails to be successfully received, the input of decoder #1 can be historical CSI feedback information (for example, the CSI feedback information received last time). Fig. 9 As shown, using historical CSI feedback information to restore channel information will lead to performance degradation. If the historical CSI feedback information is far away from the current time, it may seriously affect the accuracy of the restored channel information, that is, cause serious deterioration of performance.

[0322] The tolerance interval of the model refers to the maximum value of the difference between the reception time of the historical CSI feedback information and the current time so that the degree of performance degradation is within an acceptable range. The current time may be the time when the channel information corresponding to the CSI feedback information that failed to report is generated. Alternatively, the current time may also be the expected reception time of the CSI feedback information that failed to report. Exemplarily, the degree of performance degradation within an acceptable range may be that the degree of performance degradation is less than or equal to threshold #3. The maximum value of the difference corresponds to threshold #3. For example, when the difference between the reception time of the historical CSI feedback information and the current time is the maximum value, the degree of performance degradation caused by using the historical CSI feedback information to restore the channel information may be equal to threshold #3.

[0323] In other words, in the case of a failure in receiving the current CSI feedback information, the last received CSI feedback information is used to restore the channel information. If the difference between the reception time of the last received CSI feedback information and the current time is less than or equal to the tolerance interval, the degree of performance degradation is less than or equal to threshold #3, or in other words, within an acceptable range. If the difference between the reception time of the last received CSI feedback information and the current time is outside the tolerance interval, the degree of performance degradation is greater than threshold #3, or in other words, beyond the acceptable range.

[0324] If the CSI feedback information #2 corresponding to the reference signal #2 is reported successfully, the input of decoder #1 includes CSI feedback information #2, and the output of decoder #1 includes the channel information corresponding to the reference signal #2. If the CSI feedback information #3 corresponding to the reference signal #3 fails to be reported, the input of decoder #1 includes CSI feedback information #2, and the output of decoder #1 includes the channel information corresponding to the reference signal #3. Among them, the sending time of reference signal #2 is earlier than the sending time of reference signal #3. The tolerance interval of decoder #1 is the maximum value of the difference between the moment when decoder #1 generates the channel information corresponding to reference signal #3 and the receiving time of CSI feedback information #2. The degree of performance degradation of decoder #1 when the input includes CSI feedback information #2 when generating reference information #3 is less than or equal to threshold #3. The maximum value of the difference corresponds to threshold #3.

[0325] In the scheme of the embodiment of the present application, threshold #1 can be determined according to the ratio of the tolerance interval of decoder #1 and the transmission period of the reference signal, which is conducive to avoiding the network device from using historical CSI feedback information that exceeds the tolerance interval to restore channel information, resulting in serious performance deterioration. Specifically, when the number of packet losses reaches threshold #1, even if the packet loss is continuous, the difference between the reception time and the current time of the historical CSI feedback information used by the decoder is within the tolerance interval, triggering the terminal device to return the CSI feedback information of the failed report, and the network device side can realize the subsequent recovery of the channel information according to the returned CSI feedback information of the failed report, which is conducive to avoiding the network device from using historical CSI feedback information that exceeds the tolerance interval to restore channel information, resulting in serious performance deterioration.

[0326] Fig.10 Another communication method provided by an embodiment of the present application is shown. In method 1000, the number of failed CSI feedback information reporting can be used as a basis for determining model update. When the number of CSI feedback information reporting reaches threshold #1, the network device side and the terminal device side switch from the current CSI feedback mode to other CSI feedback modes.

[0327] like Fig.10 As shown, the method 1000 may include the following steps.

[0328] 1010. The terminal device receives indication information #4 (an example of the third indication information) sent by the network device. The indication information #4 indicates switching from the first CSI feedback mode to the second CSI feedback mode, and the number of failed CSI feedback information reporting reaches threshold #1.

[0329] 1020. The terminal device and the network device perform CSI feedback based on the second CSI feedback mode.

[0330] Exemplarily, in step 1010, when the number of failed CSI feedback information reporting reaches threshold #1, the network device may send indication information #4 to the terminal device.

[0331] The CSI feedback mode may be used to indicate a method for generating CSI feedback information and a method for recovering channel information, etc. The CSI feedback mode may also indicate other contents, such as a method for transmitting CSI feedback information, etc., which is not limited in the embodiments of the present application.

[0332] In a CSI feedback mode, the terminal device can perform channel measurement on the reference signal to obtain a channel measurement result, and process the channel measurement result based on the CSI feedback information generation method in the CSI feedback mode to generate CSI feedback information corresponding to the reference signal; after the network device receives the feedback information, it can process the CSI feedback information based on the channel information recovery method in the CSI feedback mode to obtain the channel information corresponding to the reference signal.

[0333] The first CSI feedback mode and the second CSI feedback mode are different feedback modes.

[0334] The terminal device and the network device perform CSI feedback based on the first CSI feedback mode. When the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct the terminal device to switch to the second CSI feedback mode. In this way, the network device and the terminal device can perform CSI feedback based on the second CSI feedback mode to avoid performance degradation caused by CSI feedback information packet loss in the first CSI feedback mode, which is conducive to the network device obtaining more accurate channel information, thereby ensuring feedback performance to ensure user experience.

[0335] The method 1000 may be applied to a CSI feedback scenario based on time domain correlation. The first CSI feedback mode is a CSI feedback mode based on time domain correlation.

[0336] For the specific description of the CSI feedback scenario based on time domain correlation, please refer to the previous text. To avoid repetition, some descriptions are appropriately omitted when describing method 1000.

[0337] In the first CSI feedback mode, the network device may determine channel information corresponding to the CSI feedback information according to the CSI feedback information and historical CSI feedback information relative to the CSI feedback information.

[0338] In other words, in the first CSI feedback mode, when the network device determines the channel information, it needs to be based on the currently received CSI feedback information and the CSI feedback information received at the past time.

[0339] In the first CSI feedback mode, the terminal device may determine CSI feedback information corresponding to the reference signal based on a channel measurement result of the reference signal and a channel measurement result of a historical reference signal relative to the reference signal.

[0340] In other words, in the first CSI feedback mode, when the terminal device generates CSI feedback information, it needs to be based on the current channel measurement results and the channel measurement results at historical moments.

[0341] Before step 1010 , method 1000 may further include steps 1001 to 1003 .

[0342] 1001. The network device sends a reference signal #4 (an example of a second reference signal) to the terminal device.

[0343] 1002. The terminal device generates CSI feedback information #4 (an example of second CSI feedback information) corresponding to the reference signal #4 in the first CSI feedback mode.

[0344] 1003. The terminal device sends CSI feedback information #4 to the network device.

[0345] In the first CSI feedback mode, CSI feedback information #4 is the output of encoder #1, or CSI feedback information #4 is based on the output of encoder #1. The input of encoder #1 includes the channel measurement result of reference signal #4. The output of encoder #1 is related to the channel measurement result of reference signal #4 and the historical input #2 of encoder #1 (an example of the second historical input of the second AI model). The historical input #2 of encoder #1 includes the channel measurement result of historical reference signal #2 (an example of the second historical reference signal). The sending time of historical reference signal #2 is earlier than the sending time of reference signal #4.

[0346] For the related description of reference signal #4 and CSI feedback information #4, please refer to the reference signal #1 and CSI feedback information #1 in the CSI feedback scenario based on time domain correlation in the previous method 700. To avoid repetition, they will not be repeated here.

[0347] Method 1000 may also include step 1004 .

[0348] 1004. The network device determines channel information corresponding to reference signal #4 according to CSI feedback information #4 in the first CSI feedback mode.

[0349] In the first CSI feedback mode, if CSI feedback information #4 is received successfully, the input of decoder #1 includes CSI feedback information #4 or is based on CSI feedback information #4. The output of decoder #1 includes channel information corresponding to reference signal #4. The output of decoder #1 is related to CSI feedback information #4 and historical input #2 of decoder #1. The historical input #2 of the decoder includes historical CSI feedback information #2, and the reception time of historical CSI feedback information #2 is earlier than the reception time of CSI feedback information #4. For the description of the channel information corresponding to reference signal #4, please refer to the channel information corresponding to reference signal #1 in the previous method 700. To avoid repetition, it will not be repeated here.

[0350] Step 1004 is an optional step. For example, if the network device does not successfully receive CSI feedback information #4, that is, CSI feedback information #4 fails to be reported, step 1004 is not performed. Decoder #1 can restore channel information through other CSI feedback information. For a specific description, refer to the method for restoring channel information corresponding to CSI feedback information #1 in method 700. To avoid repetition, it will not be described here.

[0351] Exemplarily, in the first CSI feedback mode, encoder #1 may generate CSI feedback information #4 based on a channel measurement result of reference signal #4 and state information #2 of encoder #1.

[0352] The state information #2 of encoder #1 may be determined by the channel measurement result of the historical reference signal #2.

[0353] Encoder #1 may also update state information #2 of encoder #1 based on the channel measurement result of reference signal #4.

[0354] Exemplarily, in the first CSI feedback mode, decoder #1 may determine channel information corresponding to reference signal #4 according to CSI feedback information #4 and state information #2 of decoder #1.

[0355] The state information #2 of decoder #1 may be determined based on the historical CSI feedback information #2.

[0356] Decoder #1 may also update status information #2 of decoder #1 based on CSI feedback information #4.

[0357] In the solution of the embodiment of the present application, the first CSI feedback mode can be a feedback mode based on time domain correlation, that is, the terminal device needs to refer to historical data when generating CSI feedback information, and the network device needs to refer to historical data when recovering channel information. When the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct the terminal device to switch to the second CSI feedback mode to avoid the accuracy of the channel information recovered by the network device from decreasing as the number of packet losses increases, which is conducive to avoiding the continuous decline of feedback performance.

[0358] Threshold #1 may be predefined, or preconfigured.

[0359] Alternatively, threshold #1 may be based on a ratio of a tolerance interval of decoder #1 and a transmission period of a reference signal.

[0360] For the description of threshold #1, please refer to the method 700 above, and will not be repeated here to avoid repetition.

[0361] The following is an exemplary description of indication information #4.

[0362] In a possible implementation, indication information #4 may be used to trigger switching of the feedback mode.

[0363] In other words, indication information #4 may indicate switching of the feedback mode.

[0364] Exemplarily, the second CSI feedback mode may be predefined.

[0365] In another possible implementation, indication information #4 may be used to determine the second feedback mode.

[0366] Exemplarily, the second CSI feedback mode may be determined by the network device, and the indication information #4 may indicate the second CSI feedback mode. The terminal device may switch from the first CSI feedback mode to the second CSI feedback mode according to the indication information #4.

[0367] For example, indication information #4 may indicate the identifier of the second CSI feedback mode. An identifier is set for each CSI feedback mode, and the identifier of each CSI feedback mode is used to distinguish each CSI feedback mode.

[0368] For another example, if the first CSI feedback mode and the second CSI feedback mode adopt different models, the indication information #4 may indicate the identifier of the model adopted by the second CSI feedback mode.

[0369] The second CSI feedback mode is exemplarily described below using Examples 1 to 3 as examples.

[0370] Example 1

[0371] The second CSI feedback mode and the first CSI feedback mode are both CSI feedback modes based on time domain correlation. The first CSI feedback mode and the second CSI feedback mode use different dual-end models based on time domain correlation.

[0372] Exemplarily, the dual-end models adopted by the first CSI feedback mode and the second CSI feedback mode may be models based on different structural parameters.

[0373] In this case, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current dual-end model based on time domain correlation is switched to other models based on time domain correlation.

[0374] The dual-end model based on time domain correlation adopted by the second CSI feedback mode may include encoder #2 and decoder #2. Encoder #2 and decoder #2 are matched. Encoder #2 and encoder #1 are different models. Correspondingly, decoder #1 and decoder #2 are different models. The specific description of encoder #2 and decoder #2 can refer to encoder #1 and decoder #1, and will not be repeated here to avoid repetition. For the terminal device side, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current encoder #1 is switched to encoder #2. For the network device side, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current decoder #1 is switched to decoder #2.

[0375] Further, the number of bits of the CSI feedback information generated in the second CSI feedback mode is smaller than the number of bits of the CSI feedback information generated in the first CSI feedback mode.

[0376] In this case, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current dual-end model based on time domain correlation is switched to the dual-end model based on time domain correlation with fewer bits of CSI feedback information.

[0377] Exemplarily, step 1020 may include the following steps.

[0378] S1-1, the network device sends a reference signal #5 (an example of a third reference signal) to the terminal device.

[0379] S1-2, the terminal device generates CSI feedback information #5 (an example of third CSI feedback information) corresponding to the reference signal #5 in the second CSI feedback mode.

[0380] S1-3, the terminal device sends CSI feedback information #5 to the network device.

[0381] In the second CSI feedback mode, CSI feedback information #5 is the output of encoder #2 (an example of the third AI model), or CSI feedback information #5 is based on the output of encoder #2. The input of encoder #2 includes the channel measurement result of reference signal #5. The output of encoder #2 is related to the channel measurement result of reference signal #5 and the historical input #3 of encoder #2 (an example of the third historical input of the third AI model). The historical input #3 of encoder #2 includes the channel measurement result of historical reference signal #3 (an example of the third historical reference signal). The sending time of historical reference signal #3 is earlier than the sending time of reference signal #5. The number of bits of CSI feedback information #5 is less than the number of bits of CSI feedback information #4. CSI feedback information #4 is the CSI feedback information generated in the first CSI feedback mode.

[0382] For the related description of reference signal #5 and CSI feedback information #5, please refer to the reference signal #1 and CSI feedback information #1 in the previous method 700. To avoid repetition, they will not be repeated here.

[0383] Step 1020 may also include step S1-4.

[0384] S1-4, the network device determines channel information corresponding to reference signal #5 according to CSI feedback information #5 in the second CSI feedback mode.

[0385] In the second CSI feedback mode, if CSI feedback information #5 is received successfully, the input of decoder #2 includes CSI feedback information #5 or is based on CSI feedback information #5. The output of decoder #2 includes channel information corresponding to reference signal #5. The output of decoder #2 is related to CSI feedback information #5 and historical input #3 of decoder #2. Historical input #3 of decoder #2 includes historical CSI feedback information #3, and the reception time of historical CSI feedback information #3 is earlier than the reception time of CSI feedback information #5. For the description of the channel information corresponding to reference signal #5, please refer to the channel information corresponding to reference signal #1 in the previous method 700. To avoid repetition, it will not be repeated here.

[0386] Step S1-4 is an optional step. For example, if the network device does not successfully receive CSI feedback information #5, step S1-4 is not performed. Decoder #2 can recover channel information through other CSI feedback information. For a specific description, refer to the method for recovering channel information corresponding to CSI feedback information #1 in method 700. To avoid repetition, it will not be described here.

[0387] Exemplarily, in the second CSI feedback mode, encoder #2 may generate CSI feedback information #5 based on the channel measurement result of reference signal #5 and state information #3 of encoder #2.

[0388] The state information #3 of encoder #2 may be determined by the channel measurement result of the historical reference signal #3.

[0389] Encoder #2 may also update state information #3 of encoder #2 based on the channel measurement result of reference signal #5.

[0390] Exemplarily, in the second CSI feedback mode, decoder #2 may determine channel information corresponding to reference signal #5 based on CSI feedback information #5 and state information #3 of decoder #2.

[0391] The state information #3 of decoder #2 may be determined based on the historical CSI feedback information #3.

[0392] Decoder #2 may also update status information #3 of decoder #2 based on CSI feedback information #5.

[0393] The specific feedback process in the second CSI feedback mode may refer to the relevant description of the first CSI feedback mode, and will not be described again here to avoid repetition.

[0394] The number of bits of the CSI feedback information generated by the model (encoder #2) adopted by the second CSI feedback mode is smaller than the number of bits of the CSI feedback information generated by the model (encoder #1) adopted by the first CSI feedback mode.

[0395] Table 1 shows a corresponding relationship between the number of bits of feedback information and the model.

[0396] Table 1

[0397] Number of bits of CSI feedback information AI model identification number (identity, ID) 60bit 1 120bit 2 180bit 3 240bit 4

[0398] Exemplarily, indication information #4 may indicate an identifier of a model using a smaller number of feedback bits.

[0399] For example, the ID of the AI ​​model (encoder #1) in the current terminal device is 4, and the identifier indicated by indication information #4 is 1. The terminal device switches from using the AI ​​model with ID 4 to using the AI ​​model with ID 1 (encoder #2).

[0400] It should be understood that the content shown in Table 1 is only an example and does not constitute a limitation on the solutions of the embodiments of the present application.

[0401] In the solution of the embodiment of the present application, the second CSI feedback mode still adopts the feedback method based on time domain correlation, so that the time domain correlation can continue to be used to improve the accuracy of channel information recovery to improve feedback performance. In addition, the feedback mode is switched to a model using a smaller number of feedback bits, that is, the number of bits of CSI feedback information is reduced, thereby reducing the requirements for the transmission conditions of the uplink feedback information transmission channel, that is, it is conducive to adapting the CSI feedback process based on time domain correlation to the current channel transmission conditions, which is conducive to reducing the packet loss of uplink feedback information, thereby helping to ensure user experience.

[0402] Optionally, method 1000 may further include: the network device sends indication information #3 to the terminal device, where the indication information #3 indicates to increase the uplink transmission power.

[0403] In the solution of the embodiment of the present application, the network device instructs to adjust the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information after switching the CSI feedback mode.

[0404] For the specific description of indication information #3, please refer to the relevant description in method 700. To avoid repetition, it will not be repeated here.

[0405] Exemplarily, the network device may also instruct the terminal device to increase uplink resources to transmit CSI feedback information generated in the second CSI feedback mode, that is, the number of uplink resources used to transmit CSI feedback information #5 is greater than the number of uplink resources used to transmit CSI feedback information #4.

[0406] In the solution of the embodiment of the present application, the network device instructs to increase uplink resources, thereby improving channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information after switching the CSI feedback mode.

[0407] Example 2

[0408] The first CSI feedback mode adopts a dual-end model based on time domain correlation. The second CSI feedback mode adopts a dual-end model based on non-time domain correlation.

[0409] In this case, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the dual-end model based on time domain correlation is switched to the dual-end model based on non-time domain correlation.

[0410] The dual-end model based on non-time domain correlation may include encoder #3 and decoder #3. Encoder #3 and decoder #3 are matched. For the terminal device side, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current encoder #1 is switched to encoder #3. For the network device side, the first CSI feedback mode is switched to the second CSI feedback mode, that is, the current decoder #1 is switched to decoder #3.

[0411] Models based on non-temporal correlation refer to models whose output results do not depend on historical inputs.

[0412] As mentioned above, for the dual-end model based on time domain correlation, the CSI feedback information is related to the current channel measurement result and the channel measurement result at the historical moment, and the recovered channel information is related to the currently received CSI feedback information and the CSI feedback information received at the past moment.

[0413] For the two-end model based on non-time domain correlation, the CSI feedback information is related to the current channel measurement result, and has nothing to do with the channel measurement result at the historical moment. The recovered channel information is related to the currently received CSI feedback information, and has nothing to do with the CSI feedback information received at the past moment.

[0414] Exemplarily, step 1020 may include the following steps.

[0415] S2-1, the network device sends a reference signal #6 (an example of a fourth reference signal) to the terminal device.

[0416] S2-2, the terminal device generates CSI feedback information #6 (an example of fourth CSI feedback information) corresponding to the reference signal #6 in the second CSI feedback mode.

[0417] S2-3, the terminal device sends CSI feedback information #6 to the network device.

[0418] In the second CSI feedback mode, the channel measurement result of the reference signal #6 is input to the encoder #3 (an example of the fourth AI model). The encoder #3 outputs the CSI feedback information #6. Alternatively, the output of the encoder #3 is processed to obtain the CSI feedback information #6. For example, the output of the encoder #3 is quantized to obtain the CSI feedback information #6.

[0419] In other words, CSI feedback information #6 is the output of encoder #3 based on the output of encoder #3. The input of encoder #3 includes the channel measurement result of reference signal #6. The output of encoder #3 is related to the channel measurement result of reference signal #6 and has nothing to do with the historical input of encoder #3. That is, CSI feedback information #6 has nothing to do with the channel measurement results of historical reference signals received in the past.

[0420] Step 1020 may also include step S2-4.

[0421] S2-4, the network device determines channel information corresponding to reference signal #6 according to CSI feedback information #6 in the second CSI feedback mode.

[0422] In the second CSI feedback mode, if the CSI feedback information #6 is received successfully, the CSI feedback information #6 is input to the decoder #3, or the CSI feedback information #6 is processed and then input to the decoder #3. For example, the CSI feedback information #6 may be obtained by quantizing the output of the encoder #3, and the CSI feedback information #6 is dequantized and then input to the decoder #3. The decoder #3 recovers the channel information corresponding to the reference signal #6.

[0423] In other words, the input of decoder #3 includes CSI feedback information #6 or is based on CSI feedback information #6. The output of decoder #3 includes channel information corresponding to reference signal #6. The output of decoder #3 is related to CSI feedback information #6 and has nothing to do with the historical input of decoder #3. That is, the channel information corresponding to reference signal #6 has nothing to do with the historical CSI feedback information received in the past.

[0424] In the solution of the embodiment of the present application, in the second CSI feedback mode, a model based on non-time domain correlation is used to realize the generation of CSI feedback information and the recovery of channel information. The determination of channel information is independent of historical data, which is conducive to ensuring feedback performance, thereby ensuring user experience. Specifically, in the second CSI feedback mode, even if packet loss occurs, it will not affect the accuracy of the subsequently recovered channel information, so as to avoid the accuracy of the channel information recovered by the network device from continuing to decrease as the number of packet losses increases, which is conducive to ensuring feedback performance, thereby ensuring user experience.

[0425] Optionally, method 1000 may further include: the network device sends indication information #3 to the terminal device, where the indication information #3 indicates to increase the uplink transmission power.

[0426] In the solution of the embodiment of the present application, the network device instructs to adjust the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information after switching the CSI feedback mode.

[0427] For the specific description of indication information #3, please refer to the relevant description in method 700. To avoid repetition, it will not be repeated here.

[0428] Exemplarily, the network device may also instruct the terminal device to increase uplink resources to transmit CSI feedback information generated in the second CSI feedback mode, that is, the number of uplink resources used to transmit CSI feedback information #6 is greater than the number of uplink resources used to transmit CSI feedback information #4.

[0429] In the solution of the embodiment of the present application, the network device instructs to increase uplink resources, thereby improving channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information after switching the CSI feedback mode.

[0430] Example 3

[0431] The first CSI feedback mode may be a CSI feedback mode based on time domain correlation.

[0432] The second CSI feedback mode may be a traditional CSI feedback mode, for example, a feedback mode based on a predefined codebook.

[0433] The predefined codebook can be understood as a non-AI model.

[0434] Exemplarily, the predefined codebook may be a codebook in the 3GPP protocol. For example, the codebook may be any of the following: a 3GPP protocol release (R) 15 type I codebook, a 3GPP protocol R15 type II codebook, a 3GPP protocol R16 enhanced type (enhanced type, etype) II codebook, a 3GPP protocol R17 codebook, or a 3GPP protocol R18 codebook. Exemplarily, step 1020 may include the following steps.

[0435] S3-1, the network device sends a reference signal #7 (an example of a fifth reference signal) to the terminal device.

[0436] S3-2, the terminal device generates CSI feedback information #7 (an example of fifth CSI feedback information) corresponding to the reference signal #7 in the second CSI feedback mode.

[0437] S3-3, the terminal device sends CSI feedback information #7 to the network device.

[0438] S3-4, the network device determines channel information corresponding to reference signal #7 according to CSI feedback information #7 in the second CSI feedback mode.

[0439] In the second CSI feedback mode, the terminal device may compress and / or quantize the channel measurement result of the reference signal #7 based on the codebook to generate CSI feedback information #7. The network device may process the CSI feedback information #7 based on the predefined codebook to restore the channel information corresponding to the reference signal #7.

[0440] In the solution of the embodiment of the present application, in the second CSI feedback mode, CSI feedback is performed based on a traditional feedback method, such as a predefined codebook feedback method, and the determination of channel information is independent of historical data, which is conducive to ensuring feedback performance, thereby ensuring user experience. Specifically, in the second CSI feedback mode, even if packet loss occurs, it will not affect the accuracy of the subsequently recovered channel information, so as to avoid the accuracy of the channel information recovered by the network device from continuing to decrease as the number of packet losses increases, which is conducive to ensuring feedback performance, thereby ensuring user experience.

[0441] Optionally, method 1000 may further include: the network device sends indication information #3 to the terminal device, where the indication information #3 indicates to increase the uplink transmission power.

[0442] For the specific description of indication information #3, please refer to the relevant description in method 700. To avoid repetition, it will not be repeated here.

[0443] Exemplarily, the network device may also instruct the terminal device to increase uplink resources to transmit CSI feedback information generated in the second CSI feedback mode, that is, the number of uplink resources used to transmit CSI feedback information #7 is greater than the number of uplink resources used to transmit CSI feedback information #4.

[0444] In the scheme of the embodiment of the present application, the network device instructs to adjust the uplink transmission power or increase the uplink resources, so as to improve the channel transmission conditions, which is conducive to ensuring the successful transmission of the CSI feedback information after switching the CSI feedback mode. When CSI feedback is performed based on the traditional CSI feedback method, the number of bits of its CSI feedback information is usually greater than the number of bits of the CSI feedback information generated by the feedback method based on AI feedback. In the scheme of the embodiment of the present application, improving the channel transmission conditions is conducive to transmitting feedback information with more bits, thereby avoiding excessive compression and / or quantization of the channel information, which is conducive to ensuring the quality of the channel information recovered by the network device under the traditional feedback method.

[0445] Fig.11 Another communication method provided by an embodiment of the present application is shown. Fig.11 The method 1100 shown can be applied to a CSI feedback process based on time domain correlation. The CSI feedback process can be implemented by a dual-end model based on time domain correlation. The dual-end model may include an encoder #1 and a decoder #1. For the relevant description of the feedback process based on time domain correlation, please refer to the previous text. To avoid repetition, some descriptions are appropriately omitted when describing method 1100. In method 1100, the number of failed CSI feedback information reports can be used as a basis for judging the model status update. When the number of CSI feedback information reports reaches threshold #1, the state of the entire model is reset.

[0446] like Fig.11 As shown, the method 1100 may include the following steps.

[0447] 1110. The terminal device receives indication information #5 (an example of the fourth indication information) sent by the network device, wherein the number of failed CSI feedback information reporting attempts reaches threshold #1.

[0448] Instruction information #5 indicates resetting the status information of encoder #1.

[0449] Specifically, the instruction information #5 indicates that the state information #4 (an example of the first state information) of the encoder #1 is reset to the state information #5 (an example of the second state information) of the encoder #1. The state information #5 of the encoder #1 is generated before the CSI feedback information reporting fails.

[0450] The state information #4 of encoder #1 is determined based on the historical input #4 of encoder #1 (an example of the fourth historical input of the second AI model). The historical input #4 of encoder #1 includes the channel measurement result of the historical reference signal #4 (an example of the fourth historical reference signal).

[0451] The state information #5 of encoder #1 is the initial state information of encoder #1. Alternatively, the state information #5 of encoder #1 is determined according to the historical input #5 of encoder #1 (an example of the fifth historical input of the second AI model). The historical input #5 of encoder #1 includes the channel measurement result of the historical reference signal #5 (an example of the fifth historical reference signal).

[0452] The sending time of historical reference signal #5 is earlier than the sending time of historical reference signal #4. That is, state information #5 is state information before state information #4.

[0453] Exemplarily, the historical reference information #5 is sent before the CSI feedback information reporting failure occurs.

[0454] Exemplarily, the state information #4 of encoder #1 can be understood as the current state information of encoder #1. The state information #5 of encoder #1 is the state information before the failure of reporting CSI feedback information occurs.

[0455] In other words, when the number of failed CSI feedback information reporting reaches threshold #1, the network device instructs to reset the state information of encoder #1, that is, to reset the state information of encoder #1 to the state information before the CSI reporting failure occurs. Correspondingly, decoder #1 is also reset to the state information before the CSI reporting failure occurs. The reset state information of decoder #1 matches the reset state information of encoder #1. Figure 6 For example, the current state information of encoder #1 (i.e., state information #4 of encoder #1) is e5, and the state information of decoder #1 is d5. For example, the state information of encoder #1 after reset (i.e., state information #5 of encoder #1) may be e1, and the state information of decoder #1 after reset may be d1. For another example, the state information of encoder #1 after reset may be e2, and the state information of decoder #1 after reset may be d2. For another example, the state information of encoder #1 after reset may be e0, and the state information of decoder #1 after reset may be d0.

[0456] 1120. The terminal device sends CSI feedback information #8 (an example of the sixth CSI feedback information) to the network device. The CSI feedback information #8 is related to the channel measurement result of the reference signal #8 (an example of the sixth reference signal) and the state information #5 of the encoder #1.

[0457] The network device sends reference signal #8 to the terminal device. The state information of encoder #1 has been reset to state information #5. The channel measurement result of reference signal #8 is input to encoder #1. CSI feedback information #8 is generated according to the output of encoder #1. The output of encoder #1 is related to the state information #5 of encoder #1 and the channel measurement result of reference signal #8.

[0458] The CSI feedback information #8 may be the output of the encoder #1. That is, the encoder #1 may output the CSI feedback information #8 according to the encoder #1 state information #5 and the channel measurement result of the reference signal #8.

[0459] Alternatively, the CSI feedback information #8 may be determined according to the output of the encoder #1. For example, quantization processing is performed according to the output of the encoder #1 to obtain the CSI feedback information #8.

[0460] Combine the following Fig.12 The method 1100 is described as an example.

[0461] like Fig.12 As shown, the terminal device inputs the channel measurement result H3 into the encoder. The encoder outputs CSI feedback information c3 according to the channel measurement result H3 and the state information e2, and updates the state information e2 to obtain the state information e3. The state information e3 can be used in the next CSI feedback process. When the CSI feedback information c3 fails to be reported, the network device inputs the CSI feedback information c2 received last time into the decoder. The decoder outputs CSI recovery information H'3 according to the CSI feedback information c2 and the state information d2, and obtains the state information d3.

[0462] Exemplarily, threshold #1 may be 1. That is, when a CSI reporting failure occurs, the network device instructs to reset the state information of the model. The current state information of the encoder (i.e., an example of state information #4 of encoder #1) is e3. The network device sends indication information #5, indicating that the state information of the encoder is reset to e0 (i.e., an example of state information #5 of encoder #1). Correspondingly, the state information of the decoder is also reset to d0.

[0463] The network device sends a reference signal R4 (i.e., an example of reference signal #8) to the terminal device. The terminal device measures the reference signal R4 to obtain a channel measurement result H4. The channel measurement result H4 is input into the encoder. The encoder outputs CSI feedback information c4 (i.e., an example of CSI feedback information #8) based on the channel measurement result H4 and the state information e0, and updates the state information e0 to obtain the state information e1'. The state information e1' can be used in the next CSI feedback process. The terminal device sends the CSI feedback information c4 to the network device. The network device inputs the CSI feedback information c4 into the decoder. The decoder outputs CSI recovery information H'4 based on the CSI feedback information c4 and the state information d0, and updates the state information d0 to obtain the state information d1'. The state information d1' can be used in the next CSI feedback process.

[0464] Threshold #1 may be predefined, or preconfigured.

[0465] Alternatively, threshold #1 may be based on a ratio of a tolerance interval of decoder #1 and a transmission period of a reference signal.

[0466] For the description of threshold #1, please refer to the method 700 above, and will not be repeated here to avoid repetition.

[0467] In the scheme of the embodiment of the present application, when the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct to reset the status information of the model used to generate the CSI feedback information, reset the status information of the model to before the CSI feedback information packet loss occurs, and restore the consistency of the status information of the model on the network device and the terminal device, thereby facilitating improving the accuracy of the channel information recovered by the network device, thereby improving the feedback performance, and ensuring the user experience.

[0468] Optionally, method 1000 may further include: the network device sends indication information #3 to the terminal device, where the indication information #3 indicates to increase the uplink transmission power.

[0469] For the specific description of indication information #3, please refer to the relevant description in method 700. To avoid repetition, it will not be repeated here.

[0470] Exemplarily, the network device may also instruct the terminal device to increase uplink resources to transmit CSI feedback information generated in the second CSI feedback mode, that is, the number of uplink resources used to transmit CSI feedback information #8 is greater than the number of uplink resources used to transmit CSI feedback information before reset.

[0471] In the solution of the embodiment of the present application, the network device instructs to adjust the uplink transmission power or increase the uplink resources, so as to improve the channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information.

[0472] Fig.13 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.13 The method 1300 shown can be applied to a CSI feedback process based on time domain correlation. The CSI feedback process can be implemented by a dual-end model based on time domain correlation. The dual-end model may include an encoder #1 and a decoder #1. For the relevant description of the feedback process based on time domain correlation, please refer to the previous text. To avoid repetition, some descriptions are appropriately omitted when describing the method 1300.

[0473] like Fig.13 As shown, method 1300 includes the following steps.

[0474] 1310. The terminal device sends CSI feedback information #1 to the network device.

[0475] The CSI feedback information #1 is the output of encoder #1 or based on the output of encoder #1. The output of encoder #1 is related to the channel measurement result of reference signal #1 and the historical input #1 of encoder #1. The historical input #1 of encoder #1 includes the channel measurement result of historical reference signal #1. The reception time of historical reference signal #1 is earlier than the reception time of reference signal #1.

[0476] 1320, the network device sends indication information #3 to the terminal device. Indication information #3 indicates to increase the uplink transmission power. The number of times the CSI feedback information reporting fails reaches threshold #1.

[0477] The network device counts the number of times cnt when CSI feedback information packet loss occurs. When the number of times cnt when CSI feedback information packet loss reaches a threshold #1, the network device instructs to increase the uplink transmission power.

[0478] For the description of threshold #1, please refer to the previous text and will not be repeated here.

[0479] In the scheme of the embodiment of the present application, the network device monitors the packet loss situation. When the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct the terminal device to increase the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring the successful transmission of the CSI feedback information, so as to avoid the subsequent CSI feedback information from continuing to lose packets and causing the feedback performance to continue to decline.

[0480] Fig.14 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.14The method 1400 shown can be applied to a CSI feedback process based on time domain correlation. The CSI feedback process can be implemented by a dual-end model based on time domain correlation. The dual-end model may include an encoder #1 and a decoder #1. For the relevant description of the feedback process based on time domain correlation, please refer to the previous text. To avoid repetition, some descriptions are appropriately omitted when describing the method 1400.

[0481] like Fig.14 As shown, method 1400 includes the following steps.

[0482] 1410. The terminal device sends CSI feedback information #1 to the network device on uplink resource #1.

[0483] The method 1400 may further include: the network device sends uplink resource configuration information #1 to the terminal device, where the uplink resource configuration information #1 indicates uplink resource #1 used to transmit the CSI feedback information #1.

[0484] The CSI feedback information #1 is the output of encoder #1 or based on the output of encoder #1. The output of encoder #1 is related to the channel measurement result of reference signal #1 and the historical input #1 of encoder #1. The historical input #1 of encoder #1 includes the channel measurement result of historical reference signal #1. The reception time of historical reference signal #1 is earlier than the reception time of reference signal #1.

[0485] The relevant description of step 1410 can refer to method 700, and will not be repeated here to avoid repetition.

[0486] 1420, the network device sends uplink resource configuration information #3 to the terminal device, where the uplink resource configuration information #3 indicates uplink resource #3 used to transmit CSI feedback information #9. The number of uplink resource #3 is greater than the number of uplink resource #1. The number of failed CSI feedback information reports reaches threshold #1.

[0487] The network device counts the number of times cnt when the CSI feedback information packet is lost. When the number of times cnt when the CSI feedback information packet is lost reaches a threshold #1, the network device instructs to increase uplink resources to send the CSI feedback information.

[0488] For example, the network device may give priority to increasing the CCE resources of the terminal device.

[0489] For the description of threshold #1, please refer to the previous text and will not be repeated here.

[0490] Exemplarily, CSI feedback information #9 may be one of the one or more CSI feedback information in method 700. In this case, uplink resource configuration information #3 is the uplink resource configuration information #2 mentioned above.

[0491] Exemplarily, CSI feedback information #9 may be CSI feedback information reported after switching to the second CSI feedback mode in method 1000, for example, CSI feedback information #5, CSI feedback information #6 or CSI feedback information #7.

[0492] Exemplarily, CSI feedback information #9 may be CSI feedback information reported after the model is reset in method 1100, for example, CSI feedback information #8.

[0493] Exemplarily, CSI feedback information #9 may also be CSI feedback information generated when CSI feedback continues to be performed in the original CSI feedback mode.

[0494] 1430. The terminal device sends CSI feedback information #9 to the network device on uplink resource #3.

[0495] In the scheme of the embodiment of the present application, the network device monitors the packet loss situation. When the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can adjust the configuration of time-frequency domain resources and increase uplink resources, thereby improving channel transmission conditions, which is conducive to ensuring the successful transmission of CSI feedback information, so as to avoid subsequent CSI feedback information from continuing to lose packets and causing feedback performance to continue to decline.

[0496] Fig.15 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.15 The method 1500 shown can be viewed as Figure 7 An example of method 700 is shown. For related descriptions, reference may be made to method 700. To avoid repetition, some contents are appropriately omitted when describing method 1500. Method 1500 may be applied to a CSI feedback scenario based on time correlation. Specifically, in method 1500, CSI feedback based on time correlation is implemented by a dual-end model based on time correlation. The dual-end model includes encoder #1 and decoder #1.

[0497] like Fig.15 As shown, method 1500 includes the following steps.

[0498] 1501. The network device sends CSI-RS#15-1 to the terminal device.

[0499] In method 1500, the reference signal is CSI-RS for exemplary description, which does not limit the solution of the embodiment of the present application. The reference signal can also be other signals. For specific description, please refer to method 700.

[0500] 1502, the terminal device measures CSI-RS#15-1.

[0501] The terminal device performs channel measurement on CSI-RS#15-1 to obtain a channel measurement result of CSI-RS#15-1.

[0502] 1503. Encoder #1 generates CSI feedback information #15-1.

[0503] Encoder #1 generates CSI feedback information #15-1 according to the channel measurement result of CSI-RS #15-1 and the current state information of encoder #1. The specific generation method of CSI feedback information can refer to CSI feedback information #1 in the above method 700, which will not be repeated here.

[0504] 1504. The terminal device sends CSI feedback information #15-1 to the network device.

[0505] 1505. Decoder #1 generates channel information corresponding to CSI-RS #15-1.

[0506] Decoder #1 generates channel information corresponding to CSI-RS #15-1 according to CSI feedback information #15-1 and current state information of decoder #1. The specific way of recovering the channel information can refer to the method 700 above, which will not be described here.

[0507] 1506. The network device sends CSI-RS#15-2 to the terminal device.

[0508] 1507, the terminal device measures CSI-RS#15-2.

[0509] The terminal device performs channel measurement on CSI-RS#15-2 to obtain a channel measurement result of CSI-RS#15-2.

[0510] 1508. Encoder #1 generates CSI feedback information #15-2.

[0511] Encoder #1 generates CSI feedback information #15-2 according to the channel measurement result of CSI-RS #15-2 and the current state information of encoder #1. The specific method of generating CSI feedback information can refer to the method 700 above, which will not be repeated here.

[0512] 1509, the terminal device sends CSI feedback information #15-2 to the network device. Fig.15 As shown, CSI feedback information #15-2 is lost.

[0513] For example, the uplink channel condition of the terminal device deteriorates and the CSI feedback information reporting fails.

[0514] 1510. The network device counts the number of times the feedback information of the terminal device is lost after access.

[0515] The network device and the terminal device continue to perform CSI feedback. The feedback process can refer to the above steps 1501 to 1509.

[0516] 1511. The terminal device sends feedback information #15-n to the network device, where n is a positive integer.

[0517] like Fig.15 As shown, feedback information #15-n is lost.

[0518] 1512. When the number of packet losses of the CSI feedback information is equal to N, trigger the sending of indication information #3 to the terminal device, instructing to increase the uplink transmission power of the terminal device.

[0519] The method for determining N may refer to method 700 .

[0520] 1513. Send indication information #1 to the terminal device, indicating to resend part or all of the N CSI feedback information that failed to be reported.

[0521] For example, indication information #1 indicates that the terminal device sends M pieces of feedback information among the N pieces of feedback information. M is a positive integer less than or equal to N.

[0522] It should be understood that the indication information #1 here is only an example, and the indication information #1 can also indicate other content. For a specific description, please refer to method 700.

[0523] 1514. The terminal device sends M feedback information to the network device.

[0524] The M CSI feedback information are one or more CSI feedback information in method 700 .

[0525] For example, the M pieces of feedback information may be the M pieces of feedback information that were recently lost. For another example, the M pieces of feedback information may be M pieces of feedback information that are randomly selected.

[0526] In the solution of the embodiment of the present application, a retransmission mechanism of CSI feedback information is introduced, that is, the network device can instruct the terminal device to transmit back the CSI feedback information that failed to be reported before. In this way, the decoder can update the decoder state information according to the transmitted CSI feedback information that failed to be reported, so as to better match the encoder state information, thereby improving the accuracy of the recovered channel information, thereby ensuring the feedback performance. Fig. 9 As shown, the method of retransmitting the CSI feedback information of the lost packet can improve the SGCS performance, that is, it is beneficial to ensure the feedback performance.

[0527] In addition, the network device may instruct the terminal device to increase the uplink transmission power, thereby improving the channel transmission conditions, which is conducive to ensuring that the terminal device can successfully transmit back the M CSI feedback information.

[0528] Fig.16 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.16 The method 1600 shown can be viewed as Figure 7 An example of method 700 is shown. For related descriptions, reference may be made to method 700. To avoid repetition, some contents are appropriately omitted when describing method 1600. Method 1600 may be applied to a CSI feedback scenario based on time correlation. Specifically, in method 1600, CSI feedback based on time correlation is implemented by a dual-end model based on time correlation. The dual-end model includes encoder #1 and decoder #1.

[0529] The main difference between method 1600 and method 1500 is that in method 1500, the network device instructs to increase the uplink transmission power of the terminal device, while in method 1600, the network device instructs to increase the uplink resources used to retransmit CSI feedback information. In method 1600, similarities with method 1500 can refer to the description of method 1500. To avoid repetition, some contents are appropriately omitted when describing method 1600.

[0530] like Fig.16 As shown, method 1600 includes the following steps.

[0531] 1601. The network device sends CSI-RS#16-1 to the terminal device.

[0532] 1602, the terminal device measures CSI-RS#16-1.

[0533] 1603. Encoder #1 generates CSI feedback information #16-1.

[0534] 1604. The terminal device sends CSI feedback information #16-1 to the network device.

[0535] 1605. Decoder #1 generates channel information corresponding to CSI-RS #16-1.

[0536] 1606. The network device sends CSI-RS#16-2 to the terminal device.

[0537] 1607, the terminal device measures CSI-RS#16-2.

[0538] 1608. Encoder #1 generates CSI feedback information #16-2.

[0539] 1609. The terminal device sends CSI feedback information #16-2 to the network device.

[0540] like Fig.16As shown, CSI feedback information #16-2 is lost.

[0541] 1610. The network device counts the number of times the feedback information of the terminal device is lost after access.

[0542] The network device and the terminal device continue to perform CSI feedback. The feedback process can refer to the above steps 1601 to 1609.

[0543] 1611. The terminal device sends feedback information #16-n to the network device.

[0544] like Fig.16 As shown, feedback information #16-n is lost.

[0545] 1612. When the number of packet losses of the CSI feedback information is equal to N, trigger the sending of uplink resource configuration information #2 to the terminal device, instructing to increase the uplink resources.

[0546] The method for determining N may refer to method 700 .

[0547] 1613, sending indication information #1 to the terminal device, indicating retransmission of part or all of the N CSI feedback information that failed to be reported.

[0548] 1614. The terminal device sends M feedback information to the network device.

[0549] In the solution of the embodiment of the present application, a retransmission mechanism of CSI feedback information is introduced, that is, the network device can instruct the terminal device to transmit back the CSI feedback information that failed to be reported before. In this way, the decoder can update the decoder state information according to the transmitted CSI feedback information that failed to be reported, so as to better match the encoder state information, thereby improving the accuracy of the recovered channel information, thereby ensuring the feedback performance.

[0550] In addition, the network device may instruct the terminal device to increase uplink resources used to transmit CSI feedback information, thereby improving channel transmission conditions, which is conducive to ensuring that the terminal device can successfully transmit back the M CSI feedback information.

[0551] Fig.17 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.17 The method 1700 shown can be viewed as Fig.10 An example of method 1000 is shown. For related descriptions, reference may be made to method 1000. To avoid repetition, some contents are appropriately omitted when describing method 1700. Method 1700 can be applied to a CSI feedback scenario based on time correlation. In method 1700, for similarities with method 1500, reference may be made to the description of method 1500. To avoid repetition, some contents are appropriately omitted when describing method 1700.

[0552] like Fig.17 As shown, method 1700 includes the following steps.

[0553] 1701. The network device sends CSI-RS#17-1 to the terminal device.

[0554] 1702, the terminal device measures CSI-RS#17-1.

[0555] 1703. Encoder #1 generates CSI feedback information #17-1.

[0556] Encoder #1 is the encoder used in the first CSI feedback mode.

[0557] 1704. The terminal device sends CSI feedback information #17-1 to the network device.

[0558] 1705. Decoder #1 generates channel information corresponding to CSI-RS #17-1.

[0559] Decoder #1 is a decoder used in the first CSI feedback mode.

[0560] 1706. The network device sends CSI-RS#17-2 to the terminal device.

[0561] 1707, the terminal device measures CSI-RS#17-2.

[0562] 1708. Encoder #1 generates CSI feedback information #17-2.

[0563] 1709. The terminal device sends CSI feedback information #17-2 to the network device.

[0564] like Fig.17 As shown, CSI feedback information #17-2 is lost.

[0565] 1710. The network device counts the number of times the feedback information of the terminal device is lost after access.

[0566] The network device and the terminal device continue to perform CSI feedback. The feedback process can refer to the above steps 1701 to 1709.

[0567] 1711. The terminal device sends feedback information #17-n to the network device.

[0568] like Fig.17 As shown, feedback information #17-n is lost.

[0569] 1712. When the number of packet losses of the CSI feedback information is equal to N, trigger sending indication information #4 to the terminal device, indicating switching from the first CSI feedback mode to the second CSI feedback mode.

[0570] The method for determining N may refer to method 700 .

[0571] Exemplarily, switching from the first CSI feedback mode to the second CSI feedback mode may include any of the following:

[0572] Switch from encoder #1 to encoder #2, and switch from decoder #1 to decoder #2. Encoder #2 and decoder #2 belong to a two-end model based on time domain correlation. The number of bits of CSI feedback information generated by encoder #2 is less than the number of bits of CSI feedback information generated by encoder #1.

[0573] Switching from encoder #1 to encoder #3, and switching from decoder #1 to decoder #3, encoder #3 and decoder #3 belong to a two-end model based on non-time domain correlation; or

[0574] Switch from the CSI feedback mode based on time domain correlation to the non-AI CSI feedback mode.

[0575] The network device and the terminal device perform CSI feedback based on the second CSI feedback mode.

[0576] Taking the second CSI feedback mode as a non-AI CSI feedback mode as an example, the second CSI feedback mode can be a CSI feedback mode based on a predefined codebook. The network device sends CSI-RS#17-(n+1) to the terminal device. The terminal device processes CSI-RS#17-(n+1) based on the predefined codebook to obtain CSI feedback information #17-(n+1), and sends CSI feedback information #17-(n+1) to the network device. The network device processes CSI feedback information #17-(n+1) based on the predefined codebook to obtain channel information corresponding to CSI-RS#17-(n+1).

[0577] In the scheme of the embodiment of the present application, the first CSI feedback mode is a feedback mode based on time domain correlation. When the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct the terminal device to switch to the second CSI feedback mode to avoid the accuracy of the channel information recovered by the network device from decreasing as the number of packet losses increases, which is beneficial to avoid a continuous decline in feedback performance.

[0578] Fig.18 A schematic diagram of another communication method provided in an embodiment of the present application is shown. Fig.18 The method 1800 shown can be viewed as Fig.10An example of method 1000 is shown. For related descriptions, reference may be made to method 1000. To avoid repetition, some contents are appropriately omitted when describing method 1800. Method 1800 may be applied to a CSI feedback scenario based on time correlation.

[0579] The main difference between method 1800 and method 1700 is that in method 1700, the network device indicates to add switching of the CSI feedback mode, while in method 1800, the network device indicates to reset the state information of the model.

[0580] In method 1800 , similarities with method 1700 can refer to the description of method 1700 . To avoid repetition, some contents are appropriately omitted when describing method 1800 .

[0581] like Fig.18 As shown, method 1800 includes the following steps.

[0582] 1801. The network device sends CSI-RS#18-1 to the terminal device.

[0583] 1802, the terminal device measures CSI-RS#18-1.

[0584] 1803. Encoder #1 generates CSI feedback information #18-1.

[0585] 1804. The terminal device sends CSI feedback information #18-1 to the network device.

[0586] 1805. Decoder #1 generates channel information corresponding to CSI-RS #18-1.

[0587] 1806. The network device sends CSI-RS#18-2 to the terminal device.

[0588] 1807, the terminal device measures CSI-RS#18-2.

[0589] 1808. Encoder #1 generates CSI feedback information #18-2.

[0590] 1809. The terminal device sends CSI feedback information #18-2 to the network device.

[0591] like Fig.18 As shown, CSI feedback information #18-2 is lost.

[0592] 1810. The network device counts the number of times the feedback information of the terminal device is lost after access.

[0593] The network device and the terminal device continue to perform CSI feedback. The feedback process can refer to the above steps 1801 to 1809.

[0594] 1811. The terminal device sends feedback information #18-n to the network device.

[0595] like Fig.18 As shown, feedback information #18-n is lost.

[0596] 1812. When the number of packet losses of the CSI feedback information is equal to N, trigger the sending of indication information #5 to the terminal device, indicating that the status information of encoder #1 is to be reset.

[0597] The method for determining N may refer to method 700 .

[0598] For example, the state information of encoder #1 is reset to the initial state of encoder #1.

[0599] The network device and the terminal device perform CSI feedback based on the reset model.

[0600] In the solution of the embodiment of the present application, in the feedback scenario based on time domain correlation, when the number of CSI feedback information that fails to be reported reaches a certain threshold, the network device can instruct to reset the state information of the model to avoid the accuracy of the channel information recovered by the network device decreasing with the increase of the number of packet losses, which is conducive to avoiding the continuous decline of feedback performance. Fig. 9 As shown, resetting the model can improve the performance of SGCS, which is beneficial to ensuring the performance of feedback.

[0601] It can be understood that in some of the above embodiments, the information names involved are only examples and do not limit the protection scope of the embodiments of the present application.

[0602] It can also be understood that the formulas involved in the various embodiments of the present application are only exemplary descriptions, and do not limit the protection scope of the embodiments of the present application. In the process of calculating the above-mentioned various parameters involved, the calculation can also be performed according to the above formula, or based on the deformation of the above formula, or according to other methods to satisfy the result of the formula calculation.

[0603] It can also be understood that some optional features in the embodiments of the present application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0604] It can also be understood that the solutions in the various embodiments of the present application can be used in reasonable combination, and the explanations or descriptions of the various terms appearing in the embodiments can be mutually referenced or explained in the various embodiments, without limitation.

[0605] It can also be understood that the sizes of the various digital serial numbers in the embodiments of the present application do not mean the order of execution, but are only distinguished for the convenience of description and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0606] It can also be understood that in the above-mentioned various method embodiments, the methods and operations implemented by the device can also be implemented by components (such as chips or circuits) that can be implemented by the device.

[0607] Corresponding to the methods given in the above-mentioned method embodiments, the embodiments of the present application also provide corresponding devices, which include modules for executing the corresponding methods in the above-mentioned method embodiments. The module can be software, hardware, or a combination of software and hardware. It can be understood that the technical features described in the above-mentioned method embodiments are also applicable to the following device embodiments.

[0608] Fig.19 1 is a schematic diagram of a communication device 1900 provided in an embodiment of the present application. The device 1900 includes a transceiver unit 1910 and a processing unit 1920. The transceiver unit 1910 can be used to implement corresponding communication functions. The transceiver unit 1910 can also be called a communication interface or a communication unit, etc. The processing unit 1920 can be used to implement corresponding processing functions, such as configuring resources. The processing unit 1920 can also be called a processor, etc.

[0609] Optionally, the device 1900 also includes a storage unit, which can be used to store instructions and / or data, and the processing unit 1920 can read the instructions and / or data in the storage unit so that the device implements the actions of the device or network element in the aforementioned method embodiments.

[0610] The device 1900 can be a terminal device, or a communication device that is applied to a terminal device or used in combination with a terminal device and can implement a communication method executed on the terminal device side; or, the device 1900 can be a network device, or a communication device that is applied to a network device or used in combination with a network device and can implement a communication method executed on the network device side.

[0611] When the device 1900 is applied to a terminal device, the device 1900 can implement the steps or processes performed by the terminal device in the above method embodiment. The transceiver unit 1910 can be used to perform the operations related to the transceiver of the terminal device in the above method embodiment, and the processing unit 1920 can be used to perform the operations related to the processing of the terminal device in the above method embodiment.

[0612] When the device 1900 is applied to a network device, the device 1900 can implement the steps or processes executed by the network device in the above method embodiment, wherein the transceiver unit 1910 can be used to execute the transceiver-related operations of the network device in the above method embodiment, and the processing unit 1920 can be used to execute the processing-related operations of the network device in the above method embodiment.

[0613] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0614] It should also be understood that the device 1900 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merged logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art can understand that the device 1900 can be specifically a terminal device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the terminal device in the above-mentioned method embodiments; or, the device 1900 can be specifically a network device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the network device in the above-mentioned method embodiments. To avoid repetition, it will not be repeated here.

[0615] The apparatus 1900 of each of the above-mentioned schemes has the function of implementing the corresponding steps performed by the device (such as a terminal device, or a network device) in the above-mentioned method. The function can be implemented by hardware, or by hardware executing the corresponding software implementation. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor, respectively performing the sending and receiving operations and related processing operations in each method embodiment.

[0616] In addition, the above-mentioned transceiver unit 1910 can also be a transceiver circuit (for example, can include a receiving circuit and a sending circuit), and the processing unit can be a processing circuit.

[0617] It should be pointed out that Fig.19The device in the embodiment may be a network element or device in the foregoing embodiment, or may be a chip or a chip system, such as a system on chip (SoC). The transceiver unit may be an input / output circuit or a communication interface; the processing unit may be a processor or a microprocessor or an integrated circuit integrated on the chip. This is not limited here.

[0618] Fig. 20 2 is a schematic diagram of another communication device 2000 provided in an embodiment of the present application. The device 2000 includes a processor 2010, and the processor 2010 is used to execute a computer program or instruction stored in a memory 2020, or read data / signaling stored in the memory 2020 to execute the method in each method embodiment above. Optionally, there are one or more processors 2010.

[0619] Alternatively, if Fig. 20 As shown, the device 2000 also includes a memory 2020, which is used to store computer programs or instructions and / or data. The memory 2020 can be integrated with the processor 2010, or can also be separately set. Optionally, the memory 2020 is one or more.

[0620] Alternatively, if Fig. 20 As shown, the device 2000 further includes a transceiver 2030, which is used to receive and / or send signals. For example, the processor 2010 is used to control the transceiver 2030 to receive and / or send signals.

[0621] As a solution, the apparatus 2000 can be applied to a terminal device, and the specific apparatus 2000 can be a terminal device, or a device that can support a terminal device and implement the functions of the terminal device in any of the above examples. The apparatus 2000 is used to implement the operations performed by the terminal device in the above various method embodiments.

[0622] For example, the processor 2010 is used to execute the computer program or instructions stored in the memory 2020 to implement the relevant operations of the terminal device in the above various method embodiments.

[0623] As another solution, the device 2000 can be applied to a network device, and the specific device 2000 can be a network device, or a device that can support a network device and implement the functions of the network device in any of the above examples. The device 2000 is used to implement the operations performed by the network device in the above various method embodiments.

[0624] For example, the processor 2010 is used to execute the computer program or instructions stored in the memory 2020 to implement the relevant operations of the network device in the above various method embodiments.

[0625] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), ASICs, field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0626] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0627] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0628] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0629] An embodiment of the present application also provides a computer-readable storage medium on which computer instructions for implementing the methods executed by the communication device in the above-mentioned method embodiments are stored.

[0630] For example, when the computer program is executed by a computer, the computer can implement the method executed by the terminal device in each embodiment of the above method.

[0631] For another example, when the computer program is executed by a computer, the computer can implement the method performed by the network device in each embodiment of the above method.

[0632] An embodiment of the present application also provides a computer program product, comprising instructions, which, when executed by a computer, implement the methods performed by a device (such as a terminal device or a network device) in the above-mentioned method embodiments.

[0633] The embodiment of the present application further provides a communication system, including the aforementioned terminal device and network device. The terminal device and the network device can implement the communication method shown in any of the aforementioned examples.

[0634] Optionally, the system also includes a device for communicating with the above-mentioned terminal device and / or network device.

[0635] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0636] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0637] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part 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 process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. For example, the computer can be a personal computer, a server, or a network device, etc. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)). For example, the aforementioned available medium includes, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0638] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A communication method, characterized in that: include: Sending first channel state information CSI feedback information to the network device; Receiving first indication information from the network device; One or more CSI feedback information are sent to the network device according to the first indication information, where the one or more CSI feedback information include the first CSI feedback information.

2. The method according to claim 1, characterized in that Before sending one or more CSI feedback information to the network device according to the first indication information, the method further includes: Second indication information is received from the network device, where the second indication information indicates to increase uplink transmission power.

3. The method according to claim 1 or 2, characterized in that: The sending first channel state information CSI feedback information to the network device includes: The step of sending the first CSI feedback information to the network device on the first uplink resource indicated by the first uplink resource configuration information; and the step of receiving the first indication information from the network device comprises: Receive first indication information and second uplink resource configuration information from the network device, wherein the second uplink resource configuration information indicates a second uplink resource used to transmit the one or more CSI feedback information, and the number of uplink resources in the second uplink resource used to transmit the first CSI feedback information is greater than the number of resources of the first uplink resource.

4. The method according to any one of claims 1 to 3, characterized in that The first indication information is used to determine the one or more CSI feedback information.

5. The method according to claim 4, characterized in that The first indication information indicates at least one of the following: The identifiers of the one or more CSI feedback information, the identifiers of the reference signals corresponding to the one or more CSI feedback information, the first time period, the identifiers of K CSI feedback information including the one or more CSI feedback information, or the identifiers of the reference signals corresponding to the K CSI feedback information, wherein K is a positive integer, the first time period is before the sending time of the first indication information, the sending time of the one or more CSI feedback information is within the first time period, or the sending time of the K CSI feedback information is within the first time period.

6. The method according to any one of claims 1 to 5, characterized in that The number of failed CSI feedback information reporting attempts reaches a first threshold.

7. The method according to claim 6, characterized in that The first threshold is predefined, preconfigured, or the first threshold is the ratio of the tolerance interval of the first artificial intelligence AI model to the sending period of the reference signal, and the tolerance interval is predefined or preconfigured.

8. The method according to any one of claims 1 to 7, characterized in that The first CSI feedback information is the output of the second AI model or is based on the output of the second AI model, the input of the second AI model includes a channel measurement result of a first reference signal, the output of the second AI model is related to the channel measurement result of the first reference signal and a first historical input of the second AI model, the first historical input of the second AI model includes the channel measurement result of the first historical reference signal, the sending time of the first historical reference signal is earlier than the sending time of the first reference signal, and when the first CSI feedback information is successfully reported, the channel information corresponding to the first reference signal is the output of the first AI model, the input of the first AI model includes the first CSI feedback information or is based on the first CSI feedback information, the output of the first AI model is related to the first CSI feedback information and the first historical input of the first AI model, the first historical input of the first AI model includes the first historical CSI feedback information or is based on the first historical CSI feedback information, and the receiving time of the first historical CSI feedback information is earlier than the receiving time of the first CSI feedback information.

9. A method of communication, characterized in that: include: Sending first uplink resource configuration information to a terminal device, where the first uplink resource configuration information indicates a first uplink resource used to transmit first channel state information CSI feedback information; Sending first indication information and second uplink resource configuration information to the terminal device, where the first indication information is used to instruct the terminal device to send one or more CSI feedback information, and the second uplink resource configuration information indicates a second uplink resource used to transmit the one or more CSI feedback information, where the one or more CSI feedback information includes the first CSI feedback information; Receive the one or more CSI feedback information from the terminal device.

10. The method according to claim 9, characterized in that Before receiving the one or more CSI feedback information from the terminal device, the method further includes: Send second indication information to the terminal device, wherein the second indication information indicates to increase the uplink transmission power.

11. The method according to claim 9 or 10, characterized in that: The number of uplink resources in the second uplink resources used for transmitting the first CSI feedback information is greater than the number of resources in the first uplink resources.

12. The method according to any one of claims 9 to 11, characterized in that The number of failed CSI feedback information reporting attempts reaches a first threshold.

13. The method according to claim 12, characterized in that The first threshold is predefined, preconfigured, or the first threshold is a ratio of a tolerance interval of the first AI model to a transmission period of a reference signal, and the tolerance interval is predefined or preconfigured.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium comprises instructions, which, when executed by a processor, enable the method of any one of claims 1 to 8 or 9 to 13 to be implemented.

15. A communication device, characterized in that: The communication device includes a processor and a storage medium, wherein the storage medium stores instructions. When the instructions are executed by the processor, the communication device performs the method according to any one of claims 1 to 8 or 9 to 13.

Images