Communication method and communication apparatus

Abstract

Provided are a communication method and a communication apparatus. In the method, a terminal side and a network side respectively use AI models to compress and reconstruct a CSI report. When the terminal side sends the CSI report for the first time, due to insufficient uplink resources, the terminal side can actively discard part of information of the CSI report and send the remaining part, and then, the report can be sent again, so as to send the discarded part of information to the network side. Therefore, the network side can obtain a complete CSI report, and update state information on the basis of the complete CSI report. The terminal side can also update the state information on the basis of a channel measurement result, and state information of the AI models of the two sides can be synchronously updated. Therefore, the network side can more accurately reconstruct the channel measurement result, thereby providing support for the feedback performance guarantee of the CSI report.

Description

Communication method and communication apparatus

[0001] This application claims priority from the Chinese patent application No. 202410445788.0 filed on April 12, 2024, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of wireless communication, and in particular, to a communication method and a communication apparatus. BACKGROUND

[0003] In a massive multiple input multiple output (Massive MIMO) system, the feedback of channel state information (CSI) report is crucial for the scheduling of a network device. For example, the network device can determine one or more of a modulation and coding scheme (MCS), precoding, etc. based on the CSI. However, as the size of the antenna array continues to increase, the number of supported antenna ports also increases, and the dimensions of the corresponding channel matrix and precoding matrix also increase, which increases the feedback overhead of the CSI report.

[0004] Currently, there are schemes that use an artificial intelligence (AI) model to compress and reconstruct (or recover) channel measurement results. The sender (such as a terminal) of the CSI report can use the AI model to compress the channel measurement results and send the obtained CSI report. The receiver (such as a network device) of the CSI report can use the AI model to reconstruct the channel measurement results based on the received CSI report.

[0005] However, in a wireless communication link, the channel of a low-speed user is continuously changing in time, and therefore the time-domain correlation of the channel needs to be mined to improve the communication performance. When the AI model of the sender compresses the CSI report, the time-domain correlation features of the channel can be extracted based on the channel measurement results as input parameters for the next CSI report compression of the AI model, and such iteration can enable each CSI report compression to adapt to the time-domain changes of the channel. In order to enable the AI model of the receiver to accurately reconstruct the channel measurement results based on the received CSI report, the AI model of the receiver also needs to obtain the same time-domain correlation features as the sender. Therefore, how to enable the transmitter and the receiver to synchronously update the time-domain correlation features of the channel is a technical problem that needs to be solved urgently. SUMMARY

[0006] The application provides a communication method and a communication device, which are beneficial to synchronously updating time-domain correlation characteristics of a channel by a transmitting and receiving party, and further beneficial to accurately reconstructing channel measurement results by a receiving party of a CSI report.

[0007] In a first aspect, a communication method is provided. The method can be applied to a terminal side, for example, can be applied to a terminal device, such as the terminal device itself, or a component deployed in the terminal device, such as a circuit or a chip (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core, etc.) inside the terminal device, etc.; or can be applied to a device other than the terminal device, such as a host or a cloud server of an over the top (OTT) system, or a component deployed in the device other than the terminal device, such as a circuit or a chip, etc.; or can be applied to a logic module or software, etc. capable of realizing all or part of the functions of the terminal side. The application does not make any limitation in this regard.

[0008] Exemplarily, the method comprises: obtaining a CSI report, the CSI report being obtained by processing a channel measurement result, the CSI report comprising a first part and a second part; transmitting a first report, the first report comprising the first part in the CSI report and not comprising the second part; and transmitting a second report, the second report comprising the second part in the CSI report.

[0009] In a second aspect, a communication method is provided. The method can be applied to a network side, for example, can be applied to a network device, such as the network device itself, or a component deployed in the network device, such as a circuit or a chip (such as a modem chip, or a SoC chip or a SIP chip containing a modem core, etc.) inside the network device having a near real-time radio access network (RAN) intelligent control function, etc.; or can be applied to a device other than the network device, such as an intelligent network element having a near real-time RAN intelligent control function, etc.; or can be applied to a logic module or software, etc. capable of realizing all or part of the functions of the network side. The application does not make any limitation in this regard.

[0010] Exemplarily, the method comprises: receiving a first report, the first report comprising a first part in a CSI report and not comprising a second part; the CSI report being obtained by processing a channel measurement result, the CSI report comprising the first part and the second part; and receiving a second report, the second report comprising the second part.

[0011] The first aspect and the second aspect above are corresponding. Wherein, the first part and the second part can be understood as two parts of information in the CSI report, or in other words, the CSI report is composed of the first part and the second part. It should be understood that the present application does not limit which information in the CSI report is included in the first part and the second part, nor does it limit the amount of data included in the first report and the second report (or the length of the first report and the second report), that is, it does not limit how many resources are needed to transmit the first report and the second report.

[0012] It can be understood that the first report includes the first part but does not include the second part, that is, the information included in the first report is part of the information in the CSI report, and therefore the first report can be a report obtained by omitting part of the information in the CSI report. The second report includes the second part, that is, the omitted part of the information can be sent through the second report. In this way, the network side can obtain the complete CSI report by receiving the first report and the second report.

[0013] Based on the above scheme, the terminal side transmits the first report and the second report, which is conducive to the network side receiving the complete CSI report, and further conducive to the network side performing subsequent steps based on the complete CSI report, such as updating the state information of the AI model. In the present application, the terminal side can update the state information of the AI model (for example, denoted as a first AI model) based on the channel measurement result. If the network side updates the state information of the AI model (for example, denoted as a second AI model) based on the first report and the second report, that is, can update the state information based on the complete CSI report, and the CSI report is obtained by processing the channel measurement result by the first AI model, therefore, the network side can also update the state information based on the same or corresponding input as the terminal side, that is, can synchronously mine the time domain related features of the channel. Thus, it is helpful for the network side to more accurately reconstruct the channel measurement result, and further conducive to improving the communication performance. In addition, by mining the time domain related features of the historical channel measurement result and the current channel measurement result to realize more accurate channel compression, the problem of channel aging is counteracted, and the overhead of feeding back the channel measurement result can be reduced.

[0014] In combination with the first aspect or the second aspect, in some possible implementation manners, the CSI report is an output obtained by processing the channel measurement result by the first AI model once.

[0015] Or in other words, the CSI report is obtained by processing the channel measurement result by the first AI model once. Or in other words, the CSI report corresponds to the same input (or in other words, the same input, or the same input once) of the first AI model, which is the channel measurement result. Or in other words, the first report and the second report correspond to the same input of the first AI model.

[0016] The processing can include compression, or compression and quantization. For example, the first AI model obtains the CSI report by compressing and quantizing the channel measurement result.

[0017] In some possible implementation manners, the first part and / or the second part are used for updating the state information of the second AI model.

[0018] Correspondingly, in the second aspect, the method further includes: updating the state information of the second AI model based on the first part and / or the second part.

[0019] The state information can be used to represent the time-domain correlation characteristics of the channel. By updating the state information, the second AI model can mine the time-domain correlation characteristics of the channel, so that the channel measurement result can be reconstructed more accurately based on the received report.

[0020] The terminal side sends the complete CSI report (i.e., including the first part and the second part) to the network side by sending the first report and the second report, so that the network side can update based on the complete CSI report. However, due to the time-varying characteristics of the channel state, packet loss may occur in the transmission of the first report and / or the second report. Therefore, the network side can use the received information to update the state information of the second AI model. If the network side receives the first report and the second report, the first part and the second part can be used for updating; if the network side receives the first report, the first part in the first report can be used for updating; if the network side receives the second report, the second part (or the second part and the first part) in the second report can be used for updating. In other words, whether the network side uses the first part or the second part or the first part and the second part for updating is related to the information received by the network side.

[0021] In some possible implementation manners, the resource used for transmitting the first report is a first resource, and the resource used for transmitting the second report is a second resource. The time offset between the first resource and the second resource in the time domain is less than or equal to a threshold value.

[0022] That is, the first report and the second report are not sent at the same time. In other words, the transmission of the first report and the second report is two different transmissions, and different resources are used.

[0023] Optionally, in some possible implementation manners of the first aspect, the method further includes: receiving first indication information, the first indication information being used to indicate the second resource.

[0024] Accordingly, in some possible implementations of the second aspect, the method further includes: sending first indication information, where the first indication information is used to indicate the second resource.

[0025] The network side may schedule the second resource for the transmission of the second report through signaling (i.e., the first indication information). In other words, the second resource used for the transmission of the second report is not necessarily the resource for CSI reporting configured in advance by the network side through the CSI reporting configuration (CSI-ReportConfig).

[0026] In combination with the first aspect or the second aspect, in some possible implementations, the first report and the second report come from the terminal side, and the above threshold value is determined based on the storage capacity of the terminal device on the terminal side.

[0027] After sending the first report, the terminal needs to send a second report to replace the discarded information. Therefore, some or all of the information in the CSI report needs to be cached. The second report is transmitted via a second resource. Therefore, the time offset between the second resource and the first resource in the time domain can be determined based on the terminal device's storage capacity.

[0028] The storage capacity of the terminal device may be an upper limit on the duration for which the terminal device can store part or all of the information in the CSI report, or in other words, the maximum duration for which the terminal device can store part or all of the information in the CSI report. Alternatively, the storage capacity of the terminal device may be an upper limit on the storage space of the terminal device, or in other words, the maximum value of the storage space of the terminal device.

[0029] Optionally, in the first aspect, the method further includes: sending capability information, where the capability information is used to indicate the storage capability of the terminal device.

[0030] Accordingly, in the second aspect, the method further includes: receiving capability information, where the capability information is used to indicate the storage capability of the terminal device.

[0031] The terminal side reports the storage capacity of the terminal device through capability information, so that the network side can take into account the storage capacity of the terminal device when scheduling the second resource for the second report, so that the second report can be sent through the second resource before being cleared from the storage space of the terminal, thereby more effectively ensuring that the terminal side sends both the first report and the second report to the network side.

[0032] In combination with the first aspect or the second aspect, in some possible implementations, the second report also includes a first part.

[0033] The second report also includes the first part, that is, the second report includes the first part and the second part, or in other words, the second report includes all the information in the CSI report, or in other words, the second report is a CSI report.

[0034] By sending the first part and the second part through the second report, the network side can perform merging processing based on the first part in the first report and the second report, thereby improving the receiving performance and obtaining accurate and complete CSI reports.

[0035] With reference to the first aspect or the second aspect, in some possible implementation manners, the second report does not include the first part.

[0036] The second report includes the second part and does not include the first part, that is, the second report only includes the second part, or in other words, the second report includes part of the CSI report.

[0037] By sending the second part through the second report, the network side can obtain the second part that is not obtained in the first report from the second report, thereby obtaining complete CSI reports. Meanwhile, by sending the second part through the second report and not sending the first part, resource occupation caused by repeated sending of the first part can be avoided, and resources can be saved.

[0038] As described above, the content of the second report can be the first part and the second part, or only the second part. The content of the second report can be notified by the network side in real time through signaling, or can be configured by the network side in advance through signaling, or can be predefined by a protocol, and the present application does not limit this.

[0039] Optionally, in some possible implementation manners of the first aspect, the method further includes: receiving second indication information, the second indication information being used to indicate the content of the second report.

[0040] Correspondingly, in some possible implementation manners of the second aspect, the method further includes: sending second indication information, the second indication information being used to indicate the content of the second report.

[0041] The second indication information can be configured in real time, for example, the network side can indicate the content of the second report of the terminal side through the second indication information after receiving the first report. For example, the second indication information and the first indication information described above for scheduling the second resource can be carried in the same signaling, for example, in downlink control information (DCI).

[0042] The second indication information can also be sent before CSI reporting, that is, pre-configured, and the terminal side can send the second report based on the second reported content indicated by the second indication information in the subsequent CSI reporting process. It can be understood that even if the second reported content can be pre-configured, the network side does not limit the data amount (or the length of the second report) in the second report, in other words, based on the configuration of the same second indication information, the data amount in the second report in two or more CSI reporting processes after that can be different or the same, which is not limited.

[0043] In a third aspect, a communication method is provided, which can be applied to a terminal side, for example, can be applied to a terminal device, such as the terminal device itself, or a component deployed in the terminal device, such as a circuit or a chip (such as a modem chip, also known as a baseband chip, or a SoC chip or a SIP chip containing a modem core, etc.) inside the terminal device, etc.; or, can be applied to a device other than the terminal device, such as a host or a cloud server of an OTT system, or a component deployed in the device other than the terminal device, such as a circuit or a chip, etc.; or, can be applied to a logic module or software, etc. capable of realizing all or part of the functions of the terminal side. The present application does not limit this.

[0044] Exemplarily, the method comprises: sending a first report, the first report comprising a first part of a CSI report, the CSI report being obtained by processing a channel measurement result, the CSI report comprising the first part and a second part; receiving third indication information, the third indication information being used for indicating a second reported content; and sending the second report based on the third indication information.

[0045] In a fourth aspect, a communication method is provided, which can be applied to a network side, for example, can be applied to a network device, such as the network device itself, or a component deployed in the network device, such as a circuit or a chip (such as a modem chip, or a SoC chip or a SIP chip containing a modem core, etc.) inside the network device having a near-real-time RAN intelligent control function, etc.; or, can be applied to a device other than the network device, such as an intelligent network element having a near-real-time RAN intelligent control function, etc.; or, can be applied to a logic module or software, etc. capable of realizing all or part of the functions of the network side. The present application does not limit this.

[0046] Exemplarily, the method comprises: sending third indication information, the third indication information being used for indicating a second reported content, the second report comprising a second part of a CSI report, the CSI report being obtained by processing a channel measurement result, the CSI report comprising the first part and the second part; and receiving the second report.

[0047] Based on the above solution, if packet loss occurs on the terminal side, the network can instruct the terminal side to send a second report through signaling, that is, to instruct the terminal side to retransmit the CSI report. As a result, the terminal side can transmit some or all of the information in the CSI report to the network side through the second report. Therefore, the network side can reconstruct the channel measurement results based on the received second report, which facilitates reasonable scheduling on the network side and improves communication performance.

[0048] In combination with the fourth aspect, in some possible implementations of the fourth aspect, the method further includes: reconstructing the channel measurement result based on the second report.

[0049] In combination with the third aspect or the fourth aspect, in some possible implementations, the CSI report is an output obtained after the first AI model processes the channel measurement result.

[0050] In other words, the CSI report is obtained after the first AI model processes the channel measurement result once. Alternatively, the CSI report corresponds to the same input (or the same input, or the same input) of the first AI model, where the same input is the channel measurement result. Alternatively, the first report and the second report correspond to the same input of the first AI model.

[0051] The processing may include compression and quantization. That is, the first AI model obtains the CSI report by compressing and quantizing the channel measurement result.

[0052] In combination with the third aspect or the fourth aspect, in some possible implementations, the second report is used to update status information of the second AI model.

[0053] Accordingly, in some possible implementations of the fourth aspect, the method further includes: updating the status information of the second AI model based on the second report.

[0054] For the description of the status information, please refer to the relevant description of the status information in the first and second aspects, which will not be repeated here.

[0055] In combination with the third aspect or the fourth aspect, in some possible implementations, the second report includes the first part of the CSI report but does not include the second part.

[0056] The second report includes the first part but does not include the second part, that is, the second report only includes the first part, or in other words, the second report includes part of the information in the CSI report.

[0057] The first report is generated by discarding part of the information of the CSI report, and the first part can contain information of a larger part of the CSI report. Therefore, by sending the first part through the second report, the network side can at least obtain information of a larger part of the CSI report, and thus can reconstruct the channel measurement structure and update the state information based on most of the information of the CSI report. This is beneficial to the network side to obtain an accurate and complete CSI report.

[0058] In some possible implementation manners, the second report includes the first part and the second part of the CSI report.

[0059] The second report includes the first part and the second part of the CSI report, that is, the second report includes all the information in the CSI report, or the second report is the CSI report.

[0060] By sending the first part and the second part through the second report, the network side can perform merging processing based on the first part in the first report and the second report, thereby improving the reception performance and being beneficial to the network side to obtain an accurate and complete CSI report.

[0061] In some possible implementation manners, the resource for transmitting the first report is a first resource, and the resource for transmitting the second report is a second resource, and a time offset between the first resource and the second resource in the time domain is less than or equal to a threshold value.

[0062] For related descriptions of the first resource, the second resource, and the threshold value, refer to the related descriptions in the first aspect and the second aspect, which will not be repeated here.

[0063] Optionally, in some possible implementation manners of the third aspect, the method further includes: receiving fourth indication information, the fourth indication information being used to indicate the second resource, and the second resource being used to transmit the second report.

[0064] Correspondingly, in some possible implementation manners of the fourth aspect, the method further includes: sending fourth indication information, the fourth indication information being used to indicate the second resource, and the second resource being used to transmit the second report.

[0065] The fourth indication information in the third aspect and the fourth aspect is similar to the second indication information in the first aspect and the second aspect, and for related descriptions of the second indication information, refer to the related descriptions in the first aspect and the second aspect, which will not be repeated here.

[0066] In some possible implementation manners, the first report and the second report are from the terminal side, and the threshold value is determined based on a storage capability of a terminal device of the terminal side.

[0067] The related description about the storage capability of the terminal device can refer to the related description in the first aspect and the second aspect, and will not be repeated.

[0068] Optionally, in some possible implementation manners of the third aspect, the method further includes: sending capability information, the capability information being used to indicate the storage capability of the terminal device.

[0069] Correspondingly, in some possible implementation manners of the fourth aspect, the method further includes: receiving capability information, the capability information being used to indicate the storage capability of the terminal device.

[0070] The capability information in the third aspect and the fourth aspect is the same as the capability information in the first aspect and the second aspect, and the related description of the capability information in the first aspect and the second aspect will not be repeated.

[0071] The fifth aspect provides an apparatus. The apparatus can include a module corresponding to each of the methods / operations / steps / actions described in the first aspect to the fourth aspect, or include a module corresponding to each of the methods / operations / steps / actions described in the first aspect to the fourth aspect. The module can be a hardware circuit, or software, or a combination of hardware circuit and software.

[0072] In one design, the apparatus can include a processing module and a communication module. The communication module can be configured to perform the sending actions and the receiving actions performed by the terminal side in the methods described in the first aspect or the third aspect, and the processing module can be configured to perform the actions related to processing performed by the terminal side in the methods described in the first aspect or the third aspect.

[0073] In one design, the apparatus can be a terminal, or an apparatus / module / circuit / chip or the like configured to be disposed in a terminal, or an apparatus capable of being used in matching with the terminal, such as an OTT host or a cloud server.

[0074] In one design, the apparatus can include a processing module and a communication module. The communication module can be configured to perform the sending actions and the receiving actions performed by the network side in the methods described in the second aspect or the fourth aspect, and the processing module can be configured to perform the actions related to processing performed by the network side in the methods described in the second aspect or the fourth aspect.

[0075] In a design, the apparatus can be a network device, or an apparatus, module, circuit or chip configured to be disposed in a network device, or an apparatus capable of matching use with a network device, such as a smart network element deployed with a radio access network (RAN) intelligent controller (RIC).

[0076] In a sixth aspect, an apparatus is provided, including a processor and a storage medium, the storage medium storing instructions which, when executed by the processor, cause the method in the first aspect or any possible implementation manner of the first aspect to be implemented, or cause the method in the second aspect or any possible implementation manner of the second aspect to be implemented, or cause the method in the third aspect or any possible implementation manner of the third aspect to be implemented, or cause the method in the fourth aspect or any possible implementation manner of the fourth aspect to be implemented.

[0077] In a seventh aspect, an apparatus is provided, including processing circuitry for processing data and / or information, so that the method in the first aspect or any possible implementation manner of the first aspect is implemented, or the method in the second aspect or any possible implementation manner of the second aspect is implemented, or the method in the third aspect or any possible implementation manner of the third aspect is implemented, or the method in the fourth aspect or any possible implementation manner of the fourth aspect is implemented.

[0078] The processing circuitry can include one or more processors, or all or part of circuitry for controlling or processing functions in the one or more processors.

[0079] Optionally, the apparatus can further include a memory for storing programs or instructions, and the processor is configured to execute the programs or instructions, so that the method in the first aspect or any possible implementation manner of the first aspect is implemented, or the method in the second aspect or any possible implementation manner of the second aspect is implemented, or the method in the third aspect or any possible implementation manner of the third aspect is implemented, or the method in the fourth aspect or any possible implementation manner of the fourth aspect is implemented.

[0080] Optionally, the apparatus can further include the transceiver circuit, or an input / output interface.

[0081] In an eighth aspect, a chip is provided, comprising processing circuitry configured to execute programs or instructions to cause the method in the first aspect or any possible implementation of the first aspect to be implemented, or to cause the method in the second aspect or any possible implementation of the second aspect to be implemented, or to cause the method in the third aspect or any possible implementation of the third aspect to be implemented, or to cause the method in the fourth aspect or any possible implementation of the fourth aspect to be implemented.

[0082] Optionally, the chip can further comprise a memory configured to store the programs or instructions.

[0083] Optionally, the chip can further comprise a transceiver circuitry, or an input / output interface.

[0084] In a ninth aspect, a computer readable storage medium is provided, comprising instructions which, when executed on a processor, cause the method in the first aspect or any possible implementation of the first aspect to be implemented, or cause the method in the second aspect or any possible implementation of the second aspect to be implemented, or cause the method in the third aspect or any possible implementation of the third aspect to be implemented, or cause the method in the fourth aspect or any possible implementation of the fourth aspect to be implemented.

[0085] In a tenth aspect, a computer program product is provided, comprising computer program code or instructions which, when executed on a processor, cause the method in the first aspect or any possible implementation of the first aspect to be implemented, or cause the method in the second aspect or any possible implementation of the second aspect to be implemented, or cause the method in the third aspect or any possible implementation of the third aspect to be implemented, or cause the method in the fourth aspect or any possible implementation of the fourth aspect to be implemented.

[0086] In an eleventh aspect, a communication system is provided, comprising the apparatus in the first or second aspect and any possible implementation of the first or second aspect, or comprising the apparatus in the third or fourth aspect and any possible implementation of the third or fourth aspect.

[0087] It should be understood that the fifth aspect to the eleventh aspect of the present application correspond to the technical solutions of the first aspect to the fourth aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding possible implementation are similar, which will not be described again. BRIEF DESCRIPTION OF DRAWINGS

[0088] FIG. 1 is a schematic diagram of a communication system suitable for the communication method provided by the embodiments of the present application;

[0089] FIG. 2 is a schematic diagram of another communication system applicable to the communication method provided by the embodiments of the present application;

[0090] FIG. 3 is a schematic diagram of a possible application architecture in a communication system;

[0091] FIG. 4 is a schematic diagram of another possible application architecture in a communication system;

[0092] FIG. 5 is a schematic diagram of CSI feedback using an auto encoder (AE) model;

[0093] FIG. 6 is a schematic diagram of a processing flow of compression, feedback and reconstruction of channel measurement results using time-domain correlation on both network side and terminal side;

[0094] FIG. 7 is a schematic flowchart of the communication method provided by the embodiments of the present application;

[0095] FIG. 8 is a schematic diagram of the method flow provided by the embodiments of the present application shown by a time sequence relationship;

[0096] FIG. 9 is another schematic diagram of the method flow provided by the embodiments of the present application shown by a time sequence relationship;

[0097] FIG. 10 is another schematic flowchart of the communication method provided by the embodiments of the present application;

[0098] FIG. 11 is yet another schematic flowchart of the communication method provided by the embodiments of the present application;

[0099] FIG. 12 is a schematic flowchart of the communication method provided by another embodiment of the present application;

[0100] FIG. 13 is a schematic diagram of the method flow provided by another embodiment of the present application shown by a time sequence relationship;

[0101] FIG. 14 is a schematic block diagram of a possible apparatus provided by the embodiments of the present application;

[0102] FIG. 15 is another schematic block diagram of a possible apparatus provided by the embodiments of the present application. DETAILED DESCRIPTION

[0103] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0104] For the convenience of understanding the embodiments of the present application, the following points are first explained:

[0105] First, in this application, the terminal side includes: terminal equipment, components deployed in the terminal equipment (such as circuits or chips inside the terminal equipment, etc.), equipment deployed outside the terminal equipment (such as OTT hosts or cloud servers), or components deployed in equipment outside the terminal equipment (such as circuits or chips inside the equipment, etc.). The network side includes: network equipment that communicates with the terminal equipment, components deployed in the network equipment (such as circuits or chips with near-real-time RAN intelligent control functions inside the network equipment, etc.), equipment deployed outside the network equipment (such as intelligent network elements, for example, the intelligent network element is an intelligent network element with near-real-time RAN intelligent control functions) or components deployed in the intelligent network element (such as circuits or chips inside the intelligent network element, etc.). Among them, network equipment may include: access network equipment, core network equipment, or operation administration and maintenance (OAM).

[0106] Second, in this application, indication includes direct indication (also called explicit indication) and indirect indication (also called implicit indication). Directly indicating information A means including information A; indirectly indicating information A may mean indicating information A through the correspondence between information A and information B and directly indicating information B; or indicating information A through a preset rule that can be used to determine A based on B and directly indicating information B. The correspondence between information A and information B, and the preset rule may be predefined, pre-stored, pre-burned, or pre-configured.

[0107] Third, in this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship, but it does not exclude the situation where the previous and next associated objects are in an "and" relationship. The specific meaning can be understood in conjunction with the context. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, c can be single or multiple.

[0108] Fourthly, in the present application, the use of prefixes such as "first", "second" and the like is merely intended to differentiate between different things belonging to the same category of names, and does not impose any constraint on the order, size or quantity of the things. For example, "first report" and "second report" are merely different reports, and do not limit the size relationship or priority relationship of the reports; for another example, "first resource" and "second resource" are merely different resources, and do not limit the size relationship or priority relationship of the resources; for yet another example, "first indication information" and "second indication information" are merely different indication information, and do not limit the quantity, time sequence relationship, size relationship or priority relationship of the information.

[0109] Fifthly, in the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending a report to the network side" can be understood as that the destination of the report is the network side, which can include direct transmission through the air interface, or indirect transmission through the air interface by other units or modules. "Receiving a report from the terminal side" can be understood as that the source of the information is the terminal side, which can include direct reception from the terminal side through the air interface, or indirect reception from the terminal side through the air interface by other units or modules. "Sending" can also be understood as "output" of a chip interface, and "receiving" can also be understood as "input" of a chip interface.

[0110] In other words, sending and receiving can be between devices, such as between network devices and terminal devices; or can be within a device, such as between components, modules, chips, software modules or hardware modules within a device through a bus, wire or interface.

[0111] Sixthly, in the embodiments of the present application, "when", "if" and "whether" all refer to the device making corresponding processing under certain objective circumstances, and are not limited in time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0112] Seventhly, in the present application, the words "example", "exemplary", "for example", "for instance" or "such as" are used to represent an example, an example or an illustration. Any embodiment or design scheme described as "example", "exemplary", "for example" or "such as" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "example", "exemplary", "for example" or "such as" is intended to present the relevant concept in a specific manner.

[0113] The technical solutions provided in the present application can be applied to various communication systems, for example: a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system such as a 6th generation (6G) mobile communication system, or a converged system of multiple systems, and the like. The technical solutions 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 an internet of things (IoT) communication system or other communication systems.

[0114] A device in a communication system can send a signal to another device or receive a signal from another device. Wherein, the signal can include information, signaling or data, etc. Wherein, the device can also be replaced by an entity, a network entity, a network element, a communication device, a communication module, a node, a communication node, etc. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It can be understood that the terminal in the present disclosure can be replaced by a first device, and the network device can be replaced by a second device, both of which perform the corresponding communication method in the present disclosure.

[0115] In a wireless communication network, e.g., in a mobile communication network, the services supported by the network are increasingly diverse, and thus the requirements to be met are increasingly diverse. For example, the network needs to be able to support ultra-high rates, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as the network becomes increasingly powerful, e.g., supports increasingly high frequency spectrum, supports high-order multiple input multiple output (MIMO) technology, supports beamforming, supports beam management, and other new technologies, 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. To meet this challenge, artificial intelligence technology can be introduced into the wireless communication network, thereby realizing network intelligence. In order to support AI technology in the wireless network, an AI node can also be introduced into the network.

[0116] FIG. 1 is a schematic diagram of a communication system suitable for a communication method according to embodiments of the present application. As shown in FIG. 1, the communication system 100A can include at least one access network device, e.g., the access network device 110 shown in FIG. 1; the communication system 100A can also include at least one terminal device, e.g., the terminal device 120 and the terminal device 130 shown in FIG. 1. The access network device 110 and the terminal devices (e.g., the terminal device 120 and the terminal device 130) can communicate through wireless links. The communication devices in the communication system, e.g., the access network device 110 and the terminal device 120, can communicate through multi-antenna technology.

[0117] FIG. 2 is a schematic diagram of another communication system suitable for a communication method according to embodiments of the present application. Compared with the communication system 100A shown in FIG. 1, the communication system 100B shown in FIG. 2 further includes an AI network element 140. The AI network element 140 is configured to perform AI-related operations, e.g., constructing a training data set or training an AI model. The AI network element can also be referred to simply as an intelligent network element.

[0118] In a possible implementation, the access network device 110 can send data related to training of the AI model to the AI network element 140, the AI network element 140 constructs a training data set and trains the AI model. For example, the data related to training of the AI model can include data reported by the terminal device. The AI network element 140 can send a result of an operation related to the AI model to the access network device 110, and forward the result to the terminal device through the access network device 110. For example, the result of the operation related to the AI model can include at least one of the following: a trained AI model, an evaluation result or a test result of the model, and the like. For example, part of the trained AI model can be deployed on the access network device 110, and the other part can be deployed on the terminal device 120 and / or the terminal device 130. Alternatively, the trained AI model can be deployed on the access network device 110. Alternatively, the trained AI model can be deployed on the terminal device 120 and / or the terminal device 130.

[0119] It should be understood that FIG. 2 is only used as an example to illustrate that the AI network element 140 is directly connected to the access network device 110, and in other scenarios, the AI network element 140 can also be connected to the terminal device. Alternatively, the AI network element 140 can be connected to both the access network device 110 and the terminal device. Alternatively, the AI network element 140 can also be connected to the access network device 110 through a third-party network element. The connection relationship between the AI network element and other network elements is not limited in the embodiments of the present application.

[0120] The AI network element 140 can also be arranged as a module in the access network device and / or the terminal device, for example, in the access network device 110 or the terminal device shown in FIG. 1.

[0121] It should be noted that FIG. 1 and FIG. 2 are only simplified schematic diagrams for understanding, for example, the communication system can also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in FIG. 1 and FIG. 2. In actual application, the communication system can include multiple access network devices, and can also include multiple terminal devices. The number of access network devices and terminal devices included in the communication system is not limited in the embodiments of the present application.

[0122] In the embodiments of the present application, the terminal device can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user device.

[0123] The terminal device may be a device that provides voice / data, such as a handheld device or 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 (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0124] As an example and not a 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 achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those 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 smart bracelets and smart jewelry for vital sign monitoring.

[0125] In the embodiments of the present application, the apparatus for implementing the function of the terminal device can be a terminal device, or can be an apparatus capable of supporting the terminal device to implement the function, for example, a chip system, which can be installed in the terminal device or used in matching with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include the chip and other discrete devices. In the embodiments of the present application, only the apparatus for implementing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited in this way.

[0126] The access network device in the embodiments of the present application can be a device for communicating with a terminal device, and the access network device can also be referred to as a wireless access network device, for example, the access network device can be a base station. The access network device in the embodiments of the present application can refer to a RAN node (or device) for accessing a terminal device to a wireless network. The base station can broadly cover or be replaced by the following various names, such as: node B (NodeB), evolved node B (eNB), next generation node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, multi-standard radio (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 can also refer to a communication module, modem or chip used in the foregoing devices or apparatuses. The base station can also be a mobile switching center and a device assuming a base station function in D2D, V2X, M2M communication, a network side device in a 6G network, a device assuming a base station function in a future communication system, etc. The base station can support networks of the same or different access technologies. Alternatively, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the V2X technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form of the access network device.

[0127] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to act as a device communicating with another base station.

[0128] In some deployments, the access network device mentioned by embodiments of the present application can 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 (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the access network device can include a gNB-CU-CP, a gNB-CU-UP and a gNB-DU.

[0129] In some deployments, wireless access is assisted for a terminal by multiple RAN nodes cooperating, different RAN nodes respectively implementing part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a BBU. The RU can be included in a radio frequency device or a radio frequency unit, for example, included in an RRU, an AAU or an RRH.

[0130] The RAN node can support one or more types of front interfaces, different front interfaces respectively corresponding to DUs and RUs having different functions. If the front interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions. If the front interface between the DU and the RU is another interface, relative to the CPRI, part of the baseband functions of the downlink and / or uplink, such as one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP) for the downlink, or one or more of digital beamforming (BF), or fast Fourier transform (FFT) / removing cyclic prefix (CP) for the uplink, are moved from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0131] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, while other functions (e.g., one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, the DU is configured to implement de-mapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, de-RE mapping) before de-mapping, while other functions (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) after de-mapping are implemented in the RU. It can be understood that the function descriptions of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which will not be described here.

[0132] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0133] In different systems, the CU (or CU-CP and CU-UP), DU, or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (ORAN) architecture, the CU can also be referred to as an open-CU (O-CU), the DU can also be referred to as an open-DU (O-DU), the CU-CP can also be referred to as an open-CU-CP (O-CU-CP), the CU-UP can also be referred to as an open-CU-UP (O-CU-UP), and the RU can also be referred to as an open-RU (O-RU). Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0134] In an embodiment of the present application, the apparatus for implementing the function of the access network device can be the access network device, or can be an apparatus capable of supporting the access network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus can be installed in the access network device or used in combination with the access network device. In the embodiments of the present application, only the apparatus for implementing the function of the access network device is taken as an example for description, and the present application is not limited in this regard.

[0135] The access network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water; and can also be deployed on airplanes, balloons and satellites in the air. The present application does not limit the scenarios in which the access network device and the terminal device are located. In addition, the terminal device and the access network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the access network device.

[0136] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, or a network element of a core network, etc. Optionally, the AI node can also be deployed separately, for example, in a host or a cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: an access network device, a terminal device, or a network element of a core network, etc.

[0137] It can be 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 responsible for different functions.

[0138] It can also be understood that the AI node can be a separate device, or can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on special hardware, or can be a virtualized function instantiated on a platform (for example, a cloud platform), and the present application does not limit the specific forms of the AI node.

[0139] The AI node can be an AI network element or an AI module.

[0140] FIG. 3 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 3, network elements in the communication system are connected through interfaces (e.g., NG interface, Xn interface), or air interface. One or more AI modules (only one is shown in FIG. 3 for clarity) are deployed in one or more of the network element nodes, such as a core network device, an access network node (RAN node), a terminal, or an OAM device. The access network node can be a single RAN node, or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or the DU can also be provided with one or more AI modules. Optionally, the CU can be further split into a CU-CP and a CU-UP. One or more AI models are deployed in the CU-CP and / or the CU-UP.

[0141] The AI module is used to implement a corresponding AI function. AI modules deployed in different network elements can be the same or different. The AI module can implement different functions according to different parameter configurations of the model of the AI module. The model of the AI module can be configured based on one or more of the following parameters: a structural parameter (e.g., at least one of a number of neural network layers, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in the activation function), an input parameter (e.g., a type of input parameter and / or a dimension of the input parameter), or an output parameter (e.g., a type of output parameter and / or a dimension of the output parameter). The bias in the activation function can also be referred to as a bias of the neural network.

[0142] One AI module can have one or more models. One model can infer an output including one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0143] The network device can be a network device provided with one or more AI modules. The network device can be one or more of the core network device, the access network node (RAN node), or the operation administration and maintenance (OAM) shown in FIG. 3. For example, the AI module can be the RIC shown in FIG. 4, such as a near-real-time RIC or a non-real-time RIC. For example, the near-real-time RIC is provided in the RAN node (for example, in the CU, the DU, etc.), and the non-real-time RIC is provided in the OAM, the cloud server, the core network device, or other network devices. The RIC can obtain a subset of data from multiple terminal devices from the RAN node (for example, the CU, the CU-CP, the CU-UP, the DU, and / or the RU), reorganize the subset of data into a training data set, and train based on the training data set. For example, the near-real-time RIC and the non-real-time RIC can also be provided as a network element, respectively, and the network device can be the near-real-time RIC or the non-real-time RIC.

[0144] FIG. 4 is a schematic diagram of a possible application framework in a communication system. In addition to the access network node (CUs, DUs, and RUs are shown in the figure) and the terminal, the communication system shown in FIG. 4 also includes a RIC. For example, the RIC can be the AI module shown in FIG. 3, which can be used to implement AI-related functions. The RIC includes a near-real-time RIC (near-RT RIC) and a non-real-time RIC (Non-RT RIC). The non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to latency, which can be on the order of seconds. The near-real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to latency, which can be on the order of tens of milliseconds.

[0145] The near-real-time RIC is used for model training and inference. For example, the near-real-time RIC is used to train an AI model and perform inference using the AI model. The near-real-time RIC can obtain network-side and / or terminal-side information from the RAN node (for example, the CU, the CU-CP, the CU-UP, the DU, and / or the RU) and / or the terminal. This information can be used as training data or inference data. Optionally, the near-real-time RIC can submit the inference result to the RAN node and / or the terminal. Optionally, the CU and the DU, and / or the DU and the RU can exchange the inference result. For example, the near-real-time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0146] The non-real-time RIC is also used for model training and inference. For example, for training an AI model, inference is performed using the model. The non-real-time RIC can obtain network-side and / or terminal-side information from the RAN node (e.g., one or more of a CU, a CU-CP, a CU-UP, a DU, or an RU) and / or a terminal. This information can be used as training data or inference data, and the inference result can be delivered to the RAN node and / or the terminal. Alternatively, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU, e.g., the non-real-time RIC delivers the inference result to the DU, which then sends it to the RU.

[0147] The near-real-time RIC and the non-real-time RIC can also be separately provided as a network element. Alternatively, the near-real-time RIC and the non-real-time RIC can also be part of other devices, e.g., the near-real-time RIC is provided in the RAN node (e.g., in the CU or the DU), and the non-real-time RIC is provided in the OAM, in the cloud server, in the core network device, or in other network devices.

[0148] With the development of wireless communication technology, more and more services are supported, and higher requirements are put forward for the communication system in terms of system capacity, communication delay, and the like. A large-scale multiple-input multiple-output (MIMO) system can achieve spatial diversity gain and significantly increase system capacity by configuring a large-scale antenna array at the transceiver end, e.g., an access network device can simultaneously send data to multiple terminal devices using the same time-frequency resource (i.e., multi-user MIMO (MU-MIMO)), or simultaneously send multiple data streams to one terminal device (i.e., single-user MIMO (SU-MIMO)). The data between the multiple terminal devices or the multiple data streams of the one terminal device are spatially multiplexed.

[0149] The access network device needs to obtain the channel state information (CSI) of the downlink channel, which is used to determine the configuration of the downlink data channel of the terminal device, such as the resource, the modulation and coding scheme (MCS), and the precoding.

[0150] Taking precoding as an example, in massive MIMO, an access network device needs to precode downlink data by using a precoding matrix. The access network device can use precoding technology to realize spatial division multiplexing between terminal devices or between data streams, that is, data between different terminal devices or between different data streams of the same terminal device is isolated in space, so as to reduce interference between different terminal devices or between different data streams and improve the signal to interference plus noise ratio (SINR) of the terminal device. In order to calculate the precoding matrix, the access network device needs to obtain the channel state information (CSI) of the downlink channel, and determine the precoding matrix according to the CSI.

[0151] In a time division duplexing (TDD) system, since the uplink and downlink channels are reciprocal, the access network device can obtain the uplink CSI by measuring the uplink reference signal, and then infer the more accurate downlink CSI, for example, using the uplink CSI as the downlink CSI. In a frequency division duplexing (FDD) system, the uplink and downlink reciprocity cannot be guaranteed, and the downlink CSI is obtained by the terminal device measuring the downlink reference signal, such as measuring the channel state information reference signal (CSI-RS) or the synchronizing signal block (SSB) to obtain the downlink CSI. Therefore, the terminal device needs to generate a CSI report in a manner of being pre-defined by a protocol or being configured by the access network device, and feed back the generated CSI report to the access network device, so that the access network device obtains the downlink CSI.

[0152] In an FDD system, one important part of CSI feedback is the precoding matrix indicator (PMI), that is, 0-1 bits are used to quantize the channel matrix or the precoding matrix in the CSI. The design of PMI (also known as codebook design) is a basic problem in mobile communication systems. The traditional codebook design method is to pre-define (agree) a series of precoding matrices and corresponding numbers in the protocol, and these precoding matrices are called code words. Using a pre-defined code word or a linear combination of multiple pre-defined code words can approximate the channel matrix or the precoding matrix. Therefore, the terminal device can feed back one or more of the corresponding numbers of the code word and the weighting coefficient to the access network device through the PMI, so as to reconstruct the channel matrix or the precoding matrix by the access network device.

[0153] With the increasing size of the antenna array of the MIMO system, the number of antenna ports that can be supported increases, and the dimension of the corresponding channel matrix and precoding matrix grows. In order to enable the terminal device to estimate (or measure) the downlink channel, the access network device increases the overhead of the reference signal. At the same time, the error of approximating the large-scale channel matrix and the precoding matrix with a limited number of predefined codebooks increases. One method to improve the accuracy of channel reconstruction is to increase the number of codebooks in the codebook, but this will also increase the overhead of the CSI feedback (including one or more of the codebook corresponding number and the weighting coefficient), thereby reducing the available resources for data transmission and causing a loss of system capacity. In summary, it is necessary to study how to more effectively compress the channel information without increasing the overhead of the reference signal and the overhead of the CSI feedback, and how to more effectively reconstruct the channel according to the feedback information.

[0154] There is a correlation between different elements in the downlink channel matrix between the access network device and the terminal device, and there is a correlation between the downlink channel matrices of different time slots. For example, the correlation between different elements in the channel matrix means that there is a set of bases (which can be represented by matrices U1 and U2), and when the channel matrix H is projected onto the set of bases, a sparse equivalent channel H' can be obtained, that is, H' = U1H H U2 is a sparse matrix, where the superscript H represents the conjugate transpose operation. In theory, only the non-zero elements in H' need to be estimated and fed back through the reference signal to reconstruct the channel matrix H. Therefore, there is a compression space for the overhead of the reference signal and the CSI feedback. However, the channel compression space is not fully utilized in the traditional CSI feedback scheme, such as the above-mentioned feedback method based on the codebook, and the channel compression process can cause a large amount of information loss. The method of machine learning (such as deep learning (DL)) has stronger nonlinear feature extraction capability, so it can more effectively extract the correlation between the channel matrices, and thus can more effectively compress the channel information and more effectively reconstruct the channel information according to the feedback information compared with the traditional scheme.

[0155] For the convenience of understanding the embodiments of the present application, the following several terms involved in the present text are briefly explained.

[0156] 1. AE model: it can generally refer to a network structure composed of two sub-models, such as an encoder and a decoder. Each sub-model can be an AI model. The AE model can also be called a bilateral model, a double-end model, a cooperative model, etc. The encoder and the decoder of the AE model are usually trained together and can be used together.

[0157] In this application, the feedback of the CSI report can be implemented based on the AI model of the AE. FIG. 5 shows a schematic diagram of CSI feedback using an AE model.

[0158] As shown in the figure, the obtained CSI measured by the terminal device can be input to the encoder. The encoder on the terminal side can compress and quantize the measured channel measurement result, and output a CSI report. The terminal device can send the CSI report to the network device. The CSI report can be input to the decoder. The decoder on the network side can reconstruct the CSI based on the CSI report to output the recovered CSI. The CSI may, for example, include a channel matrix or a precoding matrix, without limitation.

[0159] For convenience of differentiation and illustration, the CSI measured by the terminal device is denoted as the channel measurement result in this paper. The output of the encoder is denoted as the CSI report. For the encoder on the terminal side, the measured channel measurement result (denoted as H for example) is the input, and the CSI report is the output; for the decoder on the network side, the CSI report is the input, and the recovered channel measurement result (denoted as ) is the output.

[0160] It should be noted that the encoder can be deployed inside the terminal device, or in other devices outside the terminal device, such as the aforementioned OTT host or cloud server, etc.; the decoder can be deployed inside the network device, or in other devices outside the network device, such as the aforementioned intelligent network element.

[0161] 2. The CSI can be determined based on the channel measurement result of the reference signal. In the embodiments of this application, the channel measurement result of the reference signal can also be replaced by the channel information.

[0162] The CSI measurement refers to that the communication device #1 (i.e., the receiver of the reference signal) solves the channel information according to the reference signal sent by the communication device #2 (i.e., the sender of the reference signal), i.e., estimates the channel information by using the channel estimation method. Exemplarily, the reference signal can include one or more of a channel state information reference signal (CSI-RS), a synchronizing signal block (SSB), a sounding reference signal (SRS), or a demodulation reference signal (DMRS). The CSI-RS, SSB, and DMRS, etc. can be used to measure the downlink CSI. The SRS and DMRS, etc. can be used to measure the uplink CSI.

[0163] In this application, the meaning of CSI is broader than that in the traditional scheme, and is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI), but can also include one or more of the following: channel response information (such as a channel response matrix, frequency domain channel response information, and time domain channel response information), weight information corresponding to the channel response, reference signal receiving power (RSRP), or signal to interference plus noise ratio (SINR), etc.

[0164] wherein RI is used to indicate the number of layers of downlink transmission recommended by the communication device #1 for the reference signal, CQI is used to indicate the modulation and coding scheme supported by the current channel condition judged by the communication device #1 for the reference signal, and PMI is used to indicate the precoding recommended by the communication device #1 for the reference signal. The number of layers of precoding indicated by PMI corresponds to RI.

[0165] As described above, measuring the reference signal can obtain channel measurement results (or referred to as channel information). The communication device #1 can perform compression and / or quantization operations on the channel measurement results to obtain feedback information, which is reported to the communication device #2 through a CSI report. The communication device #2 can perform decompression and / or dequantization operations on the feedback information in the CSI report to recover the channel measurement results. In other words, the feedback information is carried in the CSI report, and the information included in the CSI report is the feedback information. The CSI report includes a first part and a second part, i.e., the feedback information includes a first part and a second part.

[0166] The feedback information can also be referred to as feedback information of channel measurement results, feedback information of channel information, feedback information of CSI, CSI feedback information, compressed information, compressed information of channel information, compressed information of CSI, compressed channel information, or compressed CSI, etc.

[0167] The recovered channel measurement results can also be referred to as recovered channel information, or CSI recovery information, etc.

[0168] 3. AI model status information: may also be referred to as one or more of the following: cache information related to the AI ​​model, storage information related to the AI ​​model, intermediate information (for example, intermediate information generated by the AI ​​model), internal information (for example, internal information of the device on which the AI ​​model is deployed or internal information of the AI ​​model), and parameter information generated or updated by the AI ​​model.

[0169] In this application, the state information can be obtained based on the input of the AI ​​model and is the output of the AI ​​model. At the same time, the state information can be used as the input for the next compression (corresponding to the terminal side) and reconstruction (corresponding to the network side) of the AI ​​model. In other words, the state information can be updated as the AI ​​model processes the input, and the updated state information can be used as the input for the next processing of the AI ​​model and updated as the AI ​​model processes the next input. In this way, the state information can be updated each time the AI ​​model processes the input.

[0170] In wireless communication links, channels vary continuously over time. Therefore, it's possible to improve communication performance by exploiting the time-domain correlation of channels. For example, by exploiting the time-domain correlation between historical and current channel measurements, more accurate channel compression can be achieved to combat channel aging. Alternatively, by exploiting the time-domain correlation characteristics of channels, channel measurement results can be compressed to reduce the overhead of feedback.

[0171] For ease of understanding, Figure 6 shows the process flow of compression, feedback, and reconstruction of channel measurement results using time domain correlation on both the network side and the terminal side. t Indicates that the AI ​​model is based on H t The CSI report to be fed back to the network side is processed by c t Indicates that the c t That is, the output of the terminal side AI model and the input of the network side AI model. The network side AI model can be based on the received c t Reconstruct the channel measurement results and obtain the restored channel measurement results through The AI ​​model on the terminal side generates the channel measurement result H based on the input measurement. t Output CSI report c t In addition, you can also get status information t ; The network-side AI model reports CSI based on the input t Output recovered channel measurement results In addition, you can also get status information d t . Among them, t can be taken in order from small to large, for example, starting from 0, and different values ​​of t represent the above parameters obtained at different times.

[0172] It can be seen that the terminal-side AI model and the network-side AI model can both update the state information based on each input and use the updated state information in the processing of the next input. Therefore, the update of the state information can be regarded as an iterative updating process. The initial value of the state information can be agreed in advance between the terminal-side AI model and the network-side AI model, such as both being zero.

[0173] An exemplary process is as follows: at the terminal side, the terminal device can input the channel measurement result H1 at time t1 and the state information e0 into the AI model (for example, an encoder), where the state information e0 can be determined by the information at the historical time, such as the channel measurement result H0 at the previous time, so that the time-domain correlation characteristics of the channel at time t1 can be mined based on the state information e0 and the channel measurement result H1 at time t1. Therefore, the terminal-side AI model can obtain the compressed CSI report c1 and the state information e1 based on the processing of the channel measurement result H1. The terminal device can send the CSI report c1 to the network device and use the state information e1 as an input parameter for processing the channel measurement result H2 at time t2.

[0174] At the network side, after the access network device receives the CSI report c1, the CSI report c1 and the state information d0 can be input into the AI model (for example, a decoder), where the state information d0 can be determined by the information received at the historical time, such as the CSI report c0 received at the previous time, so as to be used for mining the time-domain correlation characteristics of the channel. The network-side AI model can obtain the restored channel measurement result and the state information d1 based on the processing of the received CSI report c0. The network-side AI model can use the state information d1 as an input parameter for processing the CSI report c2 at time t2.

[0175] The mining of the time-domain correlation characteristics of the channel benefits from the synchronous update of the terminal-side state information e t and the network-side state information d t , and the synchronous update of the terminal-side and network-side state information benefits from the fact that the inputs of the AI models of the two sides are the same or corresponding information, such as, for the terminal-side AI model, the input is the channel measurement result H t at time t, and for the network-side AI model, the input is the CSI report c t obtained based on the processing of the channel measurement result at time t.

[0176] However, since the channel state can change over time, the terminal side may need to adjust the MCS when performing CSI report feedback due to reasons such as channel quality degradation, and the resources originally configured for the terminal side to perform CSI reporting may not be sufficient to transmit the CSI report. In this case, in order to feed back the CSI report to the network side, the terminal side may actively omit the transmission of part of the information. In this way, the input of the network side AI model may not be the complete CSI report. This may cause the state information of the terminal side AI model to be updated based on the channel measurement result, and the state information of the network side AI model to be updated based on the incomplete CSI report, which may cause partial update or even failure to update the state information. Therefore, the channel measurement result reconstructed by the network side may not be accurate enough, and the feedback performance of the CSI report cannot be guaranteed.

[0177] To solve the above problems, the present application provides a method. In the case where the first report sent by the terminal side is the report after actively omitting part of the CSI report, the terminal side can send a report again, such as sending a second report, to send the omitted part of the information to the network side. Thus, the network side can obtain the complete CSI report, and update the state information based on the complete CSI report. The terminal side can also update the state information based on the channel measurement result, and the state information of the dual-end AI model can be updated synchronously. Therefore, the network side can more accurately reconstruct the channel measurement result, thereby providing support for the feedback performance of the CSI report.

[0178] The method provided by the present application will be described in detail below with reference to the accompanying drawings.

[0179] FIG. 7 is a schematic flowchart of a communication method provided by an embodiment of the present application. The communication method 700 shown in FIG. 7 shows the flow of the method from the perspective of the interaction between the terminal side and the network side. The communication method 700 shown in FIG. 7 can include steps 710 to 760. Each step in the method 700 will be described in detail below.

[0180] In step 710, the terminal side obtains a CSI report, which includes a first part and a second part.

[0181] In the present application, the CSI report can be obtained by processing the channel measurement result, and the processing may, for example, include compression and quantization. For example, the terminal side can extract information from the channel measurement result, then compress the extracted information to obtain compressed data, and then quantize the compressed data to obtain the CSI report.

[0182] In a possible implementation, the CSI report is obtained by a first AI model at the terminal side from the channel measurement result. In other words, the input of the first AI model is the channel measurement result, and the output is the CSI report. In the present application, the CSI report can be an output obtained by the first AI model from the channel measurement result, or in other words, the CSI report can correspond to the same input (or the same input, or the same output) of the first AI model, which is the channel measurement result.

[0183] The first AI model is an AI model deployed at the terminal side, which can be the aforementioned encoder, and has the aforementioned function of processing the channel measurement result, such as the function of compressing and quantizing the channel measurement result. As mentioned earlier, the terminal side can include a terminal device or components deployed in the terminal device, or can include a device (such as an OTT host or a cloud server) deployed outside the terminal device or components deployed in the device outside the terminal device. The first AI model can be deployed inside the terminal device, or can be deployed outside the terminal device, such as in a device outside the terminal device. The present application does not limit this.

[0184] The CSI report in the present application can include a first part and a second part, in other words, the first part and the second part are two parts of information in the CSI report, or in other words, the CSI report is composed of the first part and the second part. For ease of understanding, a simple example is as follows: the CSI report includes a total of 1000 bits of information, the first part can be the first 700 bits of information, and the second part can be the last 300 bits of information. It should be understood that the present application does not limit which information in the CSI report is included in the first part and the second part of the CSI report, nor does it limit the amount of data included in the first part and the second part of the CSI report, nor does it limit the resources required for transmission of the first part and the second part, nor does it limit the front and rear positions of the first part and the second part in the CSI report.

[0185] It should be noted that, since the CSI report in the present application is obtained by compressing, or quantizing and compressing the channel measurement result, the CSI report in the present application is not necessarily the same as the CSI report defined in the third generation partnership project (3 rd generation partnership project, 3GPP) technical specification (TS) 38.214, such as different structures and / or different sizes. Therefore, the first part and the second part of the CSI report in the present application are also different from part 1 and part 2 of the CSI report defined in TS 38.214.

[0186] For the convenience of understanding and distinguishing, the content related to CSI reporting in TS38.214 is briefly explained here. The time domain behavior, bandwidth, report quantity, report resource, etc. of CSI reporting are defined by CSI reporting configuration (CSI-ReportConfig) in TS38.214. Among them, the time domain behavior includes periodic, semi-persistent and aperiodic, for example. The report quantity can refer to the quantity that needs to be reported in the CSI report, including but not limited to PMI, RI, CQI, CRI and layer indicator (LI), etc. TS38.214 further defines that the CSI report includes two parts, part 1 and part 2, wherein the payload size of part 1 is fixed, and the information bits of part 2 are identified in part 1, so part 1 is located before part 2 as a whole in transmission, or in other words, in a CSI report, part 1 is located before part 2 as a whole. In other words, part 1 and part 2 are transmitted by one report, or in other words, the report resources of the two are configured commonly, rather than independently, and the resource can be the report resource configured by the CSI reporting configuration described above.

[0187] The CSI report in the present application is obtained by processing the channel measurement result, which can be a channel matrix or a precoding matrix. The CSI report obtained by compressing and quantizing the channel measurement result can not include one or more of the aforementioned PMI, RI, CQI, CRI, LI, etc., but it can be understood that the above-mentioned PMI, RI, CQI, CRI, LI, etc. are obtained based on the channel matrix or the precoding matrix, so the channel measurement result can be reconstructed based on the CSI report in the present application, and one or more of the PMI, RI, CQI, CRI, LI can be further obtained based on the recovered channel measurement result.

[0188] It also needs to be explained that the first part and the second part of the CSI report in the present application are defined for the convenience of distinguishing the content in the first report and the second report in the following. When the terminal side obtains the CSI report, the CSI report can not be split into two parts, and it is not necessarily clear what the first part and the second part include.

[0189] In step 720, the terminal side sends the first report, which includes the first part of the CSI report and does not include the second part. Correspondingly, the network side receives the first report.

[0190] Since the channel state can change over time, the terminal side can adjust the MCS according to the change of the channel state. For example, in the case of good channel quality, a higher coding rate can be used, and / or a high-order modulation mode can be used, so that a higher transmission efficiency can be used for transmission; in the case of poor channel quality, a lower coding efficiency can be used, and / or a low-order modulation mode can be used, so that a lower transmission efficiency can be used for transmission. In other words, for a CSI report of a certain length, the resources required for transmission in the case of good channel quality are less than the resources required for transmission in the case of poor channel quality. The length of the CSI report is the amount of data included in the CSI report, for example, when measured by the number of bits, the length of the CSI report can be the number of bits included in the CSI report.

[0191] When the terminal side feeds back the CSI report to the network side, the terminal side can select a suitable coding rate and modulation mode according to the current channel quality, and can determine the resource size required for transmitting the CSI report based on the selected coding rate, modulation mode, and the length of the CSI report. If the resource scheduled for transmitting the CSI report is less than the actual required resource, the terminal side can discard part of the information in the CSI report to obtain a first report. In other words, the first report is a report obtained by discarding part of the information in the CSI report. The discarded part is a second part of the CSI report; the part of the CSI report that is not discarded, i.e., the part transmitted through the first report, is a first part of the CSI report. It can be understood that since the terminal side discards the second part, the first report includes the first part and does not include the second part.

[0192] It can be seen that the coding rate and / or modulation mode used by the terminal side in different channel environments can be different, and the resource size required for transmitting the CSI report can also be different, so the size of the part to be discarded in different channel environments can also be different. That is, the sizes of the first part and the second part are not fixed and can vary flexibly.

[0193] In a possible implementation, the terminal side can discard part of the information in the CSI report according to a preset rule. The preset rule can be, for example, discarding in order from back to front of the information bits in the CSI report, or discarding in order from front to back of the information bits in the CSI report, and the like. The specific content of the preset rule is not limited in the present application. In addition, the preset rule can be determined by the terminal side, can be pre-indicated by the network side through signaling, or can be pre-defined by a protocol, and the present application does not limit this.

[0194] It is to be noted that the discarding of the second part at the terminal side can be during the obtaining of the first report, and does not mean that the terminal side deletes the second part from the cache. In this application, since the terminal side discards the second part when sending the first report, the terminal side can cache the second part, or the entire CSI report (i.e., including the first part and the second part) locally, so as to send the second part through the second report when receiving the scheduling of the network side thereafter.

[0195] In step 730, the terminal side sends the second report, which includes the second part of the CSI report. Accordingly, the network side receives the second report.

[0196] In order to enable the network side to obtain the complete CSI report, so as to be able to update the state information of the AI model with the terminal side, the terminal side can also send the second report to the network side. Since the first report sent by the terminal side does not include the second part, the terminal side needs to include the second part in the second report. However, this application does not limit this. The second report includes the second part, i.e., the part of information discarded when the first report is sent can be sent through the second report.

[0197] A possible design is that the second report can include the second part and the first part, i.e., the second report is the CSI report. In this design, the terminal side sends the second report, which can also be replaced by the terminal side sending the CSI report. In this way, by sending the first part and the second part through the second report, the network side can perform merging processing based on the first part in the first report and the second report, thereby facilitating to improve the receiving performance and more facilitating the network side to obtain the accurate and complete CSI report. In this design, the terminal side can cache the CSI report before the second report is sent.

[0198] Another possible design is that the second report can include the second part and not include the first part. The second report including the second part and not including the first part can avoid resource occupation caused by repeated sending of the first part, and thus can save resources. In this design, the terminal side can cache the second part or cache the CSI report before the second report is sent.

[0199] In summary, the terminal side sends the first part of the CSI report through the first report in step 720, and sends the second part of the CSI report through the second report in step 730, or sends the first part and the second part. Through the sending of the first report and the second report, the network side can receive the complete CSI report. In other words, the purpose of the terminal sending the first report and the second report is to send the CSI report to the network side completely. Therefore, the sending of the first report can also be understood as the initial transmission of the CSI report, and the sending of the second report can also be understood as the retransmission of the CSI report, the first report can also be referred to as an initial transmission report, and the second report can also be referred to as a retransmission report.

[0200] Optionally, the method further includes step 740: the terminal side updates the state information of the first AI model based on the channel measurement result.

[0201] From the foregoing processing flow shown in FIG. 6, it can be seen that the first AI model on the terminal side can update the state information while outputting the CSI report based on the channel measurement result, and output the updated state information, which is obtained based on the input channel measurement result this time. Therefore, the process of the first AI model outputting the CSI report and the process of updating the state information can be considered as synchronous execution. Although steps 710 and 740 are shown as two steps in the figure, the execution sequence of the two steps should not be limited. For example, steps 710 and 740 can be executed synchronously, as shown above; steps 710 and 740 can also be executed asynchronously, for example, the terminal side updates the state information based on the channel measurement result after sending the first report and the second report, that is, step 740 can be executed after step 710.

[0202] Since the terminal side can update the state information of the first AI model based on the channel measurement result obtained each time the channel is measured, more accurate channel compression can be achieved by mining the time domain correlation characteristics of historical channel measurement results and current channel measurement results, and the problem of channel aging can be solved, while the overhead of feedback channel measurement results can be reduced.

[0203] Optionally, the method further includes step 750: the network side updates the state information of the second AI model based on the first part and / or the second part.

[0204] After receiving the first report and the second report, the network side can obtain the first part of the CSI report from the first report, the second part of the CSI report from the second report, or the first part and the second part of the CSI report. The network side can combine the information obtained from the first report and the second report respectively to obtain the received CSI report.

[0205] Corresponding to the terminal side, the network side can take the received CSI report as the input of the second AI model, so as to update the state information of the second AI model. In this way, the network side can take the complete CSI report as the input to update the state information, in other words, the network side and the terminal side can update the state information based on the same or corresponding input, that is, the network side and the terminal side can update the state information synchronously.

[0206] It can be understood that, due to the first report and the second report in the transmission process, packet loss may also occur, and the terminal side defaults that the first report and the second report are transmitted to the network side without retransmission due to the unawareness of the occurrence of the packet loss. In this case, the network side can update the state information of the second AI model based on the received first report and / or second report. For example, if the first report is received by the network side and the second report is lost, the network side can obtain the first part of the CSI report from the first report and update the state information of the second AI model based on the first part. For another example, if the first report is lost and the second report is received by the network side, if the second report includes the second part of the CSI report and does not include the first part, the network side can obtain the second part of the CSI report from the second report and update the state information of the second AI model based on the second part; or, if the second report includes the first part and the second part of the CSI report, the network side can obtain the first part and the second part of the CSI report from the second report and update the state information of the second AI model based on the first part and the second part.

[0207] In summary, in order to send the complete CSI report to the network side, the terminal side sends the first part and the second part of the CSI report through the first report and the second report respectively, avoids the situation that the network side receives the first part but does not receive the second part due to the loss of a part of information as much as possible, and further avoids the network side updating the state information without obtaining the complete CSI report. Therefore, it is helpful to update the state information synchronously by the network side and the terminal side, to synchronously mine the time domain related features of the channel, and further to help the network side accurately reconstruct the channel measurement result and improve the communication performance.

[0208] It should be noted that the network side can determine by itself whether the terminal side discards part of the information when sending the CSI report (or in other words, determine that the first report sent by the terminal side is not a complete CSI report). For example, the network side and the terminal side can determine whether to discard part of the information of the CSI report based on the same discarding rule. The discarding rule may, for example, be predefined by a protocol. For another example, the network side can also determine whether the terminal side discards part of the information of the CSI report according to the length of the received first report and the length of the CSI report. The length of the CSI report can be understood as the length of the CSI report that should be reported in advance, such as the length of the CSI report predefined by a protocol or preconfigured by the network side through signaling (such as CSI reporting configuration). If the network side detects that the length of the first report is shorter than the length of the CSI report that should be reported, it can be considered that the terminal side discards part of the information of the CSI report. Of course, the terminal side can also actively report to the network side whether part of the information is discarded when sending the CSI report. The present application does not limit this.

[0209] When the network side determines that the terminal side discards part of the information when sending the CSI report, it can be determined that the terminal side will send the second report, and therefore the network side can cache the first report locally after receiving the first report, and perform the above step 750 after receiving the second report.

[0210] Optionally, the method further includes step 760: the network side reconstructs the channel measurement result based on the first part and / or the second part to obtain a recovered channel measurement result.

[0211] In addition to updating the state information of the second AI model, the network side can also reconstruct the channel measurement result based on the received first report and / or the second report. Similar to the terminal side, the second AI model of the network side can reconstruct the channel measurement result based on the received first part and / or the second part, update the state information while reconstructing the channel measurement result, and obtain updated state information, which is obtained based on the input first part and / or the second part this time. Therefore, the process of reconstructing the channel measurement result by the second AI model and the process of updating the state information can be considered as being executed synchronously. Although steps 750 and 760 are shown as two steps in the figure, the execution sequence of the two steps should not be limited. For example, the steps 750 and 760 can be executed synchronously, as shown above; the steps 750 and 760 can also be executed asynchronously, for example, the network side can reconstruct the channel measurement result based on the first part in the first report after receiving the first report; and update the state information based on the first part and the second part after receiving the second report, that is, step 760 can be executed before step 750, for example, step 760 can be executed after step 720, and step 760 can specifically be that the network side reconstructs the channel measurement result based on the first part, and step 750 can be executed after step 730.

[0212] Based on the above technical solutions, the terminal side transmits the first report and the second report, which is conducive to the network side receiving a complete CSI report, and further conducive to the network side performing subsequent steps based on the complete CSI report, such as updating the state information of the AI model. In this application, the terminal side can update the state information of the first AI model based on the channel measurement result, and if the network side updates the state information of the second AI model based on the first report and the second report, that is, updates the state information based on the complete CSI report, and the CSI report is obtained by processing the channel measurement result by the first AI model, therefore, the network side can also update the state information based on the same or corresponding input as the terminal side, that is, can synchronously mine the time domain correlation characteristics of the channel. Therefore, it is helpful for the network side to accurately reconstruct the channel measurement result, and further conducive to improving the communication performance. In addition, by mining the time domain correlation characteristics of the historical channel measurement result and the current channel measurement result to realize more accurate channel compression, the problem of channel aging can be solved, and the overhead of feeding back the channel measurement result can be reduced.

[0213] In a possible implementation, the content of the second report is predefined by a protocol. For example, the protocol predefines that the second part is included in the second report and the first part is not included, or the protocol predefines that the first part and the second part are both included in the second report. By predefining the content of the second report by the protocol, the terminal side and the network side can generate and parse the second report based on the corresponding processing manners, and signaling overhead caused by the network side indicating the content of the second report to the terminal side can be saved.

[0214] In another possible implementation, the content of the second report is preconfigured by the network side through signaling. For example, the network side indicates the content of the second report through signaling when the first AI model on the terminal side is registered, or when the second AI model on the network side is interfaced with the first AI model on the terminal side, or when the terminal device is registered, or for example, the network side can indicate the content of the second report through signaling when it is determined that the terminal side discards part of the information of the CSI report.

[0215] Optionally, the method further includes that the network side sends second indication information used to indicate the content of the second report. Correspondingly, the terminal side receives the second indication information.

[0216] For example, the second indication information can indicate the content of the second report by bits “0” and “1”, and the content of the second report indicated by the bits “0” and / or “1” can be predefined, or preconfigured by the network side through high-layer signaling (such as a radio resource control (RRC) message), for example. For example, the protocol predefines or the network side preconfigures the following relationship through high-layer signaling: the bit “0” indicates that the content of the second report is the second part and the first part is not included, or the content of the second report is only the second part; and / or the bit “1” indicates that the content of the second report is the first part and the second part.

[0217] A possible design is that the second indication information is physical layer signaling, such as downlink control information (DCI). The network side can flexibly adjust the content of the second report according to the usage of resources.

[0218] In this application, the first report and the second report are reports sent by the terminal side through two sending steps in sequence, and therefore the transmission resources of the first report and the second report are different. For convenience of distinguishing and description, the resource used to transmit the first report is referred to as the first resource, the resource used to transmit the second report is referred to as the second resource, and the second resource is located after the first resource in the time domain.

[0219] It should be noted that, in this paper, the first resource is referred to as the resource for transmitting the first report for the convenience of distinguishing the first resource and the second resource. In fact, the first resource is not the resource scheduled for transmitting the first report, but the resource configured for CSI reporting. Or, the first resource is not configured for the first report, but for the reporting of the CSI report.

[0220] In a possible implementation, the first resource can be a resource for transmitting the CSI report configured by the CSI reporting configuration of the network side in advance, for example, can be periodic (such as configured by an RRC message), aperiodic (such as triggered by a downlink control information (DCI)), or semi-persistent (such as configured by an RRC message and activated by a medium access control (MAC)-control element (CE) or a downlink control information (DCI)); the second resource can be a resource scheduled for the second report by the network side after receiving the first report, or the second resource can also be a resource for transmitting the CSI report configured by the CSI reporting configuration of the network side in advance, without limitation.

[0221] Optionally, the method further includes: the network side sending first indication information, the first indication information being used for indicating the second resource. Correspondingly, the terminal side receives the first indication information.

[0222] A possible design is that the first indication information is physical layer signaling, such as a DCI. After receiving the first report, the network side can estimate the size of the second report according to the length of the CSI report and the length of the first report in the case that the terminal discards part of the information of the CSI report, and then schedule the second resource for the second report, the size of the second resource being sufficient for transmitting the second report.

[0223] It should be understood that the first indication information and the second indication information can be carried in the same signaling, such as carried in the same DCI, or can be carried in different signaling, such as carried in different DCIs, or the second indication information is carried in an RRC message and the first indication information is carried in a DCI. The present application does not limit this.

[0224] In order to better understand the scheme, FIG. 8 shows the flow of the method through the timing relationship. As an example, FIG. 8 assumes that the first resource and the second resource are both indicated by DCIs, the first resource is indicated by DCI 1, and the second resource is indicated by DCI 2.

[0225] As shown in FIG. 8, at T0, the network side triggers the terminal side to report a CSI report on a first resource through DCI 1, and the starting position of the first resource in the time domain is T1. Based on the DCI 1, the terminal side inputs the channel measurement result and the state information into the first AI model to obtain the output CSI report. In a case where the terminal side determines that the size of the first resource is insufficient to transmit the entire CSI report, the terminal side can discard the second part of the CSI report to obtain a first report. At T1, the terminal side sends the first report to the network side through the first resource. After determining that the terminal side discards part of the CSI report, the network side can instruct the terminal side to send a second report on a second resource at T2 through DCI 2, and can further indicate the content of the second report, and the starting position of the second resource in the time domain is T3. As shown in a) in the figure, the DCI 2 indicates that the second part is to be supplemented, and the terminal side can send the second report at T3, wherein the second report includes the second part and does not include the first part; as shown in b) in the figure, the DCI 2 indicates that the first part and the second part are to be supplemented, and the terminal side can send the second report at T3, wherein the second report includes the first part and the second part.

[0226] The second resource and the first resource can be discontinuous in the time domain. Alternatively, the second resource and the first resource are offset in the time domain by a time length less than or equal to a threshold value. The threshold value can be determined based on the storage capability of the terminal side and / or the storage capability of the network side, for example.

[0227] As described above, in a case where the terminal side discards part of the CSI report, the terminal side can cache the second part of the CSI report or the CSI report, and in a case where the network side receives the first report, the network side can cache the first report (or the first part of the CSI report). Therefore, the second resource should not be later than the time when the data in the cache is cleared in the time domain.

[0228] In a case where the terminal side caches the second part of the CSI report or caches the CSI, the content of the second report can be used to determine. If the content of the second report is the second part of the CSI report, the terminal side can cache the second part of the CSI report or cache the CSI report; if the content of the second report is the CSI report, the terminal side can cache the CSI report. In the following, for the convenience of description, the data cached by the terminal side is referred to as the terminal side cache data. It can be understood that the terminal side cache data can refer to the CSI report or the second part of the CSI report.

[0229] The time when the data in the cache is cleared is related to the storage capability of the device. Taking a terminal device that caches CSI reports as an example, the storage space of the terminal device is certain, and according to the reporting period of the CSI report and the length of the CSI report, the upper limit of the CSI reports that can be stored by the terminal device can be determined. For example, the storage space of the terminal device can store a data amount of 600 bits, and the length of the CSI report is 60 bits, so the storage space of the terminal device can cache 10 CSI reports (i.e., 10 reporting periods of CSI reports). In other words, the upper limit of the duration for which the CSI report can be stored in the terminal device is 10 reporting periods. Since the reporting period of the CSI report can be determined by CSI reporting configuration, the upper limit of the duration for which the CSI report can be stored by the terminal device can also be determined. For example, the reporting period of one CSI report is 10 milliseconds (ms), so the upper limit of the duration for which the CSI report can be stored by the terminal device in this example is 100 ms.

[0230] Since the terminal-side cached data is different, the size of the storage space occupied can also be different. For example, the CSI report can need to occupy a larger storage space than the second part of the CSI report, so the upper limit of the duration for which the CSI report can be stored by the terminal device and the upper limit of the duration for which the second part of the CSI report can be stored by the terminal device can also be different. In one possible case, the former is less than the latter.

[0231] To ensure that the second resource is not later than the time when the cached data is cleared in the time domain, both the time when the first report is cleared from the network-side cache by the network side and the time when the terminal-side cached data is cleared from the terminal-side cache by the terminal side need to be considered. Therefore, the threshold value should be less than the smaller of the upper limit of the duration for which the first report can be stored by the network device and the upper limit of the duration for which the CSI report or the second part of the CSI report can be stored by the terminal device.

[0232] Generally, the devices on the network side, such as network devices and intelligent network elements, have relatively large storage spaces, and the devices on the terminal side, such as OTT hosts or cloud servers, also have relatively large storage spaces, but the storage space of the terminal device is relatively limited. Therefore, the upper limit of the duration for which the terminal-side cached data can be stored by the terminal device is often less than the upper limit of the duration for which the first report can be stored by other devices (including devices on the terminal side except the terminal device and devices on the network side). Therefore, the threshold value can be determined based on the storage capability of the terminal device.

[0233] Optionally, the method further includes: the terminal side sending capability information to the network side, the capability information being used to indicate the storage capability of the terminal device. Correspondingly, the network side receives the capability information from the terminal side.

[0234] The terminal side can indicate, by the capability information, an upper limit of a time length that the terminal device can store the terminal-side buffered data, such as indicating a specific time length or indicating a number of reporting periods corresponding to the specific time length; the terminal side can also indicate, by the capability information, a size of a storage space of the terminal device, so as to facilitate the network side to determine, based on the size of the storage space, the upper limit of the time length that the terminal device can store the terminal-side buffered data.

[0235] After determining, based on the capability information, the upper limit of the time length that the terminal device can store the terminal-side buffered data, the network side can determine the upper limit as the threshold value, or can perform a simple mathematical transformation on the upper limit to obtain the threshold value, and the mathematical transformation can be, for example, a combination of one or more of the following mathematical operations: adding a coefficient, subtracting a coefficient, multiplying a coefficient, or dividing by a coefficient, etc., without limitation.

[0236] The network side can determine the position of the second resource in the time domain based on the threshold value, and then schedule the second resource for the second report.

[0237] It should be understood that the terminal side can send the capability information to the network side before the network side schedules the second resource for the terminal side, or can send the capability information to the network side when the first AI model is registered, or when the second AI model of the network side is interfaced with the first AI model of the terminal side, or when the terminal device is registered, or when the terminal side discards part of the CSI report. The timing of sending the capability information by the terminal side is not limited in the present application.

[0238] In order to better understand the scheme, FIG. 9 shows the flow of the method through the timing relationship. As an example, FIG. 9 assumes that both the first resource and the second resource are indicated by DCI, the first resource is indicated by DCI 1, and the second resource is indicated by DCI 2.

[0239] FIG. 9 and FIG. 8 have the same operations at time T0 and time T1, and the related description of FIG. 8 can be referred to, and will not be repeated. After determining that the terminal side discards part of the CSI report, the network side can indicate, at time T2, by DCI 2, the terminal side to send the second report on the second resource, and can further indicate the content of the second report, and the starting position of the second resource in the time domain is time T3. Unlike FIG. 8, the position of the second resource in the time domain scheduled by the network side for the second report is limited by the storage capability of the terminal device, and the time length between the T3 time and the T1 time (i.e., the starting position of the first resource in the time domain) is less than or equal to the threshold value, which is, for example, the upper limit of the time length that the terminal device can store the terminal-side buffered data.

[0240] To avoid confusion, the case where the DCI 2 indicates the retransmission of the second part is shown in FIG. 9, i.e., corresponding to a) in FIG. 8. It is assumed that the upper limit of the time length that the terminal side can store the second part is M1, and the threshold value is equal to the upper limit M1. This means that the terminal side will clear the second part in the cache at the time of (T1+M1) (hereinafter referred to as the time of T4). Therefore, the time of T3 shown in FIG. 9 should not be later than the time of T4, that is, the time length of the offset between the time of T3 and the time of T1 should be less than or equal to M1. As shown in the figure, the time length of the offset between the time of T3 and the time of T1 is B1, and B1

[0241] It should be noted that FIG. 8 and FIG. 9 only show the operations of the network side or the terminal side corresponding to different times for the purpose of understanding, and the area occupied by each block in the figure does not represent the size of the resource and the length occupied in the time domain. For example, the transmission resource of the DCI 2 at the time of T2 does not coincide with the time of T3; the second resource starting from the time of T3 also does not reach the time of T4 in the length occupied in the time domain.

[0242] Based on the above scheme, the terminal side reports the storage capacity of the terminal device through the capability information, so that the network side can take into account the storage capacity of the terminal device when scheduling the second resource for the second report, so that the second report can be sent out through the second resource before it is cleared from the storage space of the terminal, thereby more effectively ensuring that the terminal side sends the first report and the second report to the network side.

[0243] As mentioned above, the first AI model can be deployed at the terminal side, for example, can be deployed inside the terminal device, or can be deployed in a device outside the terminal device, such as an OTT host or a cloud server; the second AI model can be deployed at the network side, for example, can be deployed inside the network device, or can be deployed in a device outside the network device, such as an intelligent network element. The specific flow of the above method 700 under the architecture that the first AI model is deployed inside the terminal device and the second AI model is deployed inside the network device will be described below in combination with FIG. 10; the specific flow of the above method 700 under the architecture that the first AI model is deployed outside the terminal device and the second AI model is deployed outside the terminal device will be described below in combination with FIG. 11. It should be understood that FIGS. 10 and 11 are only examples, and more possible flows can be derived based on FIGS. 10 and 11, such as the first AI model is deployed inside the terminal device and the second AI model is deployed outside the network device, or the first AI model is deployed outside the terminal device and the second AI model is deployed inside the network device, or the first AI model is split into multiple sub-models and deployed inside more devices at the terminal side, or the second AI model is split into multiple sub-models and deployed inside more devices at the network side, and the like, which will not be listed.

[0244] It should also be understood that the method shown in FIGS. 10 and 11 is an example given based on the method 700 shown in FIG. 7, and the same or similar steps as the method 700, as well as the same terms in the method 700, can refer to the related description above, which will not be described again.

[0245] Referring to FIG. 10, the communication method 1000 shown in FIG. 10 shows the flow of the method from the perspective of the interaction between the terminal device and the network device. The communication method 1000 shown in FIG. 10 includes steps 1001 to 1010.

[0246] In step 1001, the network device sends a reference signal. Correspondingly, the terminal device receives the reference signal.

[0247] Exemplarily, the network device can send a CSI-RS.

[0248] In step 1002, the terminal device performs channel measurement based on the reference signal to obtain a channel measurement result.

[0249] The terminal device can estimate the channel based on the received reference signal to obtain estimated channel information, such as a channel matrix. The terminal device can also obtain the eigenvectors of the channel matrix based on the eigenvalue decomposition of the channel matrix, and then obtain a precoding matrix.

[0250] It should be understood that more specific implementations of the network device sending the reference signal and the terminal device performing channel measurement based on the reference signal can refer to the prior art, which will not be described in detail herein.

[0251] In step 1003, the terminal device inputs the channel measurement result into the first AI model to obtain the CSI report.

[0252] In this embodiment, the first AI model is deployed in the terminal device. For example, the terminal device can input the obtained channel measurement result into the first AI model through an internal channel to compress and quantize the channel measurement result by the first AI model, and obtain the CSI report.

[0253] It should be understood that steps 1001 to 1003 correspond to step 710 in method 700, and illustrate one possible implementation of obtaining the CSI report at the terminal side. For more detailed description of the CSI report, please refer to the related description in step 710 of method 700, which will not be repeated here.

[0254] In step 1004, the terminal device inputs the channel measurement result into the first AI model to update the state information.

[0255] The terminal device can input the obtained channel measurement result into the first AI model through an internal channel. The first AI model can update the previously obtained state information based on the received channel measurement result to obtain the updated state information.

[0256] It should be understood that step 1004 corresponds to step 740 in method 700, and please refer to the related description in step 740 of method 700, which will not be repeated here. It should also be understood that step 1004 and step 1003 can be executed synchronously or separately, which is not limited in the present application. One possible implementation is that the terminal device can input the channel measurement result into the first AI model after obtaining the channel measurement result, so that the first AI model performs compression and state information update based on the same input channel measurement result.

[0257] In step 1005, the terminal device sends a first report to the network device, where the first report includes the first part of the CSI report and does not include the second part. Correspondingly, the network device receives the first report from the terminal device.

[0258] It should be understood that step 1005 corresponds to step 720 in method 700, and please refer to the related description in step 720 of method 700, which will not be repeated here.

[0259] In step 1006, the terminal device sends capability information to the network device, where the capability information is used to indicate the storage capability of the terminal device. Correspondingly, the network device receives the capability information from the terminal device.

[0260] It should be understood that step 1006 corresponds to the steps of method 700 related to the sending and receiving of capability information, and reference can be made to the relevant description in method 700, which will not be repeated here.

[0261] It should also be understood that step 1006 can be performed before step 1007, or before any one of steps 1001 to 1005, such as when the first AI model is registered in the network, or when the second AI model on the network side is docked with the first AI model on the terminal side, or when the terminal device is registered in the network, or when the terminal side discards part of the information of the CSI report, etc. The timing of the terminal side sending capability information is not limited in the present application.

[0262] In step 1007, the network device sends signaling, such as DCI, to the terminal device, which is used to indicate the second resource and the content of the second report.

[0263] After determining that the terminal device discards part of the information of the CSI report, the network device sends DCI to the terminal device to schedule the second resource for the terminal device to send the second report, and indicates the content of the second report.

[0264] The signaling in step 1007 can correspond to the first indication information and the second indication information in method 700. The signaling, such as DCI, can be regarded as an example in which the first indication information and the second indication information in method 700 above are carried in the same signaling. In addition, the time length of the second resource for transmitting the second report and the first resource for transmitting the first report offset in the time domain can also be less than or equal to a threshold value, which can be determined according to the storage capability of the terminal device. More detailed descriptions about the first indication information, the second indication information, the time length of the first resource and the second resource offset in the time domain, the storage capability of the terminal device, etc. can be referred to the relevant description in method 700, which will not be repeated here.

[0265] In step 1008, the terminal device sends the second report to the network device, and the second report includes the second part of the CSI report. Correspondingly, the network device receives the second report from the terminal device.

[0266] It should be understood that step 1008 corresponds to step 730 in method 700, and reference can be made to the relevant description in step 730 of method 700, which will not be repeated here.

[0267] In step 1009, the network device inputs the first part and / or the second part into the second AI model to obtain the recovered channel measurement result.

[0268] In this embodiment, the second AI model is deployed in the network device. For example, the network device can input the received first report and / or the second report into the second AI model through an internal channel, or can also extract the first part in the first report and / or the second part in the second report (or the first part and the second part) and input them into the second AI model, so as to reconstruct the channel measurement result based on the input information by the second AI model.

[0269] It should be understood that step 1009 corresponds to step 760 in method 700, and reference can be made to the related description in step 760 of method 700, which will not be repeated here.

[0270] In step 1010, the network device inputs the first part and / or the second part into the second AI model to update the state information.

[0271] The network device can input the received first report and / or the second report into the second AI model through an internal channel, or can also input the first part in the received first report and / or the second part in the second report into the second AI model. The second AI model can update the previously obtained state information based on the first part and / or the second part to obtain updated state information.

[0272] It should be understood that step 1010 corresponds to step 750 in method 700, and reference can be made to the related description in step 750 of method 700, which will not be repeated here. It should also be understood that step 1010 and step 1009 can be executed synchronously or separately, which is not limited in the present application. For example, in the flowchart shown in FIG. 10, after receiving the first report, the network device can start to reconstruct the channel measurement result based on the information in the first report and update the state information; after receiving the second report, the network device can continue to reconstruct the channel measurement result based on the information in the second report and continue to update the state information. It can be understood that the channel measurement result and the state information reconstructed by the network device based on the first report are incomplete, and the updated state information can not be used as the input for the next channel measurement result reconstruction. The network device can continue to reconstruct the channel measurement result and update the state information after receiving the second report, and the updated state information is obtained based on the complete CSI report and can be used as the input for the next channel measurement result reconstruction. Although steps 1009 and 1010 are shown after step 1008 in the figure, it can be understood that steps 1009 and 1010 can be executed before step 1008, such as after step 1005, but completed after step 1008; or can be executed after step 1008, which is not limited in the present application.

[0273] Based on the above technical solution, the terminal device sends the first report and the second report, which is beneficial for the network device to receive the complete CSI report, and further beneficial for the network device to perform subsequent steps such as updating of the AI model state information based on the complete CSI report. In this application, the terminal device can update the state information of the first AI model based on the channel measurement result, and if the network device updates the state information of the second AI model based on the first report and the second report, i.e., can update the state information based on the complete CSI report, and the CSI report is obtained by processing the channel measurement result by the first AI model, therefore, the network device can also update the state information based on the same or corresponding input as the terminal device, i.e., can synchronously mine the time-domain correlation features of the channel. Thus, it is helpful for the network device to accurately reconstruct the channel measurement result, and further beneficial for improving the communication performance. In addition, by mining the time-domain correlation features of the historical channel measurement result and the current channel measurement result to realize more accurate channel compression, the problem of channel aging is counteracted, and the overhead of feeding back the channel measurement result can be reduced.

[0274] It should be understood that in the communication method 1000 shown in FIG. 10, the terminal device can also be replaced by an OTT host or a cloud server, and the network device can also be replaced by a smart network element. For the sake of brevity, the details are not repeated in the drawings.

[0275] Referring to FIG. 11, the communication method 1100 shown in FIG. 11 shows the flow of the method from the perspective of interaction between an OTT host or a cloud server (hereinafter referred to as OTT), a terminal device, a network device and a smart network element. Among them, the first AI model is deployed in the OTT, and the second AI model is deployed in the smart network element. The communication method 1100 shown in FIG. 11 includes steps 1101 to 1115. It should be understood that in the flow shown in method 1100, steps 1101, 1102, 1106, 1110 to 1112 are respectively the same as steps 1001, 1102, 1104, 106 to 1108 in method 1000. Please refer to the related description of each step in method 1000, which will not be repeated. The following focuses on the steps different from method 1000.

[0276] In step 1101, the network device sends a reference signal. Correspondingly, the terminal device receives the reference signal.

[0277] In step 1102, the terminal device performs channel measurement based on the reference signal to obtain a channel measurement result.

[0278] In step 1103, the terminal device sends the channel measurement result to the OTT. Correspondingly, the OTT receives the channel measurement result from the terminal device.

[0279] Since the first AI model is deployed in the OTT, the terminal device can send the channel measurement result obtained by measurement to the OTT.

[0280] In step 1104, the OTT inputs the channel measurement result into the first AI model to obtain the CSI report.

[0281] For example, the OTT can input the channel measurement result into the first AI model through an internal channel to update the state information obtained last time based on the received channel measurement result by the first AI model to obtain updated state information.

[0282] It should be understood that the specific process of step 1104 is similar to that of step 1003 in method 1000, except that the terminal device is replaced by the OTT, and thus the relevant description in step 1103 of method 1000 can be referred to and will not be repeated.

[0283] In step 1105, the OTT inputs the channel measurement result into the first AI model to update the state information.

[0284] For example, the OTT can input the channel measurement result into the first AI model through an internal channel to update the state information based on the channel measurement result by the first AI model.

[0285] It should be understood that step 1105 is similar to step 1009 in method 1000, except that the terminal device is replaced by the OTT, and thus the relevant description in step 1004 of method 1000 can be referred to and will not be repeated. In addition, step 1105 and step 1104 can be executed synchronously or asynchronously, which is not limited in the present application.

[0286] In step 1106, the OTT sends the CSI report to the terminal device. Correspondingly, the terminal device receives the CSI report from the OTT.

[0287] The OTT sends the CSI report to the terminal device so as to send the CSI report to the network device by the terminal device.

[0288] It should be understood that steps 1101 to 1103 and step 1106 can correspond to step 710 in method 700, and can be regarded as another possible implementation manner of obtaining the CSI report on the terminal side. More detailed description of the CSI report can be referred to the relevant description in step 710 of method 700, and will not be repeated.

[0289] In step 1107, the terminal device sends a first report to the network device, the first report including a first part of the CSI report and not including a second part. Correspondingly, the network device receives the first report from the terminal device.

[0290] In step 1108, the network device sends the first part of the CSI report to the intelligent network element.

[0291] Since the second AI model is deployed in the intelligent network element, the network device can send the received first part of the CSI report to the intelligent network element. The network device can directly forward the received first report to the intelligent network element, or can also send the first part of the CSI report obtained from the first report to the intelligent network element, without limitation.

[0292] In step 1109, the terminal device sends capability information to the network device, and the capability information is used to indicate the storage capability of the terminal device. Correspondingly, the network device receives the capability information from the terminal device.

[0293] In step 1110, the network device sends signaling such as DCI to the terminal device, and the signaling is used to indicate the second resource and the content of the second report. Correspondingly, the terminal device receives the signaling from the network device.

[0294] In step 1111, the terminal device sends the second report to the network device, and the second report includes the second part of the CSI report. Correspondingly, the network device receives the second report from the terminal device.

[0295] In step 1112, the network device sends the second part of the CSI report to the intelligent network element. Correspondingly, the intelligent network element receives the second part of the CSI report from the network device.

[0296] The intelligent network element can input the second part of the CSI report into the second AI model through an internal channel, so as to update the state information based on the first part and / or the second part through the second AI model.

[0297] It should be noted that the second report can include the second part of the CSI report, and does not include the first part; or can include the first part and the second part of the CSI report. Therefore, in the case where the second report includes the first part of the CSI report, the network device can also send the first part to the intelligent network element in step 1113.

[0298] The network device can directly forward the received second report to the intelligent network element, or can also send the second part (or the first part and the second part) of the CSI report obtained from the second report to the intelligent network element, without limitation.

[0299] In step 1113, the intelligent network element inputs the first part and / or the second part into the second AI model to obtain the recovered channel measurement result.

[0300] For example, the intelligent network element can input the first part and / or the second part of the CSI report into the second AI model through an internal channel to reconstruct the channel measurement result based on the input information by the second AI model.

[0301] It should be understood that step 1113 is similar to step 1009 in method 1000, except that the network device is replaced by the intelligent network element, and thus the relevant description in step 1109 of method 1000 can be referred to, and will not be repeated here.

[0302] In step 1114, the intelligent network element sends the reconstructed channel measurement result to the network device.

[0303] The intelligent network element sends the reconstructed channel measurement result to the network device, so that the network device determines one or more of the MCS, precoding, etc. according to the reconstructed channel measurement result.

[0304] In step 1115, the intelligent network element inputs the first part and / or the second part into the second AI model to update the state information.

[0305] For example, the intelligent network element can input the first part and / or the second part into the second AI model through an internal channel to update the state information by the second AI model based on the first part and / or the second part.

[0306] It should be understood that step 1115 is similar to step 1010 in method 1000, except that the network device is replaced by the intelligent network element, and thus the relevant description in step 1010 of method 1000 can be referred to, and will not be repeated here.

[0307] It should also be understood that steps 1115 and 1113 can be executed synchronously or asynchronously, and the present application does not limit this.

[0308] Based on the above technical solution, the terminal side transmits the first report and the second report, which is conducive to the network side receiving complete CSI reports, and further conducive to the network side performing subsequent steps based on the complete CSI reports, such as updating the state information of the AI model. In this application, the terminal side can update the state information of the first AI model based on the channel measurement result. If the network side updates the state information of the second AI model based on the first report and the second report, that is, the state information can be updated based on the complete CSI report, and the CSI report is obtained by processing the channel measurement result by the first AI model, therefore, the network side can also update the state information based on the same or corresponding input as the terminal side, that is, the time domain correlation characteristics of the channel can be mined synchronously. Therefore, it is helpful for the network side to accurately reconstruct the channel measurement result, and further conducive to improving the communication performance. In addition, by mining the time domain correlation characteristics of the historical channel measurement result and the current channel measurement result, more accurate channel compression is realized to resist channel aging, and the overhead of feeding back the channel measurement result can be reduced.

[0309] In addition, the embodiment shows a possible implementation process under the architecture that the first AI model and the second AI model are deployed outside the terminal device and the network device, which makes the method provided by the present application not limited to be implemented between the terminal device and the network device, and makes the scene to which the present application is applied more flexible.

[0310] In some cases, after the terminal side transmits the CSI report, the CSI report may be lost, and the terminal side does not know the occurrence of the loss, and still continues to update the parameters of the first AI model based on the channel measurement result. The network side cannot update the parameters of the second AI model because it does not receive the CSI report. Therefore, the terminal side and the network side are not synchronized in updating the state information, and the channel measurement result reconstructed by the network side may not be accurate enough, so that the feedback performance of the CSI report cannot be guaranteed.

[0311] The present application also provides a method, in which the network side sends signaling to the terminal side to instruct the terminal side to send the second report in the case that the first report from the terminal side is not received. Therefore, the terminal side can transmit part or all of the information in the CSI report to the network side through the second report in the case that the loss is unknown. This is conducive to the network side reconstructing the channel measurement result, and also conducive to the terminal side and the network side synchronously updating the state information of the AI model, and further conducive to the network side more accurately reconstructing the channel measurement result, and providing support for the feedback performance of the CSI report.

[0312] It is noted that, unlike the method embodiments described above, in the embodiments shown below, the first report can be a first part of the CSI report, or can be the CSI report (i.e., including the first part and the second part); the second report in the present embodiments can be the CSI report, or can be a first part of the CSI report.

[0313] FIG. 12 is a schematic flowchart of a communication method according to another embodiment of the present application. The communication method 1200 shown in FIG. 12 shows the flow of the method from the perspective of the interaction between the terminal side and the network side. The communication method 1200 shown in FIG. 12 can include steps 1210 to 1260. The various steps in the method 1200 are described in detail below.

[0314] In step 1210, the terminal side transmits a first report, which includes a CSI report or a first part of the CSI report.

[0315] The CSI report can be obtained by processing the channel measurement results, as in the CSI report in the method 700. For more detailed descriptions of the CSI report and the obtaining of the CSI report, please refer to the relevant descriptions in step 710 of the method 700, the relevant descriptions of steps 1001 to 1003 of the method 1000, and the relevant descriptions of steps 1101 to 1105 of the method 1100, which are not repeated here.

[0316] The terminal side can determine whether to discard part of the information in the CSI report according to the resources scheduled for transmitting the CSI report after obtaining the CSI report. The resources scheduled for transmitting the CSI report can be the reporting resources configured by the CSI reporting configuration, i.e., the same as the first resources in the method embodiments above. For more detailed descriptions of the first resources, please refer to the relevant descriptions above, which are not repeated here.

[0317] In the present embodiment, the first report transmitted by the terminal side is packet lost, i.e., the network side does not receive the first report.

[0318] In step 1220, the network side transmits third indication information to the terminal side, the third indication information being used to indicate the content of the second report. Correspondingly, the terminal side receives the third indication information from the network side.

[0319] The network side can not receive the first report on the CSI reporting resources, and can then instruct the terminal side to transmit the second report through the third indication information, and can indicate the content of the second report through the third indication information. Exemplarily, the content of the second report can be a first part of the CSI report, or the content of the second report can be a first part and a second part of the CSI report, i.e., the second report is the CSI report. In other words, the third indication information can instruct the terminal side to transmit part or all of the information of the CSI report.

[0320] It should be understood that the third indication information and the second indication information in the method 700 have the same function, both of which are used to indicate the content of the second report, only the indicated content of the second report can be different. Therefore, the relevant description of the second indication information can be referred to for understanding, and will not be described again.

[0321] In step 1230, the terminal side sends the second report to the network side based on the third indication information. Correspondingly, the network side receives the second report from the terminal side.

[0322] The terminal side can send the second report to the network device based on the content of the second report indicated by the third indication information.

[0323] As shown in the figure, step 1220 can include step 1220a or step 1220b; correspondingly, step 1230 can include step 1230a or step 1230b. The network side and the terminal side can perform steps 1220a and 1230a, or also perform steps 1220b and 1230b.

[0324] In step 1220a, the network side indicates by the third indication information that the content of the second report is the first part of the CSI report; in step 1230a, the terminal side can send the second report based on the third indication information, the second report including the first part of the CSI report and not including the second part; in step 1220b, the network side indicates by the third indication information that the content of the second report is the first part and the second part of the CSI report; in step 1230b, the terminal side can send the second report based on the third indication information, the second report including the first part and the second part of the CSI report.

[0325] Of course, the second report sent by the terminal side can also be packet loss, therefore, the network side can receive the second report from the terminal side, or can not receive the second report from the terminal side. For convenience of description, the embodiment assumes that the network side receives the second report.

[0326] Optionally, the method further includes: step 1240, the network side reconstructs the channel measurement result based on the second report.

[0327] In the case of receiving the second report, the network side can reconstruct the channel measurement result based on the second report to obtain the recovered channel measurement result.

[0328] Similar to step 760 in the method 700, the second AI model of the network side can reconstruct the channel measurement result based on the information (i.e., part or all of the information in the CSI report) in the received second report.

[0329] Based on the above scheme, the network side can instruct the terminal side to send the second report through signaling in the case of packet loss at the terminal side, that is, instruct the terminal side to retransmit the CSI report. Thus, the terminal side can deliver part or all of the information in the CSI report to the network side through the second report. Therefore, the network side can reconstruct the channel measurement result based on the received second report, thereby facilitating reasonable scheduling of the network side and improving communication performance.

[0330] Optionally, the method further includes: step 1250, updating, by the terminal side, the state information of the first AI model based on the channel measurement result.

[0331] It should be understood that step 1250 is the same as step 740 in method 700, and reference can be made to the related description in step 740 of method 700, which will not be repeated here.

[0332] Optionally, the method further includes: step 1260, updating, by the network side, the state information of the second AI model based on the second report.

[0333] The second AI model of the network side can also update the state information while reconstructing the channel measurement result, to obtain updated state information, which is obtained based on part or all of the information in the input CSI report this time. Therefore, the process of reconstructing the channel measurement result by the second AI model and the process of updating the state information can be considered as being executed synchronously. Although steps 1240 and 1250 are shown as two steps in the figure, the execution sequence of the two steps should not be limited. For example, steps 1240 and 1250 can be executed synchronously, as exemplified above; steps 1240 and 1250 can also be executed asynchronously, for example, the network side first executes step 1240 and then executes step 1250, or the network side first executes step 1250 and then executes step 1240, without limitation.

[0334] It should be understood that step 1260 is similar to step 750 in method 700, and reference can be made to the related description in step 750 of method 700, which will not be repeated here.

[0335] Based on the above scheme, the terminal side can update the state information of the first AI model based on the channel measurement result, and the network side can update the state information of the second AI model based on part or all of the CSI report. In this way, the network side and the terminal side can be prevented from updating the state information out of synchronization due to packet loss of the first report. Although the network side cannot necessarily obtain the complete CSI report, it can at least obtain the first part of the CSI report, which is generated by the terminal side discarding part of the information of the CSI report in the case of insufficient uplink resources, and therefore can contain information of a larger part of the CSI report. Therefore, the network side can update the state information based on most of the information of the CSI report, which is conducive to the network side updating the state information based on the same or corresponding input as the terminal side, i.e., the time-domain related features of the channel can be mined synchronously. Therefore, it is helpful for the network side to accurately reconstruct the channel measurement result, and further improve the communication performance. In addition, by mining the time-domain related features of the historical channel measurement result and the current channel measurement result, more accurate channel compression is realized to resist channel aging, and the overhead of feeding back the channel measurement result can be reduced.

[0336] In the present embodiment, the resource for the second report is a second resource, and the second resource is located after the first resource in the time domain. In the present embodiment, the second resource can be configured by the network side through signaling, e.g., the same as the configuration of the first resource, or the second resource can be a resource pre-configured for CSI reporting; the second resource can also be additionally configured by the network side in the case of determining packet loss of the first report, which is not limited herein.

[0337] Optionally, the method further comprises: the network side sending fourth indication information to the terminal side, the fourth indication information being used to indicate the second resource. Correspondingly, the terminal side receives the fourth indication information from the network side.

[0338] The second resource is a resource for transmitting the second report. The network side can schedule the second resource for the terminal side through the fourth indication information, so that the terminal side transmits the second report on the second resource.

[0339] The fourth indication information has the same function as the first indication information in the above method 700, and is used to indicate the second resource. Therefore, the above related description of the second indication information can be referred to for understanding, and will not be repeated here.

[0340] To better understand the scheme, FIG. 13 shows the flow of the method by time sequence. As an example, FIG. 13 assumes that both the first resource and the second resource are indicated by DCI, the first resource is indicated by DCI 1, and the second resource is indicated by DCI 2. It can be seen that the operations performed by the network side and the terminal side at various time points in FIG. 13 are similar to those in FIG. 8, except that when the network side indicates the content of the second report by DCI 2 at T2, it can indicate the first part of the CSI report, as shown in a) in the figure, and the terminal side can also send the second report including the first part and excluding the second part based on the DCI 2; when the network side indicates the content of the second report by DCI 2 at T2, it can also indicate the first part and the second part of the CSI report, as shown in b) in the figure, and the terminal side can also send the second report including the first part and the second part based on the DCI 2. The operations at other time points can be referred to the related description of FIG. 8 and will not be repeated here.

[0341] Optionally, the time length by which the first resource and the second resource are offset in the time domain is less than or equal to a threshold value.

[0342] Similar to the method 700, in order to enable the CSI report to be sent through the second report before it is cleared from the cache at the terminal side, the time length by which the second resource and the first resource are offset in the time domain is less than or equal to a threshold value.

[0343] Optionally, the threshold value is determined according to the storage capability of the terminal device. Further, the method further includes: sending, by the terminal side, capability information to the network side, the capability information being used to indicate the storage capability of the terminal device. Correspondingly, the network side receives the capability information from the terminal side.

[0344] For more detailed description of the time length by which the first resource and the second resource are offset in the time domain being less than or equal to a threshold value and the terminal side reporting the capability information, reference can be made to the related description in the method 700, which will not be repeated here.

[0345] Based on the above scheme, the terminal side reports the storage capability of the terminal device through the capability information, so that the network side can take into account the storage capability of the terminal device when scheduling the second resource for the second report, and the second report can be sent through the second resource before it is cleared from the storage space of the terminal, thereby more effectively ensuring that the terminal side sends both the first report and the second report to the network side.

[0346] The above describes in detail the method provided by the embodiments of the present application in combination with multiple drawings. The following describes the apparatus provided by the embodiments of the present application in combination with the drawings.

[0347] FIG. 14 and FIG. 15 are schematic block diagrams of possible apparatuses provided by embodiments of the present application. These apparatuses can be used to implement the functions of the terminal side or the network side in the above-described method embodiments, and thus can also achieve the beneficial effects of the above-described method embodiments.

[0348] FIG. 14 is a schematic block diagram of an apparatus provided by an embodiment of the present application. The apparatus 1400 shown in FIG. 14 can include a processing module 1410 and a communication module 1420.

[0349] In one possible design, the apparatus 1400 can be used to implement the communication method performed by the terminal side in any one of the embodiments shown in FIG. 7 to FIG. 11. For example, the processing module 1410 is configured to perform the steps related to processing, such as obtaining a CSI report, updating state information, and the like, performed by the terminal side in each of the method embodiments; and the communication module 1420 is configured to perform the steps, such as sending and / or receiving, performed by the terminal side in each of the method embodiments.

[0350] For example, the processing module 1410 is configured to implement steps 710 and 740 in the method 700, and the communication module 1420 is configured to implement steps 720 and 730 in the method 700. For another example, the processing module 1410 is configured to implement steps 1002 to 1104 in the method 1000, and the communication module 1420 is configured to implement steps 1005 to 1008 in the method 1000. For yet another example, the processing module 1410 is configured to implement step 1102 in the method 1100, and the communication module 1420 is configured to implement steps 1106, 1107, 1109, 1110 to 1111 in the method 1100, or the processing module 1410 is configured to implement step 1104 and step 1105 in the method 1100, and the communication module 1420 is configured to implement step 1103 and step 1106 in the method 1100.

[0351] For example, the processing module 1410 can be configured to obtain a CSI report, the CSI report being obtained by processing a channel measurement result, the CSI report including a first part and a second part; and the communication module 1420 can be configured to send a first report, the first report including the first part of the CSI report and not including the second part; and the communication module 1420 can be further configured to send a second report, the second report including the second part of the CSI report. Optionally, the communication module 1420 can be further configured to receive first indication information, the first indication information being used to indicate a second resource used to transmit the second report.

[0352] Optionally, the communication module 1420 can be further configured to send capability information, the capability information being used to indicate a storage capability of the terminal device.

[0353] Optionally, the communications module 1420 can also be configured to receive second indication information, the second indication information being used to indicate content of the second report.

[0354] More detailed description of the processing module 1410 and the communications module 1420 can be directly obtained by referring to the related description in the method embodiments shown in FIGS. 7-11, which will not be repeated here.

[0355] In one possible design, the apparatus 1400 can be configured to implement the communication method performed by the terminal side in the embodiments shown in FIG. 12. For example, the processing module 1410 can be configured to implement the steps related to processing, such as obtaining a CSI report, updating state information, etc., performed by the terminal side in the method 1200; and the communications module 1420 can be configured to implement the steps of sending and / or receiving, etc., performed by the terminal side in the method 1200. For example, the processing module 1410 can be configured to implement the step 1250 in the method 1200, and the communications module 1420 can be configured to implement the steps 1210-1230 in the method 1200.

[0356] For example, the processing module 1410 can be configured to obtain a CSI report, the CSI report being obtained by processing a channel measurement result, the CSI report including a first part and a second part; the communications module 1420 can be configured to send a first report, the first report including the first part of the CSI report and not including the second part; the communications module 1420 can also be configured to receive third indication information, the third indication information being used to indicate content of a second report; and the communications module 1420 can be further configured to send the second report based on the third indication information.

[0357] Optionally, the communications module 1420 can also be configured to receive fourth indication information, the fourth indication information being used to indicate a second resource used to transmit the second report.

[0358] Optionally, the communications module 1420 can also be configured to send capability information, the capability information being used to indicate storage capability of the terminal device.

[0359] More detailed description of the processing module 1410 and the communications module 1420 can be directly obtained by referring to the related description in the method embodiments shown in FIG. 12, which will not be repeated here.

[0360] In another possible design, the apparatus 1400 can be configured to implement the communication method performed by the network side in the embodiments shown in FIGS. 7-11. For example, the processing module 1410 can be configured to implement the steps related to processing, such as reconstructing channel state information, updating state information, etc., performed by the network side in the method embodiments; and the communications module 1420 can be configured to implement the steps of sending and / or receiving, etc., performed by the network side in the method embodiments.

[0361] For example, the processing module 1410 is configured to implement steps 750 and 760 in the method 700, and the communication module 1420 is configured to implement steps 720 and 730 in the method 700. For another example, the processing module 1410 is configured to implement steps 1009 and 1010 in the method 1000, and the communication module 1420 is configured to implement steps 1005 to 1008 in the method 1000. For yet another example, the communication module 1420 is configured to implement steps 1107 to 1112, and step 1114 in the method 1100, or the communication module 1420 is configured to implement steps 1108, 1112, and 1114 in the method 1100, and the processing module 1420 is configured to implement step 1113 and step 1115 in the method 1100.

[0362] For example, the communication module 1420 is configured to receive a first report, the first report comprising a first part of a CSI report and not comprising a second part, the CSI report being obtained by processing a channel measurement result, the CSI report comprising the first part and the second part; and receive a second report, the second report comprising the second part of the CSI report.

[0363] Optionally, the processing module 1410 is configured to update state information of a second AI model based on the first part and / or the second part.

[0364] Optionally, the communication module 1420 is further configured to send first indication information, the first indication information being used to indicate a second resource used for transmitting the second report.

[0365] Optionally, the communication module 1420 is further configured to receive capability information, the capability information being used to indicate a storage capability of the terminal device.

[0366] Optionally, the communication module 1420 is further configured to send second indication information, the second indication information being used to indicate a content of the second report.

[0367] For more details of the processing module 1410 and the communication module 1420, refer to the descriptions of the method embodiments shown in FIGs. 7 to 11.

[0368] In a possible design, the apparatus 1400 can be configured to implement the communication method performed by the network side in the embodiment shown in FIG. 12. For example, the processing module 1410 is configured to implement steps related to processing, such as reconstructing channel state information, updating state information, and the like, performed by the network side in the method 1200; and the communication module 1420 is configured to implement steps such as sending and / or receiving performed by the network side in the method 1200. For example, the processing module 1410 is configured to implement steps 1240 and 1260 in the method 1200, and the communication module 1420 is configured to implement steps 1220 and 1230 in the method 1200.

[0369] Exemplarily, the communication module 1420 can also be configured to send third indication information, where the third indication information is used to indicate content of the second report; and the communication module 1420 is further configured to receive the second report.

[0370] Optionally, the processing module 1410 can be configured to update state information of the second AI model based on the second report.

[0371] Optionally, the communication module 1420 is further configured to send fourth indication information, where the fourth indication information is used to indicate the second resource used to transmit the second report.

[0372] Optionally, the communication module 1420 can also be configured to receive capability information, where the capability information is used to indicate storage capability of the terminal device.

[0373] For more details of the processing module 1410 and the communication module 1420, refer to the related description in the method embodiments shown in FIG. 12, which will not be repeated here.

[0374] It should be noted that the communication module can also be referred to as a transceiver module, a transceiver unit, a transceiver, a transceiver device, or the like. The processing module can also be referred to as a processor, a processing unit, or the like. Optionally, the communication module is configured to perform the sending operation and the receiving operation of the terminal side or the network side in the above method, and the device in the communication module for realizing the receiving function can be regarded as a receiving module, and the device in the communication module for realizing the sending function can be regarded as a sending module, that is, the communication module can include a receiving module and a sending module.

[0375] It should be further noted that in a possible design, the foregoing processing module and / or communication module can be implemented through a virtual module, for example, the processing module can be implemented through a software function unit or a virtual device, and the communication module can be implemented through a software function or a virtual device. In another possible design, the processing module or the communication module can also be implemented through an entity device, for example, if the device is implemented by using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, and performs an input operation (corresponding to the foregoing receiving operation) and an output operation (corresponding to the foregoing sending operation); and the processing module can be an integrated processor or a microprocessor or an integrated circuit.

[0376] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, each function module in each example in the embodiments of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software function module.

[0377] FIG. 15 is a structural schematic diagram of a communication apparatus provided by another embodiment of the present application. As shown in FIG. 15, the apparatus 1500 includes processing circuitry 1510 and communication circuitry 1520. The processing circuitry 1510 and the communication circuitry 1520 are coupled to each other.

[0378] It can be understood that the processing circuitry 1510 can be one or more processors, or can be all or part of the control and / or processing function of one or more processors.

[0379] It can be understood that the communication circuitry 1520 can be a transceiver or an input / output interface.

[0380] Optionally, the apparatus 1500 can further include a memory 1530 for storing instructions executed by the processing circuitry 1510 or storing input data required by the processing circuitry 1510 for executing instructions or storing data generated by the processing circuitry 1510 after executing instructions.

[0381] It can be understood that the memory 1530 can be located outside the processing circuitry 1510, or located inside the processing circuitry 1510.

[0382] As an example, the processing circuitry 1510 is configured to implement the functions of the above-mentioned processing module 1410, and the communication circuitry 1520 is configured to implement the functions of the above-mentioned communication module 1420.

[0383] As an example, the apparatus 1500 can be a communication device, or can be a chip applied to a communication device.

[0384] When the apparatus 1500 is a communication device, the communication circuitry can be a transceiver; when the apparatus 1500 is a chip, the communication circuitry can be an input / output circuit, a bus, a pin or other types of communication interfaces, wherein the input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0385] In some embodiments of the present application, a computer program product is also provided. When the computer program product runs on a processor, it can implement the communication method implemented by the terminal side in the above method embodiments, or can implement the communication method implemented by the network side in the above method embodiments.

[0386] In some embodiments of the present application, a computer readable storage medium is also provided, which comprises computer instructions, which, when executed on a processor, can implement the communication method implemented by the terminal side in the method embodiments described above, or can implement the communication method implemented by the network side in the method embodiments described above.

[0387] In some embodiments of the present application, a communication system is also provided, which comprises the terminal side and the network side described above.

[0388] It can be understood that the processor in the embodiments of the present application can be all or part of the circuit of the following devices or the following devices for processing functions: a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), graphics processing units (GPUs), artificial intelligence (AI) processing units, field programmable gate arrays (FPGAs) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor, or any conventional processor.

[0389] The method steps in the embodiments of the present application can be implemented in a hardware manner, or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in a chip, such as an application-specific integrated circuit (ASIC), or a chip system, such as a system on a chip (SOC). In addition, the chip or chip system can be located in a network device or a terminal device. Of course, the processor and the storage medium can also exist as discrete components in the network device or the terminal device.

[0390] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or 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 programs or instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; an optical medium, such as a digital video disc; and a semiconductor medium, such as a solid state disk.

[0391] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0392] It can be understood that various numerical numbers involved in the embodiments of the present application are only distinguished for convenience of description, and are not used to limit the scope of the embodiments of the present application. The size of the serial number of the above processes does not mean the execution order, and the execution order of the processes should be determined according to its function and inherent logic.

Claims

1. A communication method, characterized in that: include: Obtain a channel state information (CSI) report, where the CSI report is obtained by processing a channel measurement result, and the CSI report includes a first part and a second part; sending a first report, where the first report includes the first part of the CSI report and does not include the second part; A second report is sent, where the second report includes the second part of the CSI report.

2. The method according to claim 1, wherein The resource used to transmit the first report is a first resource, the resource used to transmit the second report is a second resource, and the duration of the time domain offset between the first resource and the second resource is less than or equal to a threshold value.

3. The method according to claim 2, wherein The method further comprises: First indication information is received, where the first indication information is used to indicate the second resource.

4. The method according to claim 2 or 3, wherein: The method is applied to a terminal side, and the threshold value is determined based on the storage capacity of a terminal device on the terminal side.

5. The method according to claim 4, wherein The method further comprises: Capability information is sent, where the capability information indicates the storage capability of the terminal device.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Second indication information is received, where the second indication information is used to indicate content of the second report.

7. A communication method, characterized in that: The method comprises: receiving a first report, where the first report includes a first part of a channel state information (CSI) report and does not include a second part, where the CSI report is obtained by processing a channel measurement result, and the CSI report includes the first part and the second part; A second report is received, where the second report includes the second portion of the CSI report.

8. The method according to claim 7, wherein The resource used to transmit the first report is a first resource, the resource used to transmit the second report is a second resource, and the duration of the time domain offset between the first resource and the second resource is less than or equal to a threshold value.

9. The method according to claim 8, wherein The method further comprises: Send first indication information, where the first indication information is used to indicate the second resource.

10. The method according to claim 8 or 9, characterized in that The first report and the second report are from a terminal side, and the threshold value is determined based on a storage capacity of a terminal device on the terminal side.

11. The method according to claim 10, wherein: The method further comprises: Capability information is received, where the capability information indicates a storage capability of the terminal device.

12. The method according to any one of claims 7 to 11, characterized in that The method further comprises: Send second indication information, where the second indication information is used to indicate content of the second report.

13. The method according to any one of claims 1 to 12, characterized in that The CSI report is an output obtained by the first artificial intelligence AI model processing the channel measurement result; the first part and / or the second part are used by the second AI model to update the status information.

14. The method according to any one of claims 1 to 13, characterized in that The second report further includes the first part, or the second report does not include the first part.

15. A communication method, characterized in that: The method comprises: Sending a first report, where the first report includes a first part of a channel state information (CSI) report, where the CSI report is obtained by processing a channel measurement result, and the CSI report includes the first part and a second part; receiving third indication information, where the third indication information is used to indicate content of the second report; Based on the third indication information, the second report is sent.

16. The method according to claim 15, wherein The resource used to transmit the first report is a first resource, and the resource used to transmit the second report is a second resource. The time domain offset between the first resource and the second resource is less than or equal to a threshold value.

17. The method according to claim 16, wherein The method further comprises: Fourth indication information is received, where the fourth indication information is used to indicate the second resource, and the second resource is used to transmit the second report.

18. The method according to claim 16 or 17, wherein: The method is applied to a terminal side, and the threshold value is determined based on the storage capacity of a terminal device on the terminal side.

19. The method according to claim 18, wherein The method further comprises: Capability information is sent, where the capability information indicates the storage capability of the terminal device.

20. A communication method, characterized in that: The method comprises: Sending third indication information, where the third indication information is used to indicate content of a second report, where the second report includes a second part of a channel state information (CSI) report, where the CSI report is obtained by processing a channel measurement result, and includes a first part and a second part; The second report is received.

21. The method according to claim 20, wherein The method further comprises: Reconstruct a channel measurement result based on the second report.

22. The method according to claim 21, wherein The resource used to transmit the first report is the first resource, the resource used to transmit the second report is the second resource, the time offset between the first resource and the second resource in the time domain is less than or equal to a threshold value, and the first report includes the first part.

23. The method according to claim 22, wherein The method further comprises: Send fourth indication information, where the fourth indication information is used to indicate the second resource.

24. The method according to claim 22 or 23, wherein: The first report and the second report are from a terminal side, and the threshold value is determined based on a storage capacity of a terminal device on the terminal side.

25. The method of claim 24, wherein: The method further comprises: Capability information is received, where the capability information is used to indicate a storage capability of a terminal device.

26. The method according to any one of claims 15 to 25, characterized in that The CSI report is an output obtained by the first artificial intelligence AI model processing the channel measurement result; the first part and / or the second part are used by the second AI model to update the status information.

27. The method according to any one of claims 15 to 26, characterized in that The second report includes the first part of the CSI report but does not include the second part, or the second report includes the first part and the second part of the CSI report.

28. A communication device, characterized in that: The method comprises functional modules for implementing the method according to any one of claims 1 to 27.

29. A communication device, characterized in that: include: One or more processors and communication circuits, wherein the communication circuit is used for the communication device to perform at least one of inputting or outputting signals; the one or more processors are used to implement the method according to any one of claims 1 to 27.

30. A computer-readable storage medium, characterized in that Used to store a program or instruction, when the program or instruction is executed by a computer or a processor, the method according to any one of claims 1 to 27 is implemented.

31. A computer program, characterized in that The method comprises a program or an instruction, and when the program or the instruction is executed by a computer or a processor, the method according to any one of claims 1 to 27 is implemented.

32. A communication system, characterized in that: The invention comprises an apparatus for implementing the method according to any one of claims 1 to 14 and an apparatus for implementing the method according to any one of claims 15 to 27.

Images