Communication method and communication apparatus

Abstract

A communication method and a communication apparatus, which relate to the technical field of communications. In the communication method, on the basis of the state of a first channel report, both a first apparatus and a second apparatus can determine whether to update the values of state information of AI models deployed on respective sides. For example, when the first apparatus does not send the first channel report to the second apparatus, on the basis of the state of the first channel report (for example, the state of the first channel report is an untransmitted state), the first apparatus determines not to update the value of the state information of the AI model deployed on the side of the first apparatus, and the second apparatus also does not update the value of the state information of the AI model deployed on the side of the second apparatus. Thus, the rhythm in terms of updating the values of the state information of the AI models between the first apparatus and the second apparatus is consistent, such that the feedback performance of the channel report can be improved, thereby improving the recovery performance for channel information and the robustness of the recovery performance.

Description

Communication method and communication device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on February 8, 2024, with application number 202410177336.9 and application name “Communication Method and Communication Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Art

[0003] In a communications system, network equipment determines downlink channel configuration information, including resources, modulation and coding scheme (MCS), and precoding, for scheduling terminal devices' downlink data channels based on downlink channel state information (CSI). Terminal devices calculate downlink CSI by measuring downlink reference signals and generate CSI reports that are fed back to the network equipment.

[0004] The introduction of artificial intelligence (AI) into wireless communications has led to the emergence of an AI-based CSI feedback method. AI models have stronger feature extraction capabilities and can more effectively compress channel information, reducing information loss during the compression process and ensuring the accuracy of the recovered channel information.

[0005] Taking CSI feedback based on time-domain correlation as an example, the AI ​​model on the terminal device side outputs CSI feedback information based on the current channel measurement results and the AI ​​model's state information. The AI ​​model on the network device side recovers channel information based on the most recently received CSI feedback information and the AI ​​model's state information. The state information of the AI ​​model on the terminal device side is determined based on historical channel measurement results. The state information of the AI ​​model on the network device side is determined based on CSI feedback information received at historical moments. Because the reception of CSI feedback information depends on the transmission conditions of the channel, packet loss of CSI feedback information can lead to reduced performance in recovering channel information. A solution is urgently needed to improve the robustness of channel information recovery performance. Summary of the Invention

[0006] The present application provides a communication method and a communication device, in order to improve the feedback performance of channel reports, thereby improving the recovery performance of channel information and the robustness of the recovery performance.

[0007] In a first aspect, a communication method is provided, including: obtaining a status of a first channel report; and determining a value of status information of a first AI model, wherein the value of the status information of the first AI model is related to the status of the first channel report.

[0008] The method can be performed by a first device, which can be a device on the first AI model side, or a chip or circuit of the device on the first AI model side. The device on the first AI model side can be replaced by a device on the terminal device side or a device on the network device side. The terminal device side can include at least one of the terminal device or the AI ​​entity on the terminal device side. The AI ​​entity on the terminal device side can be the terminal device itself, or it can be an AI entity serving the terminal device, for example, a server, such as an over the top (OTT) server or a cloud server. The network device side can include at least one of the network device or the AI ​​entity on the network device side. The AI ​​entity on the network device side can be the network device itself, or it can be an AI entity serving the network device, such as a radio access network (RAN) intelligent controller (RIC), operation administration and maintenance (OAM), or a server, such as an OTT server or a cloud server.

[0009] The first AI model is a self-encoding model. The self-encoding model may also include a second AI model.

[0010] The first AI model, such as the AI ​​model on the terminal device side, can be used to generate channel reports.

[0011] The first channel report can be replaced by the first CSI report, or the first CSI feedback information, or the first CSI compression information, etc.

[0012] In the above solution, the first device can determine whether to update the value of the state information of the first AI model based on the status of the first channel report. For example, when the status of the first channel report indicates that the first channel report is in an incomplete transmission state, the first device determines not to update the value of the state information of the first AI model, that is, the first device maintains the value of the state information of the first AI model unchanged. When the second device, that is, the device on the second AI model side or the chip or circuit of the device on the second AI model side, does not receive the first channel report, the second device cannot update the value of the state information of the second AI model based on the first channel report. Based on the above solution, the first device also does not update the value of the state information of the first AI model. In this way, the first and second devices have the same rhythm for updating the value of the state information of the AI ​​model, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0013] Among them, the device on the second AI model side can be replaced by a device on the terminal device side or a device on the network device side. For the description of the device on the terminal device side and the device on the network device side, please refer to the description of the device on the first AI model side above and will not be repeated here.

[0014] In the first aspect, the first channel report is determined based on a first value of the state information of the first AI model.

[0015] In this way, channel information can be compressed based on historical channel measurement results.

[0016] In the first aspect, the value of the state information of the first AI model is related to the state reported by the first channel, including:

[0017] The status reported by the first channel is the discarded status, and the value of the status information of the first AI model remains unchanged;

[0018] The status reported by the first channel is a partial content sending status, and the value of the status information of the first AI model remains unchanged; or

[0019] The status reported by the first channel is the status of all content being sent, and the value of the status information of the first AI model is updated.

[0020] The first device can determine a corresponding action based on the status of the first channel report. For example, the first device can determine whether to update the value of the state information of the first AI model or maintain the value of the state information of the first AI model based on the status of the first channel report. This can ensure that the first and second devices have a consistent rhythm for updating the value of the AI ​​model state information, thereby improving the feedback performance of the channel report and further improving the recovery performance and robustness of the channel information.

[0021] In the first aspect, the status reported by the first channel is a discarded status, which is determined based on at least one of the following:

[0022] The resources used for transmitting the first channel report overlap with the resources used for transmitting the hybrid automatic repeat request report in the time domain;

[0023] The resources used for transmitting the first channel report overlap with the resources used for transmitting the scheduling request report in the time domain;

[0024] The priority of the first channel is lower than the priority of the second channel, the second channel overlaps with the first channel in the time domain, the first channel is used to carry the first channel report, and the second channel is used to carry uplink information; or,

[0025] The channel used to carry the first channel report conflicts with a downlink symbol or a flexible symbol configured or indicated by the network device.

[0026] The first device can determine whether the first channel report is in a discarded state based on one or more of the above. When it is determined that the first channel report is in a discarded state, the first device does not update the value of the state information of the first AI model. Since the first channel report is not received, the second device cannot update the value of the state information of the second AI model based on the first channel report. In this way, the rhythm of updating the value of the state information of the AI ​​model between the first device and the second device can be consistent, thereby improving the feedback performance of the channel report, and further improving the recovery performance of the channel information and the robustness of the recovery performance.

[0027] In the first aspect, the value of the status information of the first AI model is related to the status of the first channel report, including: the status of the first channel report is a partial content sending state, the value of the status information of the first AI model is related to the offset between the sending time unit of the second channel report and the generation time unit of the third channel report, the second channel report is determined based on the second value of the status information of the first AI model, the first value is determined by updating the second value based on the second channel report, and the third channel report is the first channel report sent after the first channel report.

[0028] When the first device sends a first channel report including partial content to the second device, the first device can determine whether to update the value of the status information of the first AI model based on the offset between the sending time unit of the second channel report and the generation time unit of the third channel report. While ensuring that the rhythm of the value of the status information of the AI ​​model between the first device and the second device is consistent, the first device utilizes real-time and effective channel information, thereby improving the feedback performance of the channel report, and thereby improving the recovery performance of the channel information and the robustness of the recovery performance.

[0029] In the first aspect, the value of the state information of the first AI model is related to the offset between the sending time unit of the second channel report and the generation time unit of the third channel report, including:

[0030] The offset is greater than the threshold, and the value of the state information of the first AI model is updated, or,

[0031] The offset is smaller than the threshold, and the value of the state information of the first AI model remains unchanged.

[0032] In this way, the first device can determine whether to update the value of the state information of the first AI model based on the relationship between the offset and the threshold.

[0033] In the first aspect, the threshold is indicated or configured by the network device, or the threshold is predefined.

[0034] The above threshold value is predefined, which may include: the above threshold value is predefined by the protocol, or the above threshold value is pre-stored, or the above threshold value is pre-burned, etc.

[0035] In the first aspect, the status reported by the first channel is a partial content sending status determined based on at least one of the following:

[0036] The processing resources available for calculation on the terminal device side are insufficient to generate the expected first channel report;

[0037] The network device configures or instructs the time unit for reporting the first channel report to not meet the time requirement for calculation of the expected first channel report;

[0038] The network device configures or indicates that the time unit corresponding to the uplink data channel carrying the first channel report does not meet the time requirement for calculation of the expected first channel report; or,

[0039] The network device configures or indicates that the transmission resources for carrying the first channel report are insufficient to carry the expected first channel report.

[0040] The first device can determine whether the first channel report is in a partial content sending state based on one or more of the above. When it is determined that the first channel report is in a partial content sending state, the first device can determine whether to update the value of the state information of the first AI model. Accordingly, this can avoid the first device updating the value of the state information of the first AI model without determining whether the first channel report is in a full content sending state, thereby supporting the first device and the second device to have a consistent rhythm for updating the value of the state information of the AI ​​model, thereby improving the feedback performance of the channel report, and further improving the recovery performance of the channel information and the robustness of the recovery performance.

[0041] In the first aspect, the first value is determined based on a channel measurement result of a historical reference signal, the sending time unit of the historical reference signal is earlier than the sending time unit of the first reference signal, and the first channel report corresponds to the first reference signal.

[0042] In this way, the channel information can be compressed by utilizing the correlation of the channel in the time domain.

[0043] In a second aspect, a communication method is provided, including: obtaining a status of a first channel report; and determining a value of status information of a second AI model, wherein the value of the status information of the second AI model is related to the status of the first channel report.

[0044] The method can be performed by a second device, which can be a device on the second AI model side, or a chip or circuit for the device on the second AI model side. The device on the second AI model side can be replaced by a device on the terminal device side or a device on the network device side. The description of the device on the terminal device side or the device on the network device side can refer to the description of the device on the first AI model side above and will not be repeated here.

[0045] The second AI model is a self-encoding model. The self-encoding model may also include the first AI model.

[0046] The second AI model is an AI model that matches the first AI model, and may be, for example, an AI model on the network device side, and may be used to recover channel information corresponding to the channel report.

[0047] In the above scheme, the second device determines the value of the status information of the second AI model based on the status of the first channel report. This can support the consistency of the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device, thereby improving the feedback performance of the channel report, and further improving the recovery performance of the channel information and the robustness of the recovery performance.

[0048] In the second aspect, the value of the state information of the second AI model is related to the state reported by the first channel, including:

[0049] The status reported by the first channel is the partial content sending status, and the value of the status information of the second AI model remains unchanged; or

[0050] The status reported by the first channel is the status of all content sent, and the value of the status information of the second AI model is updated.

[0051] The second device can determine corresponding behavior based on the status of the first channel report. For example, the second device can determine whether to update the state information of the second AI model or maintain the state information of the second AI model based on the status of the first channel report. In this way, the first and second devices synchronize their updates of the AI ​​model state information, which can improve the feedback performance of the channel report and, in turn, improve the recovery performance and robustness of the channel information.

[0052] In the second aspect, the value of the state information of the second AI model is related to the state reported by the first channel, including:

[0053] The status of the first channel report is the partial content sending status. The value of the status information of the second AI model is related to the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report. The first value of the status information of the second AI model is determined by updating the second value of the status information of the AI ​​model according to the second channel report. The update of the first value is related to the first channel report. The third channel report is the first channel report received after the first channel report.

[0054] When the first device sends a first channel report including partial content to the second device, the second device can determine whether to update the value of the status information of the second AI model based on the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report. While ensuring that the rhythm of the value of the status information of the AI ​​model between the first device and the second device is consistent, the second device can utilize real-time and effective channel information, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0055] In the second aspect, the value of the state information of the second AI model is related to the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel, including:

[0056] The offset is greater than the threshold, and the value of the state information of the second AI model is updated, or,

[0057] The offset is smaller than the threshold, and the value of the state information of the second AI model remains unchanged.

[0058] In this way, the second device can determine whether to update the value of the state information of the second AI model based on the relationship between the offset and the threshold.

[0059] In the second aspect, the threshold is indicated or configured by the network device, or the threshold is predefined.

[0060] The above threshold value is predefined, which may include: the above threshold value is predefined by the protocol, or the above threshold value is pre-stored, or the above threshold value is pre-burned, etc.

[0061] In the second aspect, the status reported by the first channel is a partial content sending status determined based on at least one of the following:

[0062] The processing resources available for calculation on the terminal device side are insufficient to generate the expected first channel report,

[0063] The network device configures or instructs the time unit for reporting the first channel report to not meet the time requirement for calculating the expected first channel report.

[0064] The network device configures or indicates that the time unit corresponding to the uplink data channel carrying the first channel report does not meet the time requirement for the calculation of the expected first channel report, or,

[0065] The network device configures or indicates that the transmission resources for carrying the first channel report are insufficient to carry the expected first channel report.

[0066] In a third aspect, a communication device is provided. The communication device may be a first device, or a device or module for executing the function of the first device.

[0067] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the first aspect. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0068] The first device mentioned above may be a terminal device or an AI entity on the terminal device side, or may be a network device or an AI entity on the network device side, which is not limited.

[0069] In a fourth aspect, a communication device is provided. The communication device may be a second device, or a device or module for executing the function of the second device.

[0070] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the second aspect. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0071] The second device mentioned above may be a network device or an AI entity on the network device side, or may be a terminal device or an AI entity on the terminal device side.

[0072] In a fifth aspect, a communication device is provided, comprising a processor, wherein the processor is configured to, by executing a computer program or instruction, or by a logic circuit, enable the communication device to execute the method described in the first aspect and any possible manner of the first aspect; or enable the communication device to execute the method described in the second aspect and any possible manner of the second aspect.

[0073] In a possible implementation, the communication device further includes a memory for storing the computer program or instruction.

[0074] In a possible implementation, the communication device further includes a communication interface, which is used to input and / or output signals.

[0075] In the sixth aspect, a communication device is provided, comprising a logic circuit and an input / output interface, the input / output interface being used to input and / or output signals, the logic circuit being used to execute the method described in the first aspect and any possible manner of the first aspect; or the logic circuit being used to execute the method described in the second aspect and any possible manner of the second aspect.

[0076] In the seventh aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or the instruction is run on a computer, the method described in the first aspect and any possible method of the first aspect is executed; or, the method described in the second aspect and any possible method of the second aspect is executed.

[0077] In an eighth aspect, a computer program product is provided, comprising instructions, which, when executed on a computer, cause the method described in the first aspect and any possible manner of the first aspect to be executed; or cause the method described in the second aspect and any possible manner of the second aspect to be executed.

[0078] In the ninth aspect, a chip or chip system is provided, comprising: one or more processors, which are used to execute computer programs or instructions in the memory, so that the chip or chip system implements the method in the first aspect and any possible implementation of the first aspect; or, enables the chip or chip system to implement the method in the second aspect and any possible implementation of the second aspect.

[0079] For the description of the beneficial effects of any aspect from the third aspect to the ninth aspect, reference can be made to the description of the beneficial effects of the first aspect and the second aspect, and no further details will be given. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] FIG1 is a schematic diagram of an application framework applicable to an embodiment of the present application.

[0081] FIG2 is a schematic diagram of another application framework applicable to an embodiment of the present application.

[0082] FIG3 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0083] FIG4 is a schematic diagram of another communication system applicable to an embodiment of the present application.

[0084] FIG5 is a schematic diagram showing the relationship between the encoder and the decoder.

[0085] FIG6 is a schematic diagram of an application scenario to which an embodiment of the present application is applicable.

[0086] Figure 7 is a schematic diagram showing that the first device and the second device of an embodiment of the present application have the same rhythm for updating the status information of the AI ​​model.

[0087] FIG8 is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present application.

[0088] FIG9 is a schematic diagram of an interaction flow of another communication method according to an embodiment of the present application.

[0089] FIG10 is a schematic diagram of an interaction flow of another communication method according to an embodiment of the present application.

[0090] FIG11 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0091] FIG12 is another schematic block diagram of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0092] The technical solution in this application will be described below with reference to the accompanying drawings.

[0093] In order to facilitate understanding of the embodiments of the present application, the following points are first explained.

[0094] 1. In this application, unless otherwise specified, "plurality" means two or more.

[0095] 2. In each embodiment of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their internal logical relationships.

[0096] 3. The various numerical numbers involved in this application are only used for the convenience of description and are not used to limit the scope of protection of this application. The size of the serial numbers involved in this application does not mean the order of execution. The order of execution of each process should be determined by its function and internal logic. For example, the terms "first", "second", "third", "fourth" and other various terminology labels (if any) in the specification and claims and drawings of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. Among them, the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than what is illustrated or described here.

[0097] At the same time, any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0098] 4. The terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product or apparatus.

[0099] 5. In this application, "used to indicate" can be understood as "enabling," and "enabling" can include direct enabling and indirect enabling. When describing that certain information is used to enable A, it can include that the information directly enables A or indirectly enables A, and does not necessarily mean that the information contains A.

[0100] The information enabled by the information is called information to be enabled. In the specific implementation process, there are many ways to enable the enabled information, such as but not limited to, directly enabling the information to be enabled, such as the information to be enabled itself or the index of the information to be enabled. The information to be enabled can also be indirectly enabled by enabling other information, wherein there is an association between the other information and the information to be enabled. It is also possible to enable only a part of the information to be enabled, while the other parts of the information to be enabled are known or agreed in advance. For example, it is also possible to enable specific information with the help of the arrangement order of each piece of information agreed in advance (such as specified in the protocol), thereby reducing the enabling overhead to a certain extent. At the same time, it is also possible to identify the common parts of each piece of information and enable them uniformly to reduce the enabling overhead caused by enabling the same information separately.

[0101] 6. In this application, "pre-configuration" may include pre-definition, such as protocol definition. "Pre-definition" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., including each network element). This application does not limit the specific implementation method.

[0102] 7. "Storage" or "saving" as used in this application may refer to storage in one or more memories. The one or more memories may be provided separately or integrated into an encoder or decoder, a processor, or a communication device. The one or more memories may also be partially provided separately and partially integrated into a decoder, processor, or communication device. The type of memory may be any form of storage medium and is not limited thereto.

[0103] 8. The “protocol” referred to in this application may refer to a standard protocol in the field of communications, such as the fourth generation (4G) network, the fifth generation (5G) network protocol, the new radio (NR) protocol, the 5.5G network protocol, the sixth generation (6 th generation, 6G) network protocols and related protocols used in future communication systems, which are not limited in this application.

[0104] 9. The arrows or boxes indicated by dotted lines in the schematic diagrams in the accompanying drawings of this application specification represent optional steps or optional modules.

[0105] 10. In this application, unless otherwise specified, “ / ” indicates that the objects associated with each other are in an “or” relationship. For example, A / B can mean A or B. “And / or” in this application is merely a description of the association relationship between 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. A and B can be singular or plural.

[0106] 11. In this application, indication includes direct indication (also called explicit indication) and implicit indication. Direct indication of information A means including information A. Implicit indication of information A means indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0107] 12. In this application, the use of information C to determine information D includes both situations where information D is determined solely based on information C and situations where information D is determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0108] 13. In this application, "device A sends information A to device B" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the device B, which may include sending information to device B directly or indirectly.

[0109] 14. In this application, the phrase "Device B receives information A from Device A" should be understood to mean that the source of information A or an intermediate network element in the transmission path between the source and the device A is Device A, and may include directly or indirectly receiving the information from Device A. Information may undergo necessary processing between the source and destination, such as formatting changes, but the destination can still understand the valid information from the source. Similar expressions in this application should be understood similarly and are not elaborated on here.

[0110] First, a communication system to which the embodiments of the present application are applicable is described.

[0111] The technical solutions provided in this application can be applied to various communication systems, such as 5G or NR systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, such as 6G mobile communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0112] A device in a communication system can send signals to or receive signals from another device. Signals can include information, signaling, or data. The term "device" can also be replaced by an entity, network entity, device, communication device, communication module, node, or communication node. This application uses devices as an example for description. For example, a communication system can include at least one terminal device and at least one network device. A network device can send downlink signals to a terminal device, and / or a terminal device can send uplink signals to a network device, and / or a terminal device can send sidelink signals to another terminal device, and / or a network device can send signals to another network device.

[0113] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0114] 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.

[0115] As an example and not a limitation, the terminal device can also be a wearable device. Wearable devices can also be called wearable smart devices, which are a general term for wearable devices that use wearable technology to intelligently design and develop wearable devices 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 full-featured, large-sized, and independent of smartphones to achieve complete or partial functions, 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.

[0116] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0117] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network.

[0118] The base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmitting point (TP), master station, auxiliary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, RAN intelligent controller (RIC), etc.

[0119] A base station may also be a macro base station, micro base station, relay node, donor node, or the like, or a combination thereof. A base station may also refer to a communication module, modem, or chip used to be installed in the aforementioned devices or apparatuses. A base station may also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station may support networks with the same or different access technologies.

[0120] Optionally, the RAN node may also be a server, a wearable device, a vehicle, or an onboard device. For example, the access network device in vehicle-to-everything (V2X) technology may be a roadside unit (RSU). The embodiments of this application do not limit the specific technology and device form used by the network device.

[0121] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0122] In some deployments, the network device may include a CU or a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network device includes a gang-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0123] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0124] A RAN node can support one or more types of fronthaul interfaces, and different fronthaul interfaces correspond to DUs and RUs with different functions.

[0125] If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions.

[0126] If the fronthaul interface between the DU and the RU is another interface, relative to CPRI, part of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal are moved from the DU to the RU for implementation.

[0127] In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (Categories) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0128] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0129] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0130] In different communication systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (open RAN, ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of 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.

[0131] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0132] The network equipment and / or terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water; and can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal equipment are located.

[0133] In addition, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (for example, a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of terminal devices and network devices.

[0134] In wireless communication networks (such as mobile communication networks), the services supported by the networks are becoming increasingly diverse, and the demands they need to meet are becoming increasingly diverse. For example, the networks need to be able to support ultra-high speeds, ultra-low latency, and ultra-large connections. This makes network planning, network configuration, and resource scheduling increasingly complex. As network functionality becomes increasingly powerful, such as supporting higher spectrum bandwidths, high-order multiple input multiple output (MIMO) technology, beamforming, and / or beam management, network energy conservation has become a hot research topic. These new demands, new scenarios, and new features pose unprecedented challenges to network planning, maintenance, and efficient operations. To meet this challenge, AI technology can be introduced into wireless communication networks to achieve network intelligence.

[0135] In order to support AI technology in wireless networks, AI nodes (also called AI entities) may be introduced into the network.

[0136] Optionally, the AI ​​entity can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​entity can be deployed separately, for example, in a location other than any of the aforementioned devices, such as a host or cloud server in an OTT system. The AI ​​entity can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements. Based on the objects served by the AI ​​entity, the AI ​​entity can include an AI entity on the network device side, an AI entity on the terminal device side, or an AI entity on the core network side.

[0137] It is understood that this application does not limit the number of AI entities. For example, when there are multiple AI entities, the multiple AI entities can be divided based on function, such as different AI entities are responsible for different functions.

[0138] It can also be understood that AI entities can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI entities.

[0139] The AI ​​entity can be an AI network element or an AI module. The AI ​​entity is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements can be the same or different. The AI ​​model in the AI ​​entity can implement different functions according to different parameter configurations. The AI ​​model in the AI ​​entity can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0140] An AI entity can have one or more models. The learning, training, or inference processes of different models can be deployed in different entities or devices, or in the same entity or device.

[0141] Figure 1 is a schematic diagram of an application framework applicable to an embodiment of the present application. As shown in Figure 1, the devices are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more of these device nodes, such as core network equipment, access network nodes (RAN nodes), terminals or OAM devices (for clarity, only one is shown in Figure 1). The access network node can be a separate RAN node or can include multiple RAN nodes, for example, including CU and DU. One or more AI modules can also be provided in the CU and / or DU. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0142] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different devices may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (for example, the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (for example, the type of input parameters and / or the dimension of the input parameters), or output parameters (for example, the type of output parameters and / or the dimension of the output parameters). The bias in the activation function can also be called the bias of the neural network.

[0143] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0144] Figure 2 is a schematic diagram of another application framework applicable to an embodiment of the present application. As shown in Figure 2, the communication system includes an RIC. For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1, which are used to implement AI-related functions. RIC includes near-real-time RIC (near-real time RIC, near-RT RIC) and non-real-time RIC (non-real time RIC, Non-RT RIC). Non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of the data can be in the order of seconds. Real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of the data is in the order of tens of milliseconds.

[0145] Near-real-time RIC is used for model training and inference. For example, it is used to train AI models and use them for inference. Near-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data.

[0146] Optionally, the near real-time RIC may deliver the inference results to the RAN node and / or the terminal.

[0147] Optionally, the inference results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near-real-time RIC delivers the inference results to the DU, which then sends them to the RU.

[0148] Non-real-time RIC is also used for model training and inference. For example, it is used to train AI models and use them for inference. Non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals.

[0149] Optionally, the inference results may be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the inference results to the DU, which then sends them to the RU.

[0150] The near-real-time RIC and the non-real-time RIC may also be provided as separate devices. Alternatively, the near-real-time RIC and the non-real-time RIC may also be provided as part of other devices. For example, the near-real-time RIC may be provided in a RAN node (e.g., a CU or DU), while the non-real-time RIC may be provided in an OAM, a cloud server, a core network device, or other devices.

[0151] FIG3 is a schematic diagram of a communication system applicable to an embodiment of the present application. As shown in FIG3 , the communication system may include at least one network device, such as network device 110. Communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130. Network device 110 and terminal devices (such as terminal device 120 and terminal device 130) may communicate via wireless links. Communication devices in the communication system, such as network device 110 and terminal device 120, may communicate using multi-antenna technology.

[0152] Figure 4 is a schematic diagram of another communication system applicable to embodiments of the present application. Compared to the communication system shown in Figure 3, the communication system shown in Figure 4 also includes an AI device 140, which is used to perform AI-related operations, such as constructing a training data set or training an AI model.

[0153] In one possible implementation, the network device 110 sends data related to the training of the AI ​​model to the AI ​​device 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​device 140 sends the results of the operations related to the AI ​​model to the network device 110, and forwards them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a part of the trained AI model is deployed on the network device 110, and the other part is deployed on the terminal device. Alternatively, the trained AI model is deployed on the network device 110. Alternatively, the trained AI model is deployed on the terminal device.

[0154] It should be understood that FIG4 illustrates only an example of a direct connection between AI device 140 and network device 110. In other scenarios, AI device 140 may also be connected to a terminal device; AI device 140 may also be connected to both network device 110 and a terminal device simultaneously; AI device 140 may also be connected to network device 110 through a third-party device, etc. Therefore, this application does not limit the connection relationship between the AI ​​device and other devices.

[0155] The AI ​​device 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG. 3 .

[0156] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In actual applications, the communication system may include multiple network devices (such as network device 110 and network device 150 (not shown in Figure 3)) and may also include multiple terminal devices. Therefore, this application does not limit the number of network devices and terminal devices included in the communication system.

[0157] Next, some technical concepts involved in this application are briefly described.

[0158] (1) AI model:

[0159] An AI model is an algorithm or computer program that can implement AI functions. It represents the mapping relationship between the model's input and output. An AI model can be understood as a function model that maps inputs of a certain dimension to outputs of a certain dimension. Its model parameters are obtained through machine learning training. For example, f(x) = a*x 2+b is a quadratic function model, which can be considered an AI model. a and b correspond to the parameters of the AI ​​model, which can be obtained through machine learning training. An AI model can also be called a model, AI function, or feature. An AI function can correspond to one or more AI models.

[0160] The type of AI model can be a neural network, linear regression model, decision tree model, support vector machine (SVM), Bayesian network, Q learning model or other machine learning (ML) model.

[0161] (2) Two-end model:

[0162] The two-end model can also be called a bilateral model, collaborative model, dual model, or two-side model. A two-end model is a model composed of multiple sub-models. The sub-models that make up the model must match each other. These sub-models can be deployed on different nodes.

[0163] The embodiments of the present application relate to an encoder for compressing CSI and a decoder for recovering CSI. The encoder and decoder are used in matching manner, and it can be understood that the encoder and decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched with the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and one-to-one corresponding. Among them, the encoder may also include a quantization module, which can be used to quantize the output of the AI ​​model in the encoder. The decoder may include an inverse quantization module, which can be used to inverse quantize the feedback information of the received channel information to obtain the input of the AI ​​model in the decoder. Inverse quantization can also be replaced by dequantization.

[0164] In one possible design, a set of matched encoders and decoders can be two parts of the same auto-encoder (AE). The AE model in which the encoder and decoder are deployed on different nodes is a typical bilateral model. The encoder and decoder of the AE model are usually a jointly trained encoder and decoder used in combination. An autoencoder is a neural network for unsupervised learning. Its characteristic is that it uses input data as label data, so an autoencoder can also be understood as a neural network for self-supervised learning. An autoencoder can be used for data compression and recovery. For example, the encoder in the autoencoder can compress (encode) data A to obtain data B; the decoder in the autoencoder can decompress (decode) data B to recover data A. Alternatively, it can be understood that the decoder is the inverse operation of the encoder. For a description of the encoder and decoder, please refer to Figure 5.

[0165] Figure 5 is a schematic diagram of the relationship between the encoder and the decoder. As shown in Figure 5, the encoder processes the input V to obtain the processed result z, and the decoder can decode the encoder output z into the desired output V'.

[0166] The autoencoding model in the embodiments of the present application may include an encoder deployed on the terminal device side and a decoder deployed on the network device side, or an encoder deployed on the terminal device side and a decoder deployed on another terminal device side, or an encoder deployed on the network device side and a decoder deployed on another network device side. In this application, the model on the encoder side is referred to as the first AI model, and the model on the decoder side is referred to as the second AI model.

[0167] (3) Neural network (NN):

[0168] Neural networks are a specific implementation of AI or machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, giving them the ability to learn arbitrary mappings.

[0169] A neural network can be composed of neural units, which can be represented by x s A neural network is a network formed by connecting many of the above-mentioned single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0170] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this disclosure can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0171] CNN is a neural network specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling along the time axis) and image data (discrete sampling along two dimensions) can both be considered grid-like data. CNNs do not utilize all input information at once for computation. Instead, they use a fixed-size window to intercept a portion of the information for convolution operations, significantly reducing the computational complexity of model parameters. Furthermore, depending on the type of information intercepted by the window (e.g., people and objects in an image represent different types of information), each window can use a different convolution kernel, enabling CNNs to better extract features from the input data.

[0172] RNNs are a type of DNN that utilizes feedback time series information. Their input consists of a new input value at the current moment and their own output value at the previous moment. RNNs are suitable for capturing temporally correlated sequence features and are particularly well-suited for applications such as speech recognition and channel encoding and decoding.

[0173] The characteristic of FNN network is that neurons in adjacent layers are fully connected to each other, which makes FNN usually require a large amount of storage space and leads to high computational complexity.

[0174] The aforementioned FNNs, CNNs, and RNNs are all constructed based on neurons. As mentioned earlier, each neuron performs a weighted summation operation on its input values, and then applies this weighted summation to a nonlinear function to produce an output. The weights of the weighted summation operation of neurons in a neural network, as well as the nonlinear function, are called the parameters of the neural network. The parameters of all neurons in a neural network constitute the parameters of the neural network.

[0175] (4) Dataset:

[0176] A dataset refers to the data used for model training, verification, and testing in machine learning. The quantity and quality of the data will affect the effectiveness of machine learning.

[0177] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0178] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0179] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0180] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function, or objective function. These are important equations used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0181] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0182] (5) AI model design:

[0183] The design of an AI model primarily involves data collection (e.g., collecting training data and / or inference data), model training, and model inference. Furthermore, it can also include the application of inference results.

[0184] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The inference process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training phase of a terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training phase of a network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training phase of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, the model inference phase corresponding to the encoder is performed in the terminal device, and the model inference phase corresponding to the decoder is performed in the network device.

[0185] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0186] (6) Channel information:

[0187] In a communication system (e.g., an LTE or NR communication system), network equipment determines one or more of the following configurations, including resources, MCS, and precoding, for scheduling a terminal device's downlink data channel based on channel information. Channel information, also known as channel state information (CSI) or channel environment information, is information that reflects channel characteristics and quality.

[0188] Channel information measurement refers to the receiving end solving the channel information based on the reference signal sent by the transmitting end, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of a channel state information reference signal (CSI-RS), a synchronization signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), or a demodulation reference signal (DMRS). One or more of CSI-RS, SSB, and DMRS can be used to measure downlink channel information. SRS and / or DMRS can be used to measure uplink channel information.

[0189] The channel information may be determined based on a channel measurement result of a reference signal. Alternatively, the channel information may be a channel measurement result of a reference signal. In an embodiment of the present application, the channel measurement result of a reference signal or the channel measurement result may also be replaced with the channel information.

[0190] Taking the FDD communication scenario as an example, in the FDD communication scenario, since the uplink and downlink channels are not reciprocal or the reciprocity of the uplink and downlink channels cannot be guaranteed, the network device needs to obtain the downlink CSI through the uplink feedback of the terminal device. The network device usually sends a downlink reference signal to the terminal device, and the terminal device receives the downlink reference signal. Since the terminal device knows the sending information of the downlink reference signal, the terminal device can perform channel measurement and interference measurement based on the received downlink reference signal to estimate (measure) the downlink channel experienced by the downlink reference signal. The terminal device generates the downlink CSI based on the downlink channel matrix obtained by the measurement. The terminal device generates a CSI report according to the method predefined by the protocol or the method configured by the network device, and feeds it back to the network device so that it can obtain the downlink CSI.

[0191] In this application, the meaning of CSI is broader than that of CSI in traditional schemes, and is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI). It can also be channel response information (such as channel response matrix, frequency domain channel response information, 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) and one or more thereof.

[0192] The RI indicates the recommended number of downlink transmission layers for the reference signal receiver, such as a terminal device. The CQI indicates the modulation and coding scheme supported by the current channel conditions determined by the reference signal receiver, such as a terminal device. The PMI indicates the recommended precoding layer for the reference signal receiver, such as a terminal device. The number of precoding layers indicated by the PMI corresponds to the RI.

[0193] As previously described, channel information can be obtained by measuring the reference signal. Feedback information can be obtained by compressing and / or quantizing the channel information. Feedback information can be reported via a channel information report. Therefore, feedback information can also be referred to as a channel report. In this embodiment of the present application, a channel report may include at least one sub-channel report.

[0194] Channel information can be restored by performing decompression and / or inverse quantization operations on the feedback information.

[0195] Feedback information may also be referred to as 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.

[0196] The recovered channel information may also be referred to as CSI recovery information.

[0197] As the size of MIMO system antenna arrays continues to grow, the number of supported antenna ports increases, and the dimensions of the corresponding channel matrix and precoding matrix grow. In order to enable terminal devices to estimate (measure) the downlink channel, the overhead of network equipment sending reference signals increases. At the same time, the error of approximating large-scale channel matrices and precoding matrices with a limited number of predefined codewords will increase. One way to improve channel recovery accuracy is to increase the number of codewords in the codebook, but this will also lead to an increase in the overhead of CSI feedback (including the corresponding codeword number and one or more weighting coefficients), thereby reducing the available resources for data transmission and causing system capacity loss.

[0198] The introduction of AI technology into wireless communication networks has resulted in an AI-based CSI feedback method, known as AI-CSI feedback. Terminal devices use AI models to compress and feedback CSI, and network devices use them to recover the compressed CSI. AI-based CSI feedback transmits a sequence (such as a bit sequence), resulting in lower overhead than traditional CSI feedback. Furthermore, AI models have stronger nonlinear feature extraction capabilities, enabling more efficient compression and representation of channel information and more effective channel recovery based on feedback information compared to traditional solutions.

[0199] CSI feedback can be implemented based on the AE's AI model. For example, in Figure 5, the encoder can be a CSI generator, and the decoder can be a CSI reconstructor. For example, the encoder can be deployed in a terminal device, and the decoder can be deployed in a network device.

[0200] The channel information V is converted into CSI feedback information z by the encoder, and the channel information is reconstructed by the decoder to obtain the recovered channel information V'.

[0201] Channel information V can be obtained through channel information measurement. For example, channel information V can include the eigenvector matrix (a matrix composed of eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and / or quantization operations of the eigenvector matrix based on the codebook in related schemes are replaced by operations in which the encoder processes the eigenvector matrix to obtain CSI feedback information z. The decoder processes the CSI feedback information z to obtain recovered channel information V'.

[0202] The following further illustrates the training process and reasoning process of the AI ​​model in the embodiments of the present application.

[0203] The training data used to train AI models includes training samples and sample labels. For example, the training samples are channel information measured by the terminal device, and the sample labels are the actual channel information, i.e., the true value CSI. If the encoder and decoder belong to the same autoencoder, the training data can only include the training samples, or the training samples are the sample labels.

[0204] In the field of wireless communications, the true CSI may be high-precision CSI.

[0205] The specific training process is as follows: the model training node uses an encoder to process the channel information, that is, the training sample, to obtain CSI feedback information, and uses a decoder to process the feedback information to obtain the recovered channel information, that is, the CSI recovery information. Then, the difference between the CSI recovery information and the corresponding sample label is calculated, that is, the value of the loss function, and the parameters of the encoder and decoder are updated according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, that is, the loss function is minimized. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeating the above operations can obtain an encoder and decoder that meet the target requirements. The above-mentioned model training node can be a terminal device, a network device, or other network element with AI function in a communication system. The implementation of the AI ​​model can be a hardware circuit, software, or a combination of software and hardware. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application or software application, etc.

[0206] As described in the background technology section, the first device (e.g., terminal device) and the second device (e.g., network device) are each deployed with an AI model. For example, the first device is deployed with a first AI model (e.g., encoder), and the second device is deployed with a second AI model (e.g., decoder). The first device can use the channel measurement result (represented by H) as the input of the first AI model and output a channel report (represented by c). The second device can use the received channel report (represented by ) as the input of the second AI model, and output the recovered channel measurement results (in ). When the first device and the second device have inconsistent rhythms in updating the status information of the AI ​​model, this may result in a loss of channel report feedback performance, as shown in FIG6 .

[0207] FIG6 is a schematic diagram of an application scenario of an embodiment of the present application. As shown in FIG6:

[0208] 1. The first device inputs e0 (the value of the state information of the first AI model) and H1 into the first AI model, outputs c1, and sends c1 to the second device. The first device uses H1 to update the value of the state information of the first AI model to e1. ​​The second device inputs d0 (the value of the state information of the second AI model) and (The second device receives the data based on c1) and inputs it to the second AI model, outputting Second device use The value of the updated state information of the second AI model is d1.

[0209] 2. The first device inputs e1 and H2 into the first AI model, outputs c2, and sends c2 to the second device. The first device uses H2 to update the state information of the first AI model to e2. The second device uses d1 and (The second device receives the data based on c2) and inputs it to the second AI model, outputting Second device use The value of the updated state information of the second AI model is d2.

[0210] 3. The first device inputs e2 and H3 into the first AI model, outputting c3, ​​but fails to send c3 to the second device. The first device uses H3 to update the state information of the first AI model to e3. The second device maintains the state information of the second AI model unchanged.

[0211] 4. The first device inputs e3 and H4 into the first AI model, outputs c4, and sends c4 to the second device. The first device uses H4 to update the state information of the first AI model to e4. The second device inputs d2 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d4.

[0212] In summary, the failure of channel report transmission between the first device and the second device may result in inconsistent rhythms in the values ​​of the status information of the AI ​​model between the first device and the second device, which may result in loss of channel report feedback performance.

[0213] In view of this, the present application provides a communication method and a communication device, which can make the rhythm of the value of the status information of the AI ​​model between the first device and the second device consistent, so as to improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0214] For a description of the consistency in the rhythm of the values ​​of the status information of the AI ​​model updated between the first device and the second device, please refer to Figure 7.

[0215] FIG7 is a schematic diagram showing that the first device and the second device have the same rhythm in updating the status information of the AI ​​model. As shown in FIG7:

[0216] When all channel information is successfully fed back, a schematic diagram is shown in FIG7 (a):

[0217] 1. The first device inputs e0 and H1 into the first AI model, outputs c1, and sends c1 to the second device. The first device uses H1 to update the state information of the first AI model to e1. ​​The second device inputs d0 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d1.

[0218] 2. The first device inputs e1 and H2 into the first AI model, outputs c2, and sends c2 to the second device. The first device uses H2 to update the state information of the first AI model to e2. The second device uses d1 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d2.

[0219] 3. The first device inputs e2 and H3 into the first AI model, outputs c3, and sends c3 to the second device. The first device uses H3 to update the state information of the first AI model to e3. The second device uses d3 and (The second device receives the data based on c3) and inputs it to the second AI model, outputting Second device use The value of the updated state information of the second AI model is d3.

[0220] When the channel information is not fully fed back successfully, one of the situations is shown in FIG7(b):

[0221] 1. The first device inputs e0 and H1 into the first AI model, outputs c1, and sends c1 to the second device. The first device uses H1 to update the state information of the first AI model to e1. ​​The second device inputs d0 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d1.

[0222] 2. The first device inputs e1 and H2 into the first AI model, outputs c2, and sends c2 to the second device. The first device uses H2 to update the state information of the first AI model to e2. The second device uses d1 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d2.

[0223] 3. When the first device fails to successfully send c3 obtained based on H3 to the second device, the first device inputs e2 and H4 into the first AI model, outputs c4, and sends c4 to the second device. The first device uses H4 to update the state information of the first AI model to e4. The second device uses d2 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d4.

[0224] When the channel information is not fully fed back successfully, another situation is shown in FIG7 (c):

[0225] 1. The first device inputs e0 and H1 into the first AI model, outputs c1, and sends c1 to the second device. The first device uses H1 to update the state information of the first AI model to e1. ​​The second device inputs d0 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d1.

[0226] 2. The first device inputs e1 and H2 into the first AI model, outputs c2, and sends c2 to the second device. The first device uses H2 to update the state information of the first AI model to e2. The second device 2 inputs d1 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d2.

[0227] 3. The first device inputs e2 and H3 into the first AI model, outputs c3 (including partial content c′3), and sends c′3 to the second device. The first device uses H3 to update the state information of the second AI model to the value e3. The second device inputs d2 and Input to the second AI model, output Second device use The value of the updated state information of the second AI model is d3.

[0228] Among them, c1, c2 and c3 are channel reports including all contents, and c′3 is a channel report including partial contents.

[0229] The status information of the present application may include any one or more of the following: cache information, storage information, intermediate information (for example, intermediate information generated by the AI ​​model), internal information (for example, internal information of the device where the AI ​​model is deployed or internal information of the AI ​​model), parameter information generated or updated by the AI ​​model, etc.

[0230] The first device and the second device can both determine whether to update the value of the AI ​​model's state information based on the status of the channel report, so that the first device and the second device can update the value of the AI ​​model's state information at the same pace. This is further described below with reference to Figures 8 to 10.

[0231] For ease of understanding and explanation, the following describes the communication method of an embodiment of the present application by taking the interaction between a first device and a second device as an example.

[0232] The first device may be a device on the first AI model side, or a chip or circuit on the device on the first AI model side. The device on the first AI model side may be replaced by a device on the terminal device side or a device on the network device side. The terminal device side may include at least one of the terminal device and the AI ​​entity on the terminal device side. The AI ​​entity on the terminal device side may be the terminal device itself, or an AI entity serving the terminal device, such as a server, such as an OTT server or a cloud server. The network device side may include at least one of the network device and the AI ​​entity on the network device side. The AI ​​entity on the network device side may be the network device itself, or an AI entity serving the network device, such as an RIC, OAM, or a server, such as an OTT server or a cloud server.

[0233] The second device may be a device on the second AI model side, or a chip or circuit for the device on the second AI model side. The device on the second AI model side may be replaced by a device on the terminal device side or a device on the network device side. The terminal device side may include at least one of the terminal device or an AI entity on the terminal device side. The AI ​​entity on the terminal device side may be the terminal device itself, or an AI entity serving the terminal device, such as a server, such as an OTT server or a cloud server. The network device side may include at least one of the network device or an AI entity on the network device side. The AI ​​entity on the network device side may be the network device itself, or an AI entity serving the network device, such as a RIC, OAM, or a server, such as an OTT server or a cloud server.

[0234] For ease of description, the first device shown in Figures 8 and 9 may be a terminal device, and the second device may be a network device. The first device and the second device shown in Figure 10 may be AI entities serving the terminal device and the network device, respectively.

[0235] The communication method and communication device according to the embodiments of the present application are described below with reference to the accompanying drawings.

[0236] FIG8 is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present application. As shown in FIG8 , the method includes:

[0237] Optionally, S801a, the second device sends a first reference signal to the first device.

[0238] Correspondingly, the first device receives the first reference signal (see the reference signal corresponding to H3 in FIG6 ).

[0239] For example, the first reference signal is used for channel measurement or for obtaining channel information. The first device can obtain channel information, channel report, or channel measurement information, etc. by measuring the first reference signal.

[0240] In one example, the first reference signal may be a CSI-RS.

[0241] In another example, the first reference signal may be a DMRS.

[0242] In summary, the embodiments of the present application do not limit the type of the first reference signal, which may be a signal used for channel measurement in an existing standard or a signal used for channel measurement in a future standard, and is not limited thereto.

[0243] In one possible implementation, before the second device sends the first reference signal to the first device, the second device has already sent at least one reference signal to the first device. For ease of description, the at least one reference signal may be referred to as a historical reference signal.

[0244] In one possible implementation, a reference signal whose sending time unit is before the sending time unit of the first reference signal may be referred to as a historical reference signal, or in other words, the sending time unit of the historical reference signal is before the sending time unit of the first reference signal.

[0245] For ease of description, the historical reference signal is hereinafter referred to as the second reference signal (see the reference signal corresponding to H2 in FIG6 ). The second reference signal is transmitted before the first reference signal. In other words, after the second device transmits the second reference signal to the first device, it transmits the first reference signal to the first device. In other words, after the second device transmits the second reference signal to the first device, the next reference signal transmitted by the second device to the first device is the first reference signal.

[0246] The first device may, upon receiving a reference signal, provide the second device with a channel report corresponding to the reference signal. Alternatively, the first device may, upon receiving multiple reference signals, provide the second device with channel reports corresponding to each of the multiple reference signals. For ease of description, the following description will not focus on the temporal correlation between the first device receiving the reference signal and the first device providing the corresponding channel report.

[0247] In the embodiment of the present application, the time unit includes but is not limited to: time, period, moment, time slot, symbol or mini-symbol, etc. In addition, the explanation of the time unit appearing below can be referred to the description here and will not be repeated here.

[0248] Optionally, S801b, the first device obtains a first channel report.

[0249] In one possible implementation, the first device obtains the first channel report, including:

[0250] The first device determines the first channel report according to the first value of the state information of the first AI model, or in other words, the first channel report is determined according to the first value of the state information of the first AI model.

[0251] For example, the first device measures the first reference signal, obtains the channel measurement result corresponding to the first reference signal, and inputs the channel measurement result of the first reference signal (see H3 in Figure 6) and the first value of the status information of the first AI model (see e2 in Figure 6) into the first AI model to obtain a first channel report (see c3 in Figure 6).

[0252] When the first channel report is determined based on the first value of the state information of the first AI model, the first device can determine whether to update the first value of the state information of the first AI model based on the state of the first channel report. When the second device does not receive the first channel report, the second device does not update the value of the state information of the second AI model, and the first device does not update the value of the state information of the first AI model. In this way, the first and second devices have a consistent rhythm for updating the state information values ​​of the AI ​​models, which can improve the feedback performance of the channel report and, in turn, improve the channel information recovery performance and the robustness of the recovery performance.

[0253] The first value of the state information of the first AI model is determined by the first device updating the second value of the state information of the first AI model (see e1 in FIG. 6 ) using the channel measurement result of the second reference signal (see H2 in FIG. 6 ). The first device can obtain a second channel report (see c2 in FIG. 6 ) based on the second value and the channel measurement result of the second reference signal.

[0254] In other words, each time the first device obtains a channel report, it can use the channel report to update the value of the state information of the first AI model. For example, the first device uses the second channel report to update the second value to obtain the first value. Correspondingly, when the value of the state information of the first AI model is updated, the first device can use the first channel report to update the first value, and the updated value can be used to generate the next channel report.

[0255] In an embodiment of the present application, the first device can generate a channel report based on the channel report configuration information or predefined configuration of the network device. For example, the format of the channel report generated by the first device conforms to the configuration or predefined configuration of the network device, or in other words, the second device can understand the channel report generated by the first device. The channel report configured by the channel report configuration information can also be referred to as an expected channel report or a target channel report. The channel report configured by the channel report configuration information or the predefined configuration can be understood as a channel report including all content.

[0256] S801. The first device obtains a status of a first channel report.

[0257] For example, after the first device obtains the first channel report, the first device may send the first channel report to the second device, or the first device may not send the first channel report to the second device, or the first device may send the first channel report including partial content to the second device. Therefore, the first channel report has corresponding statuses for different scenarios.

[0258] Exemplary:

[0259] Scenario #1:

[0260] The first device sends a first channel report to the second device (see (a) of FIG. 7 ).

[0261] When the first device sends the first channel report to the second device, the first channel report is in a completed transmission state or is not in a discarded state or is not in an ignored state or is not in a skipped transmission state, etc.

[0262] In this way, the first device can use the first channel report to update the first value of the status information of the first AI model, and the second device can also update the value of the status information of the second AI model. This can make the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device consistent, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0263] Scenario #2:

[0264] The first device does not send the first channel report to the second device (see FIG. 7( b ) ).

[0265] When the first device does not send the first channel report to the second device, the first channel report is in a discarded state, an incomplete transmission state, an incomplete transmission state of all contents, an ignored state, a skipped transmission state, and the like.

[0266] In one example, after the first device obtains the first channel report, the first device may be unable to send the first channel report to the second device due to certain factors (described below). Accordingly, the first device may discard the first channel report, ignore the sending of the first channel report, or skip sending the first channel report.

[0267] In this way, the first device does not use the first channel report to update the first value of the status information of the first AI model, and the second device does not update the value of the status information of the second AI model. This can make the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device consistent, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0268] Scenario #3:

[0269] The first device sends a first channel report including partial content to the second device (see FIG7(c) ).

[0270] A complete first channel report includes three parts: A, B, and C (or, the first channel report includes sub-channel report A, sub-channel report B, and sub-channel report C). When the first device sends the first channel report including A to the second device, the first channel report is in a partial content sending state, or the first channel report is in a partial content discarding state, or the first channel report is in a partial content ignoring sending state, or the first channel report is in a partial content skipping sending state, etc.

[0271] A possible example is that when the first device sends a first channel report including partial content to the second device, the partial content may be specified by the protocol. For example, the protocol specifies the transmission of part A, and the first device sends the first channel report including part A to the second device.

[0272] Another possible example is that when a first device sends a first channel report including partial content to a second device, the partial content may be determined based on the priority of the content in the first channel report, for example, the priority of part A is higher than the priority of part B, and the first device sends a first channel report including part A to the second device.

[0273] In the embodiment of the present application, the priority of the above content can be determined according to the following method:

[0274] 1) The protocol specifies the calculation priority between the contents. For example, the calculation priority of part A is higher than the calculation priority of part B. The first device preferably transmits the first channel report including part A.

[0275] 2) When multi-stream transmission is performed between the second device and the first device, the priority of the information of the first stream is higher than the priority of the information of the second stream. For example, the information of the first stream is part A and the information of the second stream is part B. The first device preferentially transmits the first channel report including part A.

[0276] Therefore, the first device can determine the part of content based on the above content.

[0277] In an embodiment of the present application, when a first device sends a first channel report including partial content to a second device, the first channel report including partial content can still be referred to as a first channel report, or in other words, both the first device and the second device can determine whether the first channel report includes all content based on the content included in the first channel report or the length and / or format of the included content.

[0278] For example:

[0279] For example, the first channel report includes all contents, and the first device and the second device determine that the first channel report is in a state of transmitting all contents.

[0280] For example, the first report includes partial content, and the first device and the second device determine that the first channel report is in a partial content transmission state.

[0281] In summary, the status of the first channel report is related to whether the first device sends the first channel report or the content included in the first channel report sent by the first device to the second device.

[0282] In one possible implementation, the state of the first channel report may be the transmission state of the first channel report. For example:

[0283] For example, the first device sends a first channel report to the second device, and the first channel report is in a completed transmission state;

[0284] ◆For example, the first device does not send the first channel report to the second device, and the first channel report is in an uncompleted transmission state;

[0285] ◆For example, the first device sends a first channel report including partial content (or partial sub-channel report) to the second device, and the first channel report is in a state where the partial content (or partial sub-channel report) has been transmitted.

[0286] The completed transmission state can also be understood as a state in which all contents are sent. For example, the first device sends a first channel report including all contents to the second device, and the first channel report is in a state in which all contents are sent.

[0287] The incomplete transmission state can also be understood as a state where all contents have not been sent. For example, the first device has not sent the first channel report including all contents to the second device, and the first channel report is in a state where all contents have not been sent.

[0288] The state where the partial content transmission is completed can also be understood as the state where the partial content is not sent. For example, the first device sends a first channel report including partial content to the second device, and the first channel report is in the partial content sending state.

[0289] In a possible implementation, the state reported by the first channel may also be a discarded state reported by the first channel. For example:

[0290] ◆For example, the first device does not send the first channel report to the second device, and the first channel report is in a discarded state;

[0291] ◆For example, the first device sends a first channel report to the second device, and the first channel report is in a non-discarded state;

[0292] ◆For example, the first device sends a first channel report including partial content, that is, not including all content, to the second device, and the first channel report is in a partial content discarding state.

[0293] The first channel report being in a discarded state can also be understood as: the first device discards the first channel report, or the first device ignores the sending of the first channel report, or the first device skips the sending of the first channel report, and so on.

[0294] The first channel report being in a non-discarded state can also be understood as: the first device sends the first channel report, or the first device does not ignore the sending of the first channel report, or the first device does not skip the sending of the first channel report, etc.

[0295] The first channel report being in a partial content discarding state can also be understood as: the first device sends a first channel report, but the first channel report does not include all content, and the first device discards part of the content or skips sending the part of the content (or part of the sub-channel report), etc.

[0296] In the embodiment of the present application, the first device can determine the status of the first channel report according to the following method.

[0297] Exemplary:

[0298] The first channel reports that it is in the discarding state:

[0299] Method #a:

[0300] The first device may determine whether the first channel report is in a discarded state according to a conflict situation between resources.

[0301] The first device can determine whether the first channel report is in a discarded state based on the conflict situation between the resources used to transmit the first channel report and the resources used to transmit other reports (such as hybrid automatic repeat request (HARQ) report or scheduling request (SR) report, etc.), or in other words, the first device can determine whether to discard the first channel report based on the conflict situation between the resources used to transmit the first channel report and the resources used to transmit other reports.

[0302] Scenario #a1:

[0303] The resources used to transmit the first channel report and the resources used to transmit the HARQ report overlap in the time domain.

[0304] For example, the resources used to transmit the first channel report include first time domain resources, and the resources used to transmit the HARQ report include second time domain resources. The first time domain resources and the second time domain resources overlap in the time domain, or in other words, there are common time domain resources between the first time domain resources and the second time domain resources.

[0305] Alternatively, the first device does not support simultaneous transmission of the first channel report and the HARQ report. Since the HARQ report has a higher priority than the first channel report, the first device may discard the first channel report. In this case, the first device and the second device have the same understanding of the first device discarding the first channel report. The first device does not update the value of the state information of the first AI model. The first device's action of not updating the value of the state information of the first AI model is consistent with the second device's expectation, or the second device may expect the first device not to update the value of the state information of the first AI model.

[0306] The above-mentioned overlap can also be understood as conflict, collision, collision, etc.

[0307] Scenario #a2:

[0308] The resources used to transmit the first channel report and the resources used to transmit the SR report overlap in the time domain.

[0309] For example, the resources used to transmit the first channel report include first time domain resources, and the resources used to transmit the SR report include third time domain resources. The first time domain resources and the third time domain resources overlap in the time domain, or in other words, there are common time domain resources between the first time domain resources and the third time domain resources.

[0310] Alternatively, the first device does not support simultaneous transmission of the first channel report and the SR report. Since the SR report has a higher priority than the first channel report, the first device can discard the first channel report. In this case, the first device and the second device have the same understanding of the first device discarding the first channel report. The first device does not update the value of the first AI model's status information at this time. The first device's action of not updating the value of the first AI model's status information is consistent with the second device's expectation, or the second device can expect the first device not to update the value of the first AI model's status information.

[0311] Scenario #a3:

[0312] The priority of the first channel is lower than that of the second channel. The second channel overlaps with the first channel in the time domain. The first channel is used to carry the first channel report, and the second channel is used to carry uplink information.

[0313] For example, the resources used to transmit the first channel report include the first channel, the channel used to carry uplink information is the second channel, the first channel and the second channel overlap in the time domain, or in other words, there are common time domain resources between the first channel and the second channel.

[0314] After obtaining the first channel report, the first device determines a first channel for carrying the first channel report and a second channel for carrying uplink information. When the first channel and the second channel overlap in the time domain, the priority of the first channel is lower than the priority of the second channel, and the first device discards the first channel report, or in other words, ignores or skips the transmission of the first channel report.

[0315] When ultra-reliable and low-latency communication (URLLC) and eMBB enhanced mobile broadband (EMBB) services coexist, the URLLC service may have higher priority than the EMBB service. To distinguish between these two services, network equipment will configure different priorities for the physical uplink control channel (PUCCH) / physical uplink shared channel (PUSCH), which is reflected in the priority index. When a high-priority channel (e.g., a smaller priority index) and a low-priority channel (e.g., a larger priority index) overlap in the time domain, the first device will discard the transmission of the low-priority channel. If the first channel report was originally intended to be carried on the low-priority channel, the first channel report will not be actually sent due to the discarding of the low-priority channel. In this case, the first device and the second device have the same understanding of the first device discarding the first channel report. The first device does not update the value of the status information of the first AI model at this time. The action of the first device not updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect that the first device will not update the value of the status information of the first AI model.

[0316] Scenario #a4:

[0317] The channel used to carry the first channel report conflicts with a downlink symbol or a flexible symbol configured or indicated by the network device.

[0318] The PUCCH / PUSCH channel carrying the first channel report may conflict with the downlink symbol or flexible symbol configured or indicated by the network device (which can also be understood as overlap, overlap in the time domain, or collision in the time domain, etc.). In order to avoid the occurrence of the conflict, the first device may discard the PUCCH / PUSCH channel carrying the first channel report, resulting in the first channel report being unable to be actually sent. In this case, the first device and the second device have the same understanding of the first device discarding the first channel report. The first device does not update the value of the status information of the first AI model at this time. The action of the first device not updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect that the first device will not update the value of the status information of the first AI model.

[0319] In one example, the PUCCH / PUSCH channel carrying the first channel report is a semi-statically configured channel, which conflicts with the downlink symbol or flexible symbol configured by the network device, for example, the downlink symbol or flexible symbol configured by the configuration (such as tdd-UL-DL-ConfigurationCommon or tdd-UL-DL-ConfigDedicated) of the channel or information corresponding to the downlink symbol or flexible symbol (SS / PBCH block by ssb-PositionsInBurst, or belonging to a CORESET associated with a Type0-PDCCH CSS set).

[0320] In another example, the PUCCH / PUSCH channel carrying the first channel report is a semi-statically configured channel, which conflicts with the downlink symbol or flexible symbol indicated by the network device. For example, the network device indicates one or more symbols as downlink symbols or flexible symbols through downlink control information (DCI), which are used for the transmission of downlink information.

[0321] In summary, the first device can determine the status of the first channel report based on whether there is a need to transmit a report with a higher priority. When the first device determines that there is a need to transmit a report with a higher priority, the first device can discard the first channel report and maintain the value of the state information of the first AI model unchanged. In other words, the first device maintains the value of the state information of the first AI model at the first value.

[0322] In this way, the first device can determine whether the first channel report is in a discarded state based on one or more of the above. When it is determined that the first channel report is in a discarded state, the first device does not update the value of the state information of the AI ​​model. Since the first channel report is not received, the second device does not update the value of the state information of the AI ​​model. In this way, the rhythm of updating the value of the state information of the AI ​​model between the first device and the second device is consistent, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0323] The first channel reports that it is in a partial content sending state:

[0324] Method #b:

[0325] The first device may determine whether the first channel report is in a partial content sending state according to resources used to generate or transmit the first channel report.

[0326] The first device can determine whether the first channel report is in a partial content sending state based on the resources used to transmit the first channel report and the resources configured or indicated by the network device for transmitting the first channel report, or the first device can determine whether the first channel report is in a partial content sending state based on the number of resources used to generate the first channel report.

[0327] Scenario #b1:

[0328] The processing resources available for calculation are insufficient to generate a first channel report including all content. The first channel report including all content can also be replaced by an expected first channel report or a target channel report, etc. In other words, the first channel report expected by the second device is a channel report including all content, or the target channel report that the second device expects to receive is a channel report including all content.

[0329] The processing resources available for calculation in the first device (such as one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a network processing unit (NPU)) are insufficient to generate a first channel report including all content.

[0330] For example, taking the CPU as an example, the unoccupied CPU resources in the first device are N CPU -L, N CPU is the total amount of CPU resources owned by the first device, L is the amount of CPU resources used by the first device, the first channel report includes M sub-channel reports (the sub-channel report can be understood as the aforementioned part A or part B, etc.), and the CPU resources required for each sub-channel report are respectively , n is the index of the sub-channel report in the first channel report, M is the number of sub-channel reports in the first channel report, and the CPU resources required for calculating all sub-channel reports in the first channel report are The first channel report that can be generated by the first device must meet the requirements When it is not satisfied This will result in the inability to generate and then send a complete first channel report. In this case, the first device and the second device have the same understanding that the first device discards part of the content in the first channel report. The first device does not update the value of the status information of the first AI model at this time. The action of the first device not updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device not to update the value of the status information of the first AI model. Alternatively, the first device and the second device have the same understanding that the first device discards part of the content in the first channel report. The first device can update the value of the status information of the first AI model. The action of the first device updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device to update the value of the status information of the first AI model.

[0331] Scenario #b2:

[0332] The time unit configured or instructed by the network device to report the first channel report does not meet the time requirement for calculation of the first channel report including all contents.

[0333] The time unit in which the network device configures or instructs the first device to report the first channel report does not meet the time requirement for calculating the full content of the first channel report. Accordingly, the first device discards some or all bits (or part of the content or part of the sub-channel report) in the complete first channel report and does not send it to the base station, resulting in the inability to actually send the complete first channel report. In this case, the first device and the second device have the same understanding of the first device discarding part of the content in the first channel report. The first device does not update the value of the state information of the first AI model at this time. The action of the first device not updating the value of the state information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device not to update the value of the state information of the first AI model. Alternatively, the first device and the second device have the same understanding of the first device discarding part of the content in the first channel report. The first device can update the value of the state information of the first AI model. The action of the first device updating the value of the state information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device to update the value of the state information of the first AI model.

[0334] For example, when the network device configures or instructs the first device to report the first channel report, the sending of the first channel report is triggered by the first channel report request. The calculation time requirement of the first device for the first channel report corresponds to the first time unit (Z ref ) and the second time unit Z ref'(n), the first time unit is composed of the sending time of the first channel report request (for example, the last symbol of the physical downlink control channel (PDCCH) carrying the first channel report request) and the first time threshold T proc,csi Determine; the second time unit is reported by the first channel corresponding to the reference signal resource (eg, the last symbol of the reference signal resource) and the second time threshold T ' proc,csi If the network device configures or instructs the first device to report the first channel report at a time unit earlier than the first time unit and / or earlier than the second time unit, the first device discards some or all bits in the first channel report.

[0335] Scenario #b3:

[0336] The network device configures or indicates that the time unit corresponding to the uplink data channel carrying the first channel report does not meet the time requirement for calculation of the first channel report including all contents.

[0337] The network device configures or indicates that the time unit corresponding to the PUSCH channel carrying the first channel report does not meet the calculation time of the first channel report including all the contents, resulting in the inability to actually send the complete first channel report. In this case, the first device and the second device have the same understanding of the first device discarding part of the contents in the first channel report. The first device does not update the value of the status information of the first AI model at this time. The action of the first device not updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device not to update the value of the status information of the first AI model. Alternatively, the first device and the second device have the same understanding of the first device discarding part of the contents in the first channel report. The first device can update the value of the status information of the first AI model. The action of the first device updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device to update the value of the status information of the first AI model.

[0338] Scenario #b4:

[0339] The network device configures or indicates that the transmission resources for carrying the first channel report are insufficient to carry the first channel report including all contents.

[0340] The network device configures or indicates that the transmission resources used to carry uplink control information (UCI) (used to carry the first channel report) are insufficient to carry all information of the first channel report, and the first device discards the first channel report or part of the information with lower priority in the first channel report.

[0341] In one example, because the resources carrying the UCI are insufficient to carry any information in the first channel report, the first device discards the first channel report.

[0342] In another example, because the resources carrying the UCI are insufficient to carry all the information in the first channel report, the first device discards part of the information with lower priority in the first channel report, but still retains part of the information with higher priority for transmission. As a result, the complete first channel report cannot be actually sent. In this case, the first device and the second device have the same understanding of the first device discarding part of the content in the first channel report. The first device does not update the value of the status information of the first AI model at this time. The action of the first device not updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device not to update the value of the status information of the first AI model. Alternatively, the first device and the second device have the same understanding of the first device discarding part of the content in the first channel report. The first device can update the value of the status information of the first AI model. The action of the first device updating the value of the status information of the first AI model is consistent with the expectation of the second device, or the second device can expect the first device to update the value of the status information of the first AI model.

[0343] In summary, the first device may determine the status of the first channel report based on the transmission resources or processing resources of the first channel report. For example, when the first device determines that there are insufficient processing resources or transmission resources, the first device sends the first channel report including partial content to the second device.

[0344] In this way, the first device can determine whether the first channel report is in a partial content sending state based on one or more of the above. When it is determined that the first channel report is in a partial content sending state, the first device can determine whether to update the value of the state information of the AI ​​model. Accordingly, this can avoid the first device updating the value of the state information of the first AI model without determining whether the first channel report is in a full content sending state, thereby supporting the first device and the second device to have a consistent rhythm for updating the value of the state information of the AI ​​model, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0345] S802: The first device determines the value of the status information of the first AI model.

[0346] For example, the value of the state information of the first AI model is related to the state reported by the first channel.

[0347] Exemplarily, the status of the first channel report is the status of sending all content, and the first device updates the value of the status information of the first AI model. For example, the first device uses the first channel report to update the first value of the status information of the first AI model to obtain a new value (see (a) of Figure 7).

[0348] Exemplarily, the status reported by the first channel is a state in which all contents are not sent, and the first device maintains the value of the status information of the first AI model unchanged (see (b) of FIG. 7 ).

[0349] Exemplarily, the status reported by the first channel is a partial content sending status, and the first device does not update the value of the status information of the first AI model. For example, the first device maintains the value of the status information of the first AI model as the first value.

[0350] Exemplarily, the state of the first channel report is a partial transmission state, and the first device updates the value of the state information of the first AI model. For example, the first device uses the channel measurement result of the first reference signal to update the first value of the state information of the first AI model to obtain a new value (see Figure 7 (c)).

[0351] In this way, the first device can determine corresponding behavior based on the status of the first channel report. For example, the first device can determine whether to update the value of the state information of the first AI model or maintain the value of the state information of the first AI model based on the status of the first channel report. In this way, the first and second devices are consistent in the rhythm of updating the value of the AI ​​model state information, which can improve the feedback performance of the channel report and further improve the recovery performance and robustness of the channel information.

[0352] In one possible implementation, the status of the first channel report is a partial sending state, and the value of the status information of the first AI model is related to the offset between the sending time unit of the second channel report and the generation time unit of the third channel report.

[0353] When the first device sends a first channel report including partial content to the second device, the first device can determine whether to update the value of the status information of the first AI model based on the offset between the sending time unit of the second channel report and the generation time unit of the third channel report. While ensuring that the rhythm of the value of the status information of the AI ​​model between the first device and the second device is consistent, the first device can utilize real-time and effective channel information to ensure the performance of channel report feedback.

[0354] The third channel report is the first channel report sent after the first channel report, or the third channel report is the first channel report generated after the first channel report.

[0355] Exemplarily, the first device may determine whether to update the value of the state information of the first AI model based on the offset between the sending time unit of the second channel report and the generation time unit of the third channel report.

[0356] For example, the offset between the sending time unit of the second channel report and the generation time unit of the third channel report is greater than threshold #1 (for example, threshold #1 is 50ms, or threshold #1 is the measurement period of 10 reference signals), and the first device updates the value of the status information of the first AI model, such as the first device uses the channel measurement result of the first reference signal to update the value of the status information of the first AI model to obtain a new value.

[0357] For example, the offset between the sending time unit of the second channel report and the generation time unit of the third channel report is less than threshold #1, and the first device maintains the value of the status information of the first AI model unchanged, such as the value of the status information of the first AI model is the first value.

[0358] When the offset between the sending time unit of the second channel report and the generation time unit of the third channel report is equal to threshold #1, the first device can update the value of the status information of the first AI model or maintain the value of the status information of the first AI model unchanged, which is not limited.

[0359] The threshold #1 is indicated or configured by the network device, or the threshold #1 is predefined.

[0360] The above-mentioned threshold #1 is predefined, which may include: threshold #1 is predefined by the protocol, or threshold #1 is pre-stored, or threshold #1 is pre-burned, etc.

[0361] It should be noted that threshold #1 can be understood as a time length. When the offset between the sending time unit of the second channel report and the generation time unit of the third channel report is greater than threshold #1, the first device can use the channel measurement result of the first reference signal corresponding to the first channel report to update the value of the state information of the first AI model to avoid excessive loss of feedback performance of the channel report. When the offset between the sending time unit of the second channel report and the generation time unit of the third channel report is less than threshold #1, the first device can determine whether to update the value of the state information of the first AI model based on the status of the third channel report. This can support the use of the channel measurement result corresponding to the more complete channel report to update the value of the state information of the first AI model, which is beneficial to improving the feedback performance of the channel report.

[0362] In this way, the first device can determine whether to update the value of the state information of the first AI model based on the relationship between the offset and the threshold. In one possible implementation, the first device can determine the value of the state information of the first AI model based on whether the offset between the transmission time unit of the second channel report and the generation time unit of the third channel report meets the first condition.

[0363] An example of the first condition may be greater than or equal to the aforementioned threshold #1, or may be within a first numerical range. For example, the first numerical range may be 50 ms to 100 ms. Alternatively, for example, the first numerical range may be 5 reference signal measurement periods to 10 reference signal measurement periods.

[0364] For example, if the offset between the sending time unit of the second channel report and the generating time unit of the third channel report satisfies the first condition, the first device updates the value of the state information of the first AI model;

[0365] For another example, the offset between the sending time unit of the second channel report and the generating time unit of the third channel report does not meet the first condition, and the first device maintains the value of the state information of the first AI model unchanged.

[0366] Alternatively, an example of the first condition may be less than the aforementioned threshold #1, or may be not belonging to the first numerical range (for example, belonging to the second numerical range, which does not overlap with the first numerical range).

[0367] The offset between the sending time unit of the second channel report and the generating time unit of the third channel report does not satisfy the first condition, and the first device updates the value of the state information of the first AI model;

[0368] Alternatively, the offset between the sending time unit of the second channel report and the generation time unit of the third channel report meets the first condition, and the first device maintains the value of the state information of the first AI model unchanged.

[0369] In summary, the first device can determine whether to update the value of the state information of the first AI model based on whether the offset between the sending time unit of the second channel report and the generation time unit of the third channel report meets the first condition. For example, when the first device determines to update the value of the state information of the first AI model, the first device uses the channel measurement result of the first reference signal corresponding to the first channel report to update the value of the state information of the first AI model, thereby avoiding excessive loss of the feedback performance of the channel report; when the first device determines not to update the value of the state information of the first AI model, the first device can determine whether to update the value of the state information of the first AI model based on the status of the third channel report. This can support the use of the channel measurement result corresponding to the more complete channel report to update the value of the state information of the first AI model, thereby helping to improve the feedback performance of the channel report.

[0370] It should be noted that the generation time unit of the third channel report can also be the processing time unit of the third channel report or the start generation time unit of the third channel report, etc., which is not limited to this.

[0371] In an embodiment of the present application, when the first channel report is in a state of fully sending content, for the first device, the first channel report may be an expected channel report (expected report), and for the second device, the first channel report may be a received channel report (received report). When the first channel report is in a state of partially sending content, for the first device, the first channel report may be a transmitted channel report (transmitted report), and for the second device, the first channel report may be a received channel report (received report). When the first channel report is in a discarded state, for the first device, the first channel report may also be understood as a discarded channel report (dropped report).

[0372] In the above scheme, the first device can determine whether to update the value of the status information of the first AI model based on the status of the first channel report. For example, when the status of the first channel report indicates that the first channel report is in an incomplete transmission state, the first device determines not to update the value of the status information of the first AI model, that is, the first device maintains the value of the status information of the first AI model unchanged. When the second device does not receive the first channel report, the second device does not update the value of the status information of the second AI model, and the first device does not update the value of the status information of the first AI model. In this way, the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device is consistent. In this way, this can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0373] Figure 8 describes an example of a first device determining the value of the state information of the first AI model based on the state reported by the first channel. The following describes the content of a second device determining the value of the state information of the second AI model based on the state reported by the first channel.

[0374] FIG9 is a schematic diagram of an interaction flow of another communication method according to an embodiment of the present application. As shown in FIG9 , the method includes:

[0375] Optionally, S901a, the second device sends a first reference signal to the first device.

[0376] Accordingly, the first device receives the first reference signal.

[0377] For the description of S901a, please refer to the description of S801a above.

[0378] Optionally, S901b, the first device obtains a first channel report.

[0379] For the description of S901b, please refer to the description of S801b above.

[0380] Optionally, S901c: The first device sends a first channel report to the second device.

[0381] Accordingly, the second device receives the first channel report.

[0382] S901. The second device determines a status of a first channel report.

[0383] When the first device sends the first channel report to the second device, the second device may determine the status of the first channel report according to the content included in the first channel report.

[0384] For example, the second device determines that the first channel report includes only partial content, the second device determines that the first channel report is in a partial content sending state or the first channel report is in a partial content receiving state.

[0385] For example, the second device determines that the first channel report includes all content, the second device determines that the first channel report is in an all content sending state or the first channel report is in an all content receiving state.

[0386] For the description of the status of the first channel report, please refer to the description of Figure 8 and will not be repeated here.

[0387] S902. The second device determines the value of the status information of the second AI model.

[0388] For example, the value of the status information of the second AI model is related to the status reported by the first channel.

[0389] Exemplarily, the state reported by the first channel is the state of sending all content. The second device updates the value of the state information of the second AI model. For example, the second device updates the first value of the state information of the second AI model (see d2 in (a) of FIG. 7 ) using the first channel report to obtain a new value.

[0390] Among them, the first value of the status information of the second AI model is determined by updating the second value of the status information of the second AI model (see d1 in (a) of Figure 7) based on the second channel report, and the update of the first value is related to the first channel report.

[0391] Exemplarily, the state reported by the first channel is a partial content sending state. The second device does not update the value of the state information of the second AI model. For example, the second device maintains the value of the state information of the second AI model as the first value.

[0392] Exemplarily, the state of the first channel report is a partial transmission state. The first device updates the value of the state information of the second AI model. For example, the second device updates the first value of the state information of the second AI model using the first channel report including the partial content to obtain a new value.

[0393] In one possible implementation, the state of the first channel report is a partial sending state, and the value of the state information of the second AI model is related to the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel.

[0394] The third channel report is the first channel report received after the first channel report (see c4 in (b) of FIG7 ).

[0395] Exemplarily, the second device determines whether to update the value of the state information of the second AI model based on the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel.

[0396] For example, the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report is greater than threshold #2, and the second device updates the value of the status information of the second AI model, such as the second device uses the first channel report to update the value of the status information of the second AI model to obtain a new value.

[0397] For example, the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel is less than threshold #2, and the second device maintains the value of the status information of the second AI model unchanged, such as the value of the status information of the second AI model is the first value.

[0398] When the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel is equal to threshold #2, the second device can update the value of the status information of the second AI model or maintain the value of the status information of the second AI model unchanged, which is not limited.

[0399] The description of threshold #2 can refer to the description of threshold #1, which will not be repeated here. For example, threshold #2 = threshold #1.

[0400] Threshold #2 is indicated or configured by the network device, or threshold #2 is predefined.

[0401] The above-mentioned threshold #2 is predefined, which may include: threshold #2 is predefined by the protocol, or threshold #2 is pre-stored, or threshold #2 is pre-burned, etc.

[0402] It should be noted that threshold #2 can be understood as a time length. When the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report is greater than threshold #2, the second device can use the first channel report including partial content to update the value of the state information of the second AI model to avoid excessive loss of feedback performance of the channel report. When the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report is less than threshold #2, the second device does not update the value of the state information of the second AI model, and can determine whether to update the value of the state information of the second AI model based on the status of the third channel report. This can support the use of a more complete channel report to update the value of the state information of the first AI model, thereby helping to improve the feedback performance of the channel report.

[0403] In one possible implementation, the second device determines the value of the state information of the second AI model based on whether the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel meets the second condition.

[0404] For example, if the offset between the reception time unit reported by the second channel and the reception time unit reported by the third channel satisfies the second condition, the second device updates the value of the state information of the second AI model;

[0405] For another example, if the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel does not meet the second condition, the second device maintains the value of the state information of the second AI model unchanged.

[0406] The description of the second condition can refer to the description of the first condition, which will not be repeated here. For example, the second condition is the same as the first condition.

[0407] In summary, the second device can determine whether to update the value of the state information of the second AI model based on whether the offset between the reception time unit of the second channel report and the reception time unit of the third channel report meets the second condition. For example, when the second device determines to update the value of the state information of the second AI model, the second device uses the first channel report including partial content to update the value of the state information of the second AI model, thereby avoiding excessive loss of feedback performance of the channel report; when the second device determines not to update the value of the state information of the second AI model, the second device can determine whether to update the value of the state information of the second AI model based on the status of the third channel report. This can support the use of a more complete channel report to update the value of the state information of the second AI model, thereby helping to improve the feedback performance of the channel report.

[0408] In the scheme shown in Figure 9, when the first device determines the value of the status information of the first AI model based on the status of the first channel report, the second device also determines the value of the status information of the second AI model based on the status of the first channel report. This can support the consistency of the rhythm of updating the status information of the AI ​​model between the first device and the second device, which can improve the feedback performance of the channel report, and thereby improve the recovery performance of the channel information and the robustness of the recovery performance.

[0409] The contents shown in Figures 8 and 9 are described by taking the first device as a terminal device and the second device as a network device as an example. The following describes the scenario in which the first device and the second device are AI entities serving the terminal device and the network device respectively in conjunction with Figure 10.

[0410] FIG10 is a flow chart of another communication method according to an embodiment of the present application. As shown in FIG10 , the first device is OTT, the second device is near real-time RIC, and the method includes:

[0411] Optionally, S1001a, the network device sends a first reference signal to the terminal device.

[0412] Correspondingly, the terminal device receives the first reference signal.

[0413] For the description of S1001a, please refer to the description of S801a and will not be repeated here.

[0414] Optionally, S1001b, the terminal device obtains a channel measurement result of the first reference signal.

[0415] Optionally, S1001c, the terminal device sends the channel measurement result of the first reference signal to the OTT.

[0416] Correspondingly, OTT receives the channel measurement result of the first reference signal.

[0417] S1001. OTT obtains a first channel report.

[0418] For the description of S1001, please refer to the description of S801b, which will not be repeated here.

[0419] S1002. OTT sends a first channel report to the terminal device.

[0420] Correspondingly, the terminal device receives the first channel report.

[0421] S1003. The terminal device sends a first channel report to the network device.

[0422] Accordingly, the network device receives the first channel report.

[0423] S1004: The network device sends a first channel report to the near real-time RIC.

[0424] Accordingly, the near real-time RIC receives the first channel report.

[0425] S1005. OTT obtains the status of the first channel report.

[0426] For the description of S1005, please refer to the description of S801 and will not be repeated here.

[0427] S1006. OTT determines the value of the status information of the first AI model.

[0428] For the description of S1006, please refer to the description of S802 and will not be repeated here.

[0429] S1007: The near real-time RIC obtains the status of the first channel report.

[0430] For the description of S1007, please refer to the description of S901 and will not be repeated here.

[0431] S1008. The near real-time RIC determines the value of the state information of the second AI model.

[0432] For the description of S1008, please refer to the description of S902 and will not be repeated here.

[0433] In the method shown in FIG10 , the status reported by the first channel is a partial content sending status.

[0434] The method shown in FIG10 can make the rhythm of updating the status information of the AI ​​model consistent between OTT and near real-time RIC, thereby improving the feedback performance of the channel report and further improving the recovery performance of the channel information and the robustness of the recovery performance.

[0435] In combination with the methods shown in Figures 8 to 10, the first device and the second device can determine whether to update the value of the status information of the AI ​​model based on the status of the first channel report. This can avoid the occurrence of a scenario where the first device updates the value of the status information of the AI ​​model but the second device does not update the value of the status information of the AI ​​model, thereby supporting the improvement of the feedback performance of the channel report, and further improving the recovery performance of the channel information and the robustness of the recovery performance.

[0436] In addition, when the first device is a terminal device and the second device is a near real-time RIC, the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device can be kept consistent according to the above method, which will not be repeated. Alternatively, when the first device is an OTT and the second device is a network device, the rhythm of updating the value of the status information of the AI ​​model between the first device and the second device can be kept consistent according to the above method, which will not be repeated.

[0437] Finally, the device embodiment of the embodiment of the present application is introduced.

[0438] To implement the various functions of the method provided herein, the first device and the second device may each include hardware structures and / or software modules, and implement the aforementioned functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0439] Figure 11 is a schematic block diagram of a communication device according to an embodiment of the present application. The communication device includes a processing circuit 1110 and a transceiver circuit 1120. The processing circuit 1110 and the transceiver circuit 1120 may be interconnected or coupled, for example, via a bus 1130. The communication device may be a first device or a second device.

[0440] Optionally, the communication device may further include a memory 1140. The memory 1140 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or portable read-only memory (CD-ROM), and is used for related instructions and data.

[0441] The processing circuit 1110 may be all or part of the processing circuitry of one or more processors, or may be one or more processors. The processor may be a central processing unit (CPU). When the processing circuit 1110 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0442] The processing circuit 1110 may be a signal processor, a chip, or other integrated circuit that can implement the method of the present application, or a portion of the circuit used for processing functions in the aforementioned processor, chip or integrated circuit.

[0443] The transceiver circuit 1120 may also be a transceiver, or an input / output interface. The input / output interface is used for input or output of signals or data, and may also be referred to as an input / output circuit.

[0444] When the communication device is the first device, the processing circuit 1110 is configured to perform the following operations: obtaining a status of a first channel report; determining a value of status information of a first AI model, etc.

[0445] When the communication device is the second device, the processing circuit 1110 is configured to perform the following operations: obtaining a status of a first channel report; determining a value of status information of a second AI model, etc.

[0446] The above contents are merely exemplary descriptions. When the communication device is the first device or the second device, it will be responsible for executing the methods or steps related to the first device or the second device in the above method embodiments.

[0447] When the communication device is the first device or the second device, the transceiver circuit 1120 may be a transceiver.

[0448] When the communication device is a chip used for the first device or the second device, the transceiver circuit 1120 may be an input / output circuit.

[0449] For specific details, please refer to the contents shown in the above method embodiment.

[0450] The implementation of each operation in FIG11 may also correspond to the corresponding description of the method embodiments shown in FIG8 to FIG10 .

[0451] Figure 12 is another schematic block diagram of a communication device according to an embodiment of the present application. The communication device may be a first device or a second device, and is configured to implement the method according to the above embodiment.

[0452] The communication device includes a transceiver unit 1210 and a processing unit 1220. The transceiver unit 1210 may include a transmitting unit and a receiving unit. The transmitting unit is configured to perform a transmitting operation of the communication device, and the receiving unit is configured to perform a receiving operation of the communication device. For ease of description, the present embodiment combines the transmitting unit and the receiving unit into a single transceiver unit. This is described here as a unified description and will not be repeated later.

[0453] When the communication device is a first device, illustratively, the transceiver unit 1210 is configured to receive a first reference signal, etc., and the processing unit 1220 is configured to execute the content of the first device involving processing, control, etc. For example, the processing unit 1220 is configured to obtain the status of the first channel report, etc.

[0454] When the communication device is the second device, illustratively, the transceiver unit 1210 is configured to transmit a first reference signal, etc., and the processing unit 1220 is configured to execute the processing, control, etc. steps of the second device. For example, the processing unit 1220 is configured to obtain the status of the first channel report, etc.

[0455] When the communication device is the first device or the second device, it will be responsible for executing one or more of the methods or steps related to the first device or the second device in the aforementioned method embodiments.

[0456] Optionally, the communication device further includes a storage unit 1230, which is used to store a program or code for executing the aforementioned method.

[0457] The transceiver unit in FIG12 may correspond to the transceiver circuit in FIG11 , and the processing unit in FIG12 may correspond to the processing circuit in FIG11 .

[0458] The device embodiments shown in Figures 11 and 12 are used to implement the contents described in Figures 8 to 10. The specific execution steps and methods of the devices shown in Figures 11 and 12 can refer to the contents described in the above method embodiments.

[0459] The present application also provides a chip including a processor configured to retrieve and execute instructions stored in a memory, so that a communication device equipped with the chip executes the methods described in the above examples. The memory may be integrated within the chip or located outside the chip.

[0460] The present application also provides another chip, comprising: an input interface, an output interface, and a processing circuit, wherein the input interface, the output interface, and the processor are connected via an internal connection path, and the processing circuit is used to execute the code in the memory. When the code is executed, the processing circuit is used to execute the method in each of the above examples. Optionally, the chip also includes a memory, which is used to store computer programs or code. The input interface and the output interface can be independent of each other, or can be integrated into an input and output interface.

[0461] The processing circuit may be all or part of the processing circuits in one or more processors, or one or more processors.

[0462] The present application also provides a processor for coupling with a memory, and for executing the methods and functions involving a network device or a terminal device in any of the above embodiments.

[0463] In another embodiment of the present application, a computer program product including instructions is provided. When the computer program product is run on a computer, the method of the above embodiment is implemented.

[0464] The present application also provides a computer program. When the computer program is executed in a computer, the method of the aforementioned embodiment is implemented.

[0465] In another embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a computer, the method described in the above embodiment is implemented.

[0466] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0467] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0468] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0469] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0470] Those skilled in the art will appreciate that the various exemplary units and algorithmic steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented using hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application. Those skilled in the art will clearly understand that, for ease of description and brevity, the specific operating processes of the systems, devices, and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other divisions may be used, such as multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. Furthermore, the coupling or direct coupling or communication connection shown or discussed between each other can be through some interface, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0471] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, the functional units in the various embodiments of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. If the above functions are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the portion that contributes to the prior art, or the portion of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0472] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

Claims

1. A communication method, characterized in that: include: Get the status of the first channel report; Determine a value of state information of a first artificial intelligence (AI) model, where the value of the state information of the first AI model is related to a state reported by the first channel.

2. The method according to claim 1, characterized in that The first channel report is determined according to a first value of the status information of the first AI model.

3. The method according to claim 2, characterized in that The value of the state information of the first AI model is related to the state reported by the first channel, including: The state reported by the first channel is a discarded state, and the value of the state information of the first AI model remains unchanged. The state reported by the first channel is a partial content sending state, and the value of the state information of the first AI model remains unchanged, or, The status reported by the first channel is the status of all content being sent, and the value of the status information of the first AI model is updated.

4. The method according to claim 3, characterized in that The state reported by the first channel is a discarded state, which is determined based on at least one of the following: The resources used to transmit the first channel report overlap with the resources used to transmit the hybrid automatic repeat request report in the time domain, The resources used to transmit the first channel report overlap with the resources used to transmit the scheduling request report in the time domain, The priority of the first channel is lower than the priority of the second channel, the second channel overlaps with the first channel in the time domain, the first channel is used to carry the first channel report, and the second channel is used to carry uplink information, or, The channel used to carry the first channel report conflicts with a downlink symbol or a flexible symbol configured or indicated by the network device.

5. The method according to claim 2, characterized in that The value of the state information of the first AI model is related to the state reported by the first channel, including: The status of the first channel report is a partial content sending status, and the value of the status information of the first AI model is related to the offset between the sending time unit of the second channel report and the generation time unit of the third channel report. The second channel report is determined according to a second value of the state information of the first AI model, and the first value is determined by updating the second value based on the second channel report. The third channel report is the first channel report sent after the first channel report.

6. The method according to claim 5, characterized in that The value of the state information of the first AI model is related to the offset between the sending time unit of the second channel report and the generation time unit of the third channel report, including: The offset is greater than a threshold, and the value of the state information of the first AI model is updated, or, The offset is less than the threshold, and the value of the state information of the first AI model remains unchanged.

7. The method according to claim 5 or 6, characterized in that The threshold is indicated or configured by the network device, or the threshold is predefined.

8. The method according to any one of claims 3 to 7, characterized in that The status reported by the first channel is a partial content sending status determined based on at least one of the following: The processing resources available for computation are insufficient to generate the expected first channel report, The network device configures or instructs the time unit for reporting the first channel report to not meet the time requirement for calculation of the expected first channel report, The network device configures or indicates that the time unit corresponding to the uplink data channel carrying the first channel report does not meet the time requirement for calculation of the expected first channel report, or, The network device configures or indicates that the transmission resources for carrying the first channel report are insufficient to carry the expected first channel report.

9. The method according to any one of claims 2 to 8, characterized in that The first value is determined based on a channel measurement result of a historical reference signal, The sending time unit of the historical reference signal is earlier than the sending time unit of the first reference signal, The first channel report corresponds to the first reference signal.

10. A communication method, characterized in that: include: Get the status of the first channel report; Determine a value of status information of a second artificial intelligence (AI) model, where the value of the status information of the second AI model is related to a status reported by the first channel.

11. The method according to claim 10, characterized in that The value of the status information of the second AI model is related to the status reported by the first channel, including: The status reported by the first channel is a partial content sending status, and the value of the status information of the second AI model remains unchanged, or, The status reported by the first channel is the status of all content being sent, and the value of the status information of the second AI model is updated.

12. The method according to claim 10, characterized in that The value of the status information of the second AI model is related to the status reported by the first channel, including: The status reported by the first channel is a partial content sending status, and the value of the status information of the second AI model is related to the offset between the receiving time unit reported by the second channel and the receiving time unit reported by the third channel. The first value of the state information of the second AI model is determined by updating the second value of the state information of the second AI model based on the second channel report, and the update of the first value is related to the first channel report. The third channel report is the first channel report received after the first channel report.

13. The method according to claim 12, characterized in that The value of the state information of the second AI model is related to the offset between the receiving time unit of the second channel report and the receiving time unit of the third channel report, including: The offset is greater than a threshold, and the value of the state information of the second AI model is updated, or, The offset is less than the threshold, and the value of the state information of the second AI model remains unchanged.

14. The method according to claim 12 or 13, characterized in that The threshold is indicated or configured by the network device, or the threshold is predefined.

15. The method according to any one of claims 11 to 14, characterized in that The status reported by the first channel is a partial content sending status determined based on at least one of the following: The processing resources available for calculation on the terminal device side are insufficient to generate the expected first channel report, The network device configures or instructs the time unit for reporting the first channel report to not meet the time requirement for calculation of the expected first channel report, The network device configures or indicates that the time unit corresponding to the uplink data channel carrying the first channel report does not meet the time requirement for calculation of the expected first channel report, or, The network device configures or indicates that the transmission resources for carrying the first channel report are insufficient to carry the expected first channel report.

16. A communication device, characterized in that: comprising a processing circuit for, By executing computer programs or instructions, or by hardware circuits, causing the communication device to perform the method according to any one of claims 1 to 9, or The communication device is enabled to perform the method according to any one of claims 10 to 15.

17. A communication device, characterized in that: Comprising means for performing the method of any one of claims 1 to 15.

18. A communication device, characterized in that: comprising a processor configured to, by executing computer programs or instructions, or by executing logic circuits, causing the communication device to perform the method according to any one of claims 1 to 9; Or enable the communication device to perform the method according to any one of claims 10 to 15.

19. A communication device, characterized in that: It includes a logic circuit and an input / output interface, wherein the input / output interface is used to input and / or output signals. The logic circuit is configured to execute the method according to any one of claims 1 to 9; or The logic circuit is configured to execute the method according to any one of claims 10 to 15 .

20. A computer-readable storage medium, characterized in that The computer readable storage medium stores a computer program or instruction. When the computer program or instruction is executed on a computer, causing the method of any one of claims 1 to 9 to be performed; or, The method according to any one of claims 10 to 15 is performed.

21. A computer program product, characterized in that Contains instructions that, when executed on a computer, causing the method of any one of claims 1 to 9 to be performed; or, The method according to any one of claims 10 to 15 is performed.

22. A chip, characterized in that: comprising one or more processors configured to execute computer programs or instructions in a memory, so that the chip implements the method according to any one of claims 1 to 9; or The chip is configured to implement the method according to any one of claims 10 to 15.

23. A chip system, characterized in that: comprising one or more processors configured to execute computer programs or instructions in a memory so that the chip system implements the method according to any one of claims 1 to 9; or The chip system is enabled to implement the method according to any one of claims 10 to 15.

Images