Communication method and apparatus, and terminal device and network device

Abstract

The present application relates to the technical field of communications. Disclosed are a communication method and apparatus, and a terminal device and a network device. When an AI technique is applied to CSI processing, the application of the AI technique to CSI processing may bring certain advantages, such as realizing CSI processing intelligentization, improving air-interface performance, or reducing air-interface overheads, and may also bring certain disadvantages, such as a relatively large computing power occupied by an AI inference process or a relatively large error between an AI inference result and an actual result. To this end, the present application introduces a fallback mechanism for CSI processing. In this way, in the fallback mechanism for CSI processing, when first CSI processing (that is, AI-based CSI processing) has problems such as having a disadvantage, failing to be successfully executed, or failing to achieve an expected result, the present application can perform fallback on the first CSI processing on the basis of a first fallback mode, such that the first CSI processing can be returned, restored, or undone to a state in which same can be processed, executed or expected.

Description

Communication methods and devices, terminal equipment and network equipment

[0001] This invention claims priority to the earlier application filed on July 12, 2024, entitled "Communication Method and Apparatus, Terminal Equipment and Network Equipment" (application number 2024109405825), the contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method and apparatus, terminal equipment and network equipment. Background Technology

[0003] Artificial intelligence (AI) technology can solve problems that are difficult to address using traditional modeling methods, such as nonlinear problems and problems with overly complex parameters. It establishes problem-solving patterns through training on large amounts of data and provides relatively accurate predictions. AI can include machine learning (ML), deep learning (DL), and other related techniques.

[0004] With the continuous development of AI technology and the evolution of wireless communication systems, the 3rd Generation Partnership Project (3GPP) is currently discussing the integration of AI technology with wireless communication systems. One area of ​​discussion is applying AI technology to channel state information (CSI) processing. Summary of the Invention

[0005] This application provides a communication method and apparatus, a terminal device and a network device, which are intended to enable network configuration or network indication reference signals and data channels to use non-orthogonal transmission.

[0006] Firstly, a communication method according to this application includes:

[0007] Determine the first rollback method;

[0008] The first CSI process is rolled back according to the first rollback method. The first CSI process refers to AI-based CSI process.

[0009] It is evident that when AI technology is applied to CSI processing, it can bring both advantages, such as enabling intelligent CSI processing, improving air interface performance, or reducing air interface overhead, and disadvantages, such as the AI ​​inference process consuming significant computing power or a large discrepancy between the AI's inference results and the actual results. Therefore, this embodiment introduces a rollback mechanism for CSI processing.

[0010] Thus, in the rollback mechanism of CSI processing, when the first CSI processing (i.e., AI-based CSI processing) has drawbacks, fails to execute successfully, or fails to achieve the expected results, the terminal device can roll back the first CSI processing according to the first rollback method, so that the first CSI processing can return, restore or cancel to a processable, executable or predictable state.

[0011] In some possible examples, the first CSI process is rolled back according to the first rollback method, including:

[0012] The first CSI process can be rolled back to the second CSI process according to the first rollback method, or the first CSI process can be rolled back to not performing CSI process according to the first rollback method;

[0013] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0014] In some possible examples, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing. In some possible examples, after the first CSI processing is rolled back to the second CSI processing according to the first rollback method, it further includes:

[0015] Determine the first rollback trigger condition and the corresponding rollback method;

[0016] If the first rollback trigger condition is triggered, the second CSI process will be rolled back according to the rollback method corresponding to the first rollback trigger condition.

[0017] It is evident that if the first rollback trigger condition is triggered, it indicates that the second CSI process has flaws, cannot be executed successfully, or cannot achieve the expected results. In this case, the terminal device can continue to roll back the second CSI process according to the rollback method corresponding to the first rollback trigger condition, so that the second CSI process can return, restore, or be undone to a processable, executable, or predictable state.

[0018] In some possible examples, the first rollback trigger condition includes at least one of the following:

[0019] The performance information of the second CSI processing does not meet the preset requirements, the resource requirements of the second CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the second CSI processing.

[0020] In some possible examples, the performance information of the second CSI processing includes at least one of the following: the accuracy of the second CSI processing, the processing time of the second CSI processing, the memory usage of the second CSI processing, the resource utilization of the second CSI processing, the complexity of the second CSI processing, the data distribution characteristics of the second CSI processing, or the signal transmission performance information of the second CSI processing; or,

[0021] The resource requirements for the second CSI processing include at least one of the following: computing power required for the second CSI processing, processing units required for the second CSI processing, memory required for the second CSI processing, storage units required for the second CSI processing, network bandwidth required for the second CSI processing, or power required for the second CSI processing; or,

[0022] The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

[0023] In some possible examples, the second CSI processing is rolled back according to the rollback method corresponding to the first rollback trigger condition, including:

[0024] The second CSI process is rolled back to the third CSI process according to the rollback method corresponding to the first rollback trigger condition, or the second CSI process is rolled back to not executing CSI process.

[0025] The third CSI processing refers to AI-based CSI processing other than the first CSI processing and the second CSI processing, or the third CSI processing refers to non-AI-based CSI processing other than the first CSI processing and the second CSI processing.

[0026] It is understandable that the rollback method corresponding to the first rollback trigger condition is used to roll back the second CSI process to the third CSI process, or the rollback method corresponding to the first rollback trigger condition is used to roll back the second CSI process to not perform CSI process.

[0027] In some possible examples, the third CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, or other AI-based CSI processing besides the second CSI processing, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, non-AI-based CSI processing, CSI processing based on measurement resources no later than the CSI reference resource, or non-AI-based CSI processing.

[0028] In some possible examples, the first rollback method is determined, including:

[0029] Receive rollback mode indication information, which is used to indicate the first rollback mode.

[0030] As can be seen, the fallback method indication information enables the network device to configure or indicate the first fallback method to the terminal device, so that the terminal device can determine the first fallback method through the fallback method indication information. Since the first fallback method is configured or indicated by the network, the terminal device can fall back the first CSI processing according to the network requirements.

[0031] In some possible examples, the first rollback method is determined, including:

[0032] Determine one or more rollback trigger conditions and the rollback method corresponding to one or more rollback trigger conditions;

[0033] If one or more rollback trigger conditions are triggered, the rollback method corresponding to the triggered rollback trigger condition is determined to be the first rollback method.

[0034] As can be seen, the terminal device in this embodiment can decide on its own whether a rollback trigger condition is triggered among the one or more rollback trigger conditions, and roll back the first CSI process according to the rollback method corresponding to the triggered rollback trigger condition.

[0035] In some possible examples, determine one or more rollback trigger conditions and the corresponding rollback method for one or more rollback trigger conditions, including:

[0036] Receive configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to one or more rollback trigger conditions.

[0037] As can be seen, the configuration information enables the network device to configure or instruct the terminal device on one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, so that the terminal device can determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions through the configuration information.

[0038] In some possible examples, one or more fallback trigger conditions include at least one of the following:

[0039] The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

[0040] In some possible examples, the performance information of the first CSI process includes at least one of the following: the accuracy of the first CSI process, the processing time of the first CSI process, the memory usage of the first CSI process, the resource utilization of the first CSI process, the complexity of the first CSI process, the data distribution characteristics of the first CSI process, or the signal transmission performance information of the first CSI process; or,

[0041] The resource requirements for the first CSI processing include at least one of the following: computing power required for the first CSI processing, processing units required for the first CSI processing, memory required for the first CSI processing, storage units required for the first CSI processing, network bandwidth required for the first CSI processing, or power required for the first CSI processing; or...

[0042] The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

[0043] In some possible examples, after determining that the rollback method corresponding to the first rollback trigger condition is the first rollback method, it also includes:

[0044] Send rollback method feedback information, which is used to indicate the first rollback method.

[0045] As can be seen, by feeding back information through the fallback method, the terminal device can report the first fallback method to the network device, so that the network device can know the fallback method adopted by the terminal device.

[0046] In some possible examples, rollback feedback information is carried by the CSI report.

[0047] In this way, the terminal device can use the CSI report to provide feedback on the first fallback method to the network device.

[0048] In some possible examples, after backing down the first channel state information (CSI) processing according to the first back-down method, the following is also included:

[0049] Send result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0050] Therefore, when the result feedback information indicates that the rollback of the first CSI process is complete, the network device can know that the rollback of the first CSI process is complete through the result feedback information. When the result feedback information indicates the rollback method used to roll back the first CSI process, the network device can know the rollback method used for the first CSI process through the result feedback information. When the result feedback information indicates the type of CSI process after the rollback of the first CSI process, the network device can know the type of CSI process after the rollback of the first CSI process through the result feedback information. When the result feedback information indicates the information obtained based on the type of CSI process after the rollback of the first CSI process, the network device can know the information obtained based on the type of CSI process after the rollback of the first CSI process through the result feedback information.

[0051] In some possible examples, the results feedback information is carried by the CSI report.

[0052] In this way, the terminal device can use CSI reports to provide feedback to the network device on the rollback execution result of the first CSI process.

[0053] Secondly, a communication method according to this application includes:

[0054] Send rollback method indication information. The rollback method indication information is used to indicate the first rollback method. The first rollback method is used to roll back the first CSI process. The first CSI process refers to AI-based CSI process.

[0055] As can be seen, the fallback method indication information enables the network device to configure or indicate the first fallback method to the terminal device, so that the terminal device can determine the first fallback method through the fallback method indication information. Since the first fallback method is configured or indicated by the network, the terminal device can fall back the first CSI processing according to the network requirements.

[0056] In some possible examples, the first rollback method is used to roll back the first CSI process, including:

[0057] The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process;

[0058] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0059] In some possible examples, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0060] In some possible examples, this also includes:

[0061] Receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0062] In some possible examples, the results feedback information is carried by the CSI report.

[0063] Thirdly, a communication method according to this application includes:

[0064] Send configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions;

[0065] Among them, the rollback method corresponding to one of the rollback triggering conditions is the first rollback method. The first rollback method is used to roll back the first CSI process. The first CSI process refers to AI-based CSI process.

[0066] As can be seen, the configuration information enables the network device to configure or instruct the terminal device on one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, so that the terminal device can determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions through the configuration information.

[0067] In some possible examples, one or more fallback trigger conditions include at least one of the following:

[0068] The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

[0069] In some possible examples, the performance information processed by the first CSI includes at least one of the following:

[0070] The accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing.

[0071] In some possible examples, after sending the configuration information, the following may also be included:

[0072] Receive rollback method feedback information, which is used to indicate the first rollback method.

[0073] In some possible examples, rollback feedback information is carried by the CSI report.

[0074] In some possible examples, the first rollback method is used to roll back the first CSI process, including:

[0075] The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process;

[0076] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0077] In some possible examples, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0078] In some possible examples, this also includes:

[0079] Receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0080] In some possible examples, the results feedback information is carried by the CSI report.

[0081] Fourthly, a communication method according to this application includes:

[0082] Receive CSI processing instruction information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0083] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0084] In some possible examples, the process may include the following before receiving CSI processing instruction information:

[0085] Receive CSI processing instruction information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0086] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is configured or indicated by the network, the terminal device can execute the relevant CSI process according to the network-required CSI process. Then, the network device configures or instructs the terminal device to activate or deactivate the first CSI process through activation instruction information.

[0087] Fifthly, a communication method according to this application includes:

[0088] Send CSI processing instruction information, which is used to indicate the first CSI process from one or more candidate CSI processes.

[0089] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0090] In some possible examples, the following may also be included before sending the CSI processing instruction information:

[0091] Send CSI processing instruction information, which is used to indicate the first CSI process from one or more candidate CSI processes.

[0092] Sixthly, a communication device according to this application, wherein the communication device includes:

[0093] The determining unit is used to determine the first rollback method;

[0094] The rollback unit is used to roll back the first CSI process according to the first rollback method. The first CSI process refers to AI-based CSI processing.

[0095] A seventh aspect is a communication device according to this application, wherein the communication device includes:

[0096] The sending unit is used to send rollback mode indication information, which indicates a first rollback mode. The first rollback mode is used to roll back the first CSI process, which refers to AI-based CSI processing.

[0097] Eighthly, a communication device according to this application, wherein the communication device includes:

[0098] The sending unit is used to send configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions.

[0099] Among them, the rollback method corresponding to one of the rollback triggering conditions is the first rollback method. The first rollback method is used to roll back the first CSI process. The first CSI process refers to AI-based CSI process.

[0100] Ninthly, a communication device according to this application, wherein the communication device includes:

[0101] The receiving unit is used to receive CSI processing indication information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0102] Tenthly, a communication device according to this application, wherein the communication device includes:

[0103] The sending unit is used to send CSI processing indication information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0104] Eleventhly, the steps in the methods described in the first or fourth aspects above are applied to the terminal device.

[0105] In the twelfth aspect, the steps in the methods described in the second, third, or fifth aspects above are applied to network devices.

[0106] Thirteenthly, a terminal device according to this application includes a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps in the methods involved in the first or fourth aspects above.

[0107] The fourteenth aspect is a network device according to this application, including a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps in the methods involved in the second, third, or fifth aspects described above.

[0108] The fifteenth aspect is a chip according to this application, including a processor, wherein the processor performs the steps of the methods involved in any one of the first to fourth aspects described above.

[0109] The sixteenth aspect is a chip module according to this application, including a transceiver component and a chip, wherein the chip includes a processor, and the processor performs the steps of the methods involved in any one of the first to fifth aspects above.

[0110] The seventeenth aspect is a computer-readable storage medium of this application, wherein the computer-readable storage medium stores a computer program or instructions, which, when executed, implement the steps of the methods involved in any one of the first to fifth aspects described above.

[0111] The eighteenth aspect is a computer program product of this application, comprising a computer program or instructions, wherein when the computer program or instructions are executed, the steps in the methods involved in any one of the first to fifth aspects described above are performed. Exemplarily, the computer program product may be a software installation package.

[0112] The nineteenth aspect is a communication system according to this application, including the terminal equipment involved in the thirteenth aspect and the network equipment involved in the fourteenth aspect.

[0113] It should be understood that the beneficial effects of the technical solutions in aspects five through nineteen can be found in the technical effects of the technical solutions in aspects one, two, three, or four mentioned above, and will not be repeated here. Attached Figure Description

[0114] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of this application;

[0115] Figure 2 is a schematic diagram of the architecture of another communication system according to an embodiment of this application;

[0116] Figure 3 is a schematic diagram of a time slot distribution according to an embodiment of this application;

[0117] Figures 4 to 12 are schematic flowcharts of a communication method according to an embodiment of this application;

[0118] Figures 13 to 16 are functional unit block diagrams of a communication device according to an embodiment of this application;

[0119] Figure 17 is a schematic diagram of the structure of a terminal device according to an embodiment of this application;

[0120] Figure 18 is a schematic diagram of the structure of a network device according to an embodiment of this application. Detailed Implementation

[0121] It should be understood that the terms "first," "second," etc., used in the embodiments of this application are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, software, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may also include steps or units not listed, or may also include other steps or units inherent to these processes, methods, products, or devices.

[0122] The term "embodiment" as used in the embodiments of this application means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0123] In the embodiments of this application, "at least one" or "at least one item" refers to one or more, and "multiple" refers to two or more.

[0124] In the embodiments of this application, "and / or" describes the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. Among them, A and B can be singular or plural.

[0125] In the embodiments of this application, "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent the following seven cases: a, b, c, a and b, a and c, b and c, a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0126] In the embodiments of this application, the terms "of," "corresponding (relevant)," "corresponding," "associated (related)," and "mapped" may sometimes be used interchangeably. It should be noted that when no distinction is emphasized, the concepts or meanings expressed are consistent.

[0127] In the embodiments of this application, "network" can be expressed as the same concept as "system," and a communication system is a communication network.

[0128] In this application, "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices, and is not specifically limited thereto.

[0129] The technical solutions of the embodiments of this application will be described in detail below.

[0130] The communication system of this embodiment will be described in detail below.

[0131] Communication System

[0132] The technical solutions of this application can be applied to various wireless communication systems, such as: Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, non-terrestrial networks (NTN) systems, Universal Mobile Telecommunications System (UMTS), 6th-Generation (6G) communication systems, or other future communication systems.

[0133] It should be noted that traditional communication systems support a limited number of user connections and are easy to implement. With the development of communication technology, the communication system of this application can support not only traditional communication systems, but also communication systems such as device-to-device (D2D), machine-to-machine (M2M), machine-type communication (MTC), vehicle-to-vehicle (V2V), vehicle-to-everything (V2X), and narrowband internet of things (NB-IoT). Therefore, the technical solutions of the embodiments of this application can also be applied to the above-mentioned communication systems.

[0134] For example, embodiments of this application can be applied to beamforming, carrier aggregation (CA), dual connectivity (DC), or standalone (SA) deployment scenarios.

[0135] For example, embodiments of this application can be applied to communication scenarios using unlicensed spectrum. In these embodiments, unlicensed spectrum can also be considered as shared spectrum. Alternatively, embodiments of this application can also be applied to licensed spectrum. In these embodiments, licensed spectrum can also be considered as non-shared spectrum.

[0136] As an example, the network architecture of a communication system according to an embodiment of this application can be referred to FIG1. ​​As shown in FIG1, the communication system 10 may include a network device 110 and a terminal device 120. The terminal device 120 can communicate with the network device 110 wirelessly.

[0137] It should be understood that Figure 1 is merely an example of a network architecture for a communication system and does not constitute a limitation on the network architecture of the communication system in the embodiments of this application. For example, the communication system 10 may also include a server or other devices, or the communication system 10 may include other network devices besides network device 110, or the communication system 10 may include other terminal devices besides terminal device 120.

[0138] The terminal devices and network devices mentioned in this embodiment will be described below.

[0139] Terminal equipment

[0140] Terminal equipment can be a device with transceiver capabilities, and can also be referred to as a terminal, user equipment (UE), remote terminal equipment (relay UE), relay equipment (relay UE), access terminal equipment, user unit, user station, mobile station, mobile station, remote station, mobile device, user terminal equipment, smart terminal equipment, wireless communication equipment, user agent, or user device. It should be noted that relay equipment is a terminal device capable of providing relay forwarding services to other terminal equipment (including remote terminal equipment).

[0141] For example, terminal devices can be mobile phones, tablets, computers with wireless transceiver capabilities, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminal devices in industrial control, wireless terminal devices in autonomous driving, wireless terminal devices in remote medical care, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, or wireless terminal devices in smart homes, etc.

[0142] For example, a terminal device can be a cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in next-generation communication systems (such as NR communication systems, 6G communication systems), or terminal device in a future public land mobile network (PLMN), etc., without specific limitations.

[0143] Optionally, the terminal equipment can be deployed on land, on water (such as ships), or in the air (such as airplanes, balloons, and satellites).

[0144] Optionally, the terminal device includes means for wireless communication functionality, such as a chip system, chip, chip module, device, or unit. For example, the chip system may include a chip, and may also include other discrete components.

[0145] Optionally, the terminal device includes an AI model. The AI ​​model can be a software unit and / or hardware unit that utilizes AI technology for channel, information, or signal processing. For example, the AI ​​model can be used for AI-based CSI processing.

[0146] It should be noted that AI can include ML, DL, etc., and AI models can have certain model parameters and model architectures, and AI models can include various linear and nonlinear network models, such as linear regression, vector machines, CNN, DNN, etc. In addition, the term "AI model" in this embodiment can be understood as ML model, DL model, intelligent model, AI interface, AI device, AI unit, AI module, AI algorithm, or intelligent module, etc., without specific limitations.

[0147] Optionally, AI models include chips, chip modules, etc.

[0148] Network equipment

[0149] A network device is a device with transceiver capabilities that can be used to communicate with terminal devices.

[0150] Network devices may include means for providing wireless communication capabilities to terminal devices, such as chip systems, chips, or chip modules. For example, the chip system may include chips or other discrete devices. The network device provides services to a cell, and terminal devices within that cell can communicate with the network device through transmission resources (such as spectrum resources). This cell may be a macro cell, small cell, metro cell, micro cell, pico cell, or femto cell, etc.

[0151] Optionally, the network equipment may have mobility characteristics; for example, the network equipment may be a mobile device. Optionally, the network equipment may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary Earth orbit (GEO) satellite, or a high elliptical orbit (HEO) satellite. Optionally, the network equipment may also be a base station located on land, water, or other similar locations.

[0152] Optionally, the network device includes means for wireless communication functionality, such as a chip system, chip, chip module, device, or unit. For example, the chip system may include a chip, and may also include other discrete components.

[0153] Optionally, network devices may include AI models. These AI models can be software and / or hardware units that utilize AI technology for channel, information, or signal processing. For example, an AI model can be used for AI-based CSI processing.

[0154] Optionally, AI models include chips, chip modules, etc.

[0155] Optionally, network devices may include access network devices and / or devices in the core network (CN).

[0156] The access network equipment and core network equipment are described in detail below.

[0157] Access network equipment

[0158] Access network equipment can be called a radio access network (RAN). An RAN can be a network composed of multiple 5G-RAN nodes, implementing radio physical layer functions, resource scheduling and radio resource management, radio access control, and mobility management functions. The 5G-RAN connects to the User Plane Interface (N3) and the User Platform Function (UPF) for transmitting data from terminal devices; it also establishes a control plane signaling connection with the Access and Mobility Management Function (AMF) through the Control Plane Interface (N2) to implement radio access bearer control and other functions. The RAN can be any device with radio transceiver capabilities, including but not limited to 5G node base stations (gNBs), evolved Node Base Stations (eNBs), access points (APs), World Interoperability for Microwave Access Base Stations (WiMAX BSs), transmission receiving points (TRPs), radio relay nodes, radio backhaul nodes, master nodes (MNs) in dual-connectivity architectures, and secondary nodes (SNs) in dual-connectivity architectures, etc.

[0159] In addition, access network equipment can refer to equipment used for communication with terminal equipment. For example, access network equipment can be a base transceiver station (BTS) in a Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) system, a base station (nodeB, NB) in a Wideband Code Division Multiple Access (WCDMA) system, an evolved node base (eNB) in an LTE system, a radio controller in a cloud radio access network (CRAN) scenario, or a relay station, access point, vehicle-mounted equipment, wearable device, and access network equipment in future 5G networks or future evolved PLMN networks, etc. The embodiments of this application are not limited to these.

[0160] In 5G NR, the functionality of access network equipment is divided into two parts, known as centralized unit (CU) - distributed unit (DU) separation. From a protocol stack perspective, the CU includes the Radio Resource Control (RRC) layer and Packet Data Convergence Protocol (PDCP) layer of the LTE base station, while the DU includes the Radio Link Control (RLC) layer, Media Access Control (MAC) layer, and Physical (PHY) layer of the LTE base station. In a typical 5G base station deployment, the CU and DU are physically connected via fiber optic cable, and logically share a specially defined F1 interface for communication between them. Functionally, the CU is primarily responsible for radio resource control and configuration, inter-cell mobility management, and bearer management. The DU is primarily responsible for scheduling, physical signal generation, and transmission.

[0161] Optionally, the access network equipment can be macro base stations, micro base stations, pico base stations, small stations, relay stations, balloon stations, etc.

[0162] Core network equipment

[0163] Core network equipment may include network elements that provide various functions. The term "network element" can also be referred to as an entity, device, apparatus, or module, without specific limitation. Furthermore, for ease of understanding and explanation, the description of "network element" will be omitted in some descriptions. For example, a network exposure function (NEF) network element may be abbreviated as NEF. In this case, "NEF" should be understood as either a NEF network element or a NEF entity. The following will omit descriptions of similar cases.

[0164] For example, core network equipment may include a mobility management entity (MME), a broadcast multicast service center (BMSC), or corresponding functional entities in the 5G system, such as core network control plane (CP) or user plane (UP) network functions. The core network control plane can also be understood as the core network control plane function (CPF) entity.

[0165] Optionally, the network elements included in the core network equipment include at least one of the following: session management function (SMF), user plane function (UPF), policy control function (PCF), NEF, authentication server function (AUSF), unified data management (UDM), network slice selection function (NSSF), network repository function (NRF), unified data management (UDM), application function (AP), unified data repository (UDR), network data analytics function (NWDAF), service control point (SCP), network slice admission control function (NSACF), or network slice specific authentication and authorization function (NSSAAF).

[0166] It should be noted that terminal devices can connect to access network devices wirelessly, and access network devices can connect to core network devices wirelessly or via wired connections. Core network devices can connect to a data network (DN). Access network devices and core network devices can be independent physical devices, or the functions of core network devices and the logical functions of access network devices can be integrated into the same physical device. Alternatively, a single physical device can integrate some of the functions of core network devices and some of the functions of access network devices.

[0167] It should be noted that the terminal device connects to the access network device wirelessly, and the access network device connects to the core network device wirelessly or via a wired connection. The access network device and the core network device can be independent physical devices, or the functions of the core network device and the logical functions of the access network device can be integrated into the same physical device, or a single physical device can integrate some of the functions of the core network device and some of the functions of the access network device.

[0168] For example, Figure 2 is a schematic diagram of the architecture of another communication system according to an embodiment of this application. The names of the network elements included in Figure 2 are merely names and do not limit the function of the network elements themselves. In 5G networks and other future networks, the aforementioned network elements may also have other names, and no specific limitations are made. For example, in 6G networks, some or all of the aforementioned network elements may use the terminology from 5G, or they may have other names, etc. This will be uniformly explained here and will not be elaborated further below.

[0169] Furthermore, the various network elements in Figure 2 do not necessarily need to exist simultaneously; the required network elements can be determined based on needs. The connection relationships between the various network elements in Figure 2 are also not uniquely defined and can be adjusted according to requirements. It is understood that the aforementioned network elements or functions can be network components in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform).

[0170] It should be understood that Figure 2 is merely an example of the network architecture of a communication system and does not constitute a limitation on the network architecture of the communication system in the embodiments of this application.

[0171] The communication system has been described above. The following is a detailed explanation of the application of AI technology to CSI in this embodiment.

[0172] AI technology applied to CSI

[0173] Channel quality information (CSI) can be used to describe information related to channel quality. For example, CSI describes the propagation process of a wireless signal between the transmitter and receiver, including the effects of distance, scattering, and fading on the signal. For downlink transmission, CSI can be used by terminal devices to report downlink channel quality to network devices, enabling the network devices to perform resource scheduling, beam management, mobility management, and other processing based on the CSI. For example, CSI can be used in LTE or 5G NR systems.

[0174] Within the CSI framework, network devices execute CSI resource configuration and CSI report configuration to enable terminal devices to perform CSI measurement, CSI calculation, and CSI reporting processes based on these configurations. During CSI measurement and calculation, terminal devices can perform channel and / or interference measurements using reference signals (such as CSI reference signal (CSI-RS), demodulation reference signal (DMRS), or synchronization signal block (SSB)) to obtain CSI measurement results. During CSI reporting, terminal devices can feed back or report CSI measurement results to network devices via CSI reports, enabling network devices to perform link adaptation, etc. The CSI measurement results may include CSI information and / or channel information.

[0175] CSI information can refer to relevant information obtained from channel measurements based on reference signals (such as CSI-RS, DMRS, or SSB), or it can refer to relevant information used to assess and describe the channel state, or it can be determined based on the channel matrix H.

[0176] For example, CSI information includes at least one of the following: CSI-RS Resource Indicator (CRI), SSB Resource Indicator (SSBRI), Rank Indicator (RI), Precoding Matrix Indicator (PMI), Channel Quality Indicator (CQI), Layer Indicator (LI), Time-Domain Channel Properties (TDCP), Layer 1 Reference Signal Received Power (L1-RSRP), Layer 1 Signal-to-Noise and Interference Ratio (L1-SINR), Angle of Arrival (AOA), Angle of Arrival Spread (AAS), Angle of Departure (AOD), Angle of Departure Spread (ADS), Spatial Correlation, etc. It should be understood that the content included in CSI information is not limited to the above-listed items and can be adjusted according to actual needs in practical applications. In other words, any relevant information that can be used to describe the channel state can be the CSI information in this embodiment, and there is no specific limitation on it.

[0177] Channel information can refer to relevant information used to describe channel characteristics, channel state, or channel quality.

[0178] For example, channel information may include at least one of the following: channel matrix H, a portion of channel matrix H, a vector or vector obtained by processing channel matrix H, an eigenvector or vector obtained by processing channel matrix H, a right singular vector of channel matrix H, a matrix transformed from channel matrix H (such as an equivalent channel matrix), time-domain information of the channel, frequency-domain information of the channel, time-frequency-domain information of the channel, CSI information, or channel information in the delay-Doppler domain, etc., without specific limitations. It should be understood that the content of channel information is not limited to the above-listed contents, and the channel information can be adjusted according to the actual situation in practical applications. That is to say, any information that can be used to describe channel characteristics, channel state, or channel quality can be the channel information of this embodiment, and this embodiment does not make specific limitations on it.

[0179] Currently, AI technology can be applied to CSI processing. When applied to CSI processing, AI models can perform relevant processing on the air interface transmission of communication systems to achieve intelligent communication and improve air interface performance, such as increasing the reliability of air interface transmission and reducing air interface overhead. Of course, applying AI technology to CSI processing may bring both advantages and disadvantages, such as the AI ​​model's inference process consuming significant computing power or a large discrepancy between the AI ​​model's inference results and the actual results. Therefore, the decision to adopt AI technology for CSI processing needs to be made prudently.

[0180] Therefore, the types of CSI processing in this embodiment may include AI-based CSI processing and non-AI-based CSI processing.

[0181] AI-based CSI processing can refer to methods that use AI technology to perform CSI processing. It can be a method that uses machine learning and data-driven approaches to optimize and enhance traditional CSI processing, and can be implemented through AI models. In other words, it uses AI to perform CSI processing.

[0182] Non-AI-based CSI processing refers to methods that perform CSI processing without using AI technology. In other words, it involves performing CSI processing in a non-AI manner.

[0183] It should be noted that AI-based CSI processing focuses on optimizing the CSI processing procedure using a large amount of real and measured data. Through machine learning algorithms, complex channel characteristics or channel states can be learned from the data.

[0184] For example, AI-based CSI processing can involve the following steps: data preprocessing, feature extraction, AI model training, AI model testing, and AI model deployment. Data preprocessing can be understood as preprocessing the input data, such as quantization and encoding. Feature extraction can be understood as extracting key features from the input data. AI model training can be understood as using a large amount of sample data to train the AI ​​model, enabling it to accurately identify and simulate different CSI processing methods. The training objectives of the AI ​​model can be diverse, such as maximizing spectral efficiency, minimizing the bit error rate, or reducing power consumption. By defining appropriate loss functions and training processes, the AI ​​model can learn how to achieve these training objectives. Model testing can be understood as evaluating the performance of the AI ​​model on independent test sets. AI model deployment can be understood as deploying the trained AI model into a real communication system to implement CSI processing.

[0185] In some possible examples, AI-based CSI processing may include at least one of the following: AI-based CSI prediction, AI-based CSI compression, or AI-based CSI reconstruction. CSI reconstruction can also be referred to as "CSI resume / recovery".

[0186] In some possible examples, the type of non-AI-based CSI processing may include at least one of the following: non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI reconstruction, or CSI processing based on measurement resources no later than the CSI reference resource.

[0187] It should be understood that, regardless of whether CSI processing is AI-based or non-AI-based, CSI processing can also include some processing during communication, such as encoding, decoding, quantization, or dequantization, without specific limitations.

[0188] The following sections provide detailed explanations of CSI prediction, CSI compression, CSI reconstruction, and CSI processing based on measurement resources no later than the CSI reference resources.

[0189] CSI Forecast

[0190] After the terminal device acquires CSI measurement results based on the reference signal, it may need to make predictions based on these results to obtain CSI prediction information. This prediction information is then used to forecast future channel characteristics, channel state, channel quality, and / or transmission processing. CSI prediction information can be understood as the relevant information obtained from predictions based on the CSI measurement results.

[0191] For example, CSI prediction information may include predicted CSI information and / or predicted channel information.

[0192] It should be noted that when a terminal device acquires CSI measurement result information based on a reference signal, the predicted CSI information can include CSI information corresponding to one or more time domain positions after the time domain position where the reference signal is located, or CSI information corresponding to one or more time domain positions after the time domain position corresponding to the CSI measurement result information. In other words, the CSI measurement result information is used to predict the CSI information for a future period.

[0193] When a terminal device acquires CSI measurement result information based on a reference signal, the predicted channel information can include channel information corresponding to one or more time domain positions after the time domain position where the reference signal is located, or channel information corresponding to one or more time domain positions after the time domain position corresponding to the CSI measurement result information. In other words, the channel information for a future period is predicted using the CSI measurement result information.

[0194] For example, in Figure 3, the terminal device performs channel measurement and / or interference measurement based on the reference signal in time slot n-4 to obtain the CSI measurement result information corresponding to time slot n-4. That is, the time domain location of the reference signal is time slot n-4, and the CSI measurement result information corresponding to time slot n-4 includes the CSI information and / or channel information corresponding to time slot n-4. Then, CSI prediction is performed on the CSI measurement result information corresponding to time slot n-4 to obtain the CSI prediction information corresponding to time slot n+1 and time slot n+2. The CSI prediction information corresponding to time slot n+1 may include the CSI information and / or channel information corresponding to time slot n+1, and the CSI prediction information corresponding to time slot n+2 may include the CSI information and / or channel information corresponding to time slot n+2.

[0195] AI-based CSI prediction can refer to methods that use AI technology to predict CSI results. It can be a method that uses machine learning and data-driven approaches to optimize and enhance the traditional CSI prediction process, and can be implemented through AI models. In other words, it uses AI to perform CSI prediction.

[0196] For example, CSI prediction information can be obtained by using an AI model to perform CSI measurement results information, thereby realizing AI-based CSI prediction.

[0197] Non-AI-based CSI prediction refers to methods that perform CSI prediction without using AI technology. In other words, it involves performing CSI prediction in a non-AI manner.

[0198] CSI compression and CSI reconstruction

[0199] CSI measurement results may have a large number of bits, and directly feeding back these results through CSI reports would lead to high resource consumption and signaling overhead. Therefore, to reduce resource consumption and signaling overhead, this embodiment can compress the CSI measurement results to obtain compressed CSI information.

[0200] It should be noted that CSI compressed information can be understood as the relevant information obtained by compressing the CSI measurement result information. Thus, compared to the original CSI measurement result information, CSI compressed information has the characteristics of a smaller number of bits, which helps to reduce resource consumption and signaling overhead when reporting CSI compressed information.

[0201] For example, in Figure 3, the terminal device performs channel measurements and / or interference measurements based on the reference signal in time slot n-4 to obtain CSI measurement result information corresponding to time slot n-4. Then, the terminal device compresses the CSI measurement result information corresponding to time slot n-4 to obtain CSI compressed information.

[0202] The counterpart to CSI compression is CSI reconstruction, which restores compressed CSI information to its original form. In other words, CSI reconstruction is the inverse process of CSI compression.

[0203] AI-based CSI compression can refer to methods that use AI technology to achieve CSI compression. It can be a method that uses machine learning and data-driven approaches to optimize and enhance the traditional CSI compression process, and can be implemented through AI models. In other words, it uses AI to perform CSI compression.

[0204] For example, CSI compression information can be obtained by using an AI model to compress CSI measurement results, thereby achieving AI-based CSI compression.

[0205] AI-based CSI refactoring can refer to methods that use AI technology to refactor CSI. It can be a method that uses machine learning and data-driven approaches to optimize and enhance the traditional CSI refactoring process, and can be implemented through AI models. In other words, it involves using AI to perform CSI refactoring.

[0206] For example, CSI reconstruction can be performed on compressed CSI information using an AI model to obtain the original CSI measurement results, thereby achieving AI-based CSI reconstruction.

[0207] Non-AI-based CSI compression refers to methods that implement CSI compression without using AI technology. In other words, it involves performing CSI compression in a non-AI manner.

[0208] Non-AI-based CSI refactoring refers to methods that refactor CSI without using AI technology. In other words, it involves performing CSI refactoring in a non-AI manner.

[0209] CSI Prediction and CSI Compression

[0210] CSI prediction information obtained based on CSI measurement results may have a large number of bits. Directly feeding back the CSI prediction information through CSI reports would result in high resource consumption and signaling overhead. Therefore, to reduce resource consumption and signaling overhead, this embodiment can compress the CSI prediction information to obtain compressed CSI prediction information.

[0211] It should be noted that CSI prediction compressed information can be understood as information obtained by first performing CSI prediction on the CSI measurement result and then performing CSI compression. Therefore, compared to CSI prediction information, CSI prediction compressed information has the advantages of fewer bits, which helps reduce resource consumption and signaling overhead when reporting CSI prediction compressed information.

[0212] For example, in Figure 3, the terminal device performs channel measurement and / or interference measurement based on the reference signal on time slot n-4 to obtain the CSI measurement result information corresponding to time slot n-4. Then, CSI prediction and CSI compression are performed on the CSI measurement result information corresponding to time slot n-4 to obtain the CSI prediction and compression information corresponding to time slot n+1 and time slot n+2, and / or the CSI prediction and compression information jointly corresponding to time slot n+1 and time slot n+2.

[0213] It is worth noting that the CSI prediction compression information corresponding to time slot n+1 can be obtained by performing CSI prediction and CSI compression on the CSI measurement result information corresponding to time slot n-4. For example, CSI prediction is performed on the CSI measurement result information corresponding to time slot n-4 to obtain the CSI prediction information corresponding to time slot n+1, and then CSI compression is performed on the CSI prediction information corresponding to time slot n+1 to obtain the CSI prediction compression information corresponding to time slot n+1.

[0214] The CSI prediction compression information corresponding to time slot n+2 is obtained by performing CSI prediction and CSI compression on the CSI measurement results information corresponding to time slot n-4. For example, CSI prediction is performed on the CSI measurement results information corresponding to time slot n-4 to obtain the CSI prediction information corresponding to time slot n+2, and then CSI compression is performed on the CSI prediction information corresponding to time slot n+2 to obtain the CSI prediction compression information corresponding to time slot n+2.

[0215] The CSI prediction compression information corresponding to time slot n+1 and time slot n+2 is obtained by using an AI model to predict the CSI measurement results information corresponding to time slot n-4 to obtain the predicted CSI information corresponding to time slot n+1 and time slot n+2, and then performing joint CSI compression on the predicted CSI information corresponding to time slot n+1 and time slot n+2.

[0216] AI-based CSI prediction and compression (i.e., AI-based CSI prediction and compression) can refer to methods that use AI technology to achieve CSI prediction and compression. It can be a method that utilizes machine learning and data-driven approaches to optimize and enhance the traditional CSI prediction and compression process, and can be implemented through AI models. In other words, it uses AI to perform CSI prediction and compression.

[0217] For example, the same AI model can be used to perform CSI prediction and CSI compression on CSI measurement results to obtain CSI prediction compressed information. Alternatively, one AI model can be used to perform CSI prediction on CSI measurement results to obtain CSI prediction information, and then another AI model can be used to perform CSI compression on the CSI prediction information to obtain CSI prediction compressed information.

[0218] Non-AI-based CSI prediction and compression refers to methods that achieve CSI prediction and compression without using AI technology. In other words, it involves performing CSI prediction and compression in a non-AI manner.

[0219] CSI processing based on measurement resources no later than the CSI reference signal

[0220] It should be noted that each CSI report corresponds to a CSI reference resource. When a network device configures at least one measurement resource for CSI measurement to a terminal device, the at least one measurement resource may include the CSI reference resource corresponding to the CSI report and the measurement resource associated with the CSI report.

[0221] For example, for periodic CSI reporting, CSI will be reported periodically, and each CSI report will correspond to a CSI reference resource.

[0222] A CSI reference resource can be a time-frequency resource. The time domain of a CSI reference resource can be a time slot, and the frequency domain can be the frequency granularity of the CSI measurement. For example, when CSI is used for subband measurement, the frequency domain of the CSI reference resource is subband; when CSI is used for wideband measurement, the frequency domain of the CSI reference resource is wideband.

[0223] When the uplink time slot where the CSI report is located is time slot n′ (where n′ represents the time slot index), the downlink time slot where the CSI reference resource is located is time slot n′. K offset This indicates a parameter configured at a higher level. This indicates that in the frequency range 1 and K offset Subcarrier spacing configuration with μ = 0 DL This indicates the downlink subcarrier spacing configuration.

[0224] Since the CSI reference resource is a downlink resource, its time domain is the downlink time slot. Therefore, time slot n represents the downlink time slot corresponding to time slot n′, and is calculated as follows:

[0225] Where, μ UL Indicates the uplink subcarrier spacing configuration. and μ offset,DL Indicates downlink time slot offset. and This indicates the uplink time slot offset.

[0226] n CSI_ref This indicates the slot offset between slot n and the CSI reference resource located in the effective downlink slot.

[0227] For periodic or non-continuous CSI reporting, if the CSI report is associated with a channel measurement resource (such as a CSI-RS / SSB for channel measurement), then n CSI_ref It is greater than or equal to This ensures that the CSI reference resource corresponding to the CSI report is located at the minimum of the effective downlink time slot.

[0228] For example, assuming the uplink and downlink subcarrier spacing is the same, i.e., μ DL =μ UL =0. From greater than or equal to Let n start with the minimum value in the range. CSI_ref for Calculated It then determines whether time slot n-4 is a valid downlink time slot. If time slot n-4 is a valid downlink time slot, then the CSI reference resource is located in time slot n-4; if time slot n-4 is not a valid downlink time slot, then n... CSI_ref for Calculated It then determines whether time slot n-5 is a valid downlink time slot. If time slot n-5 is a valid downlink time slot, the CSI reference resource is located in time slot n-5; if time slot n-5 is not a valid downlink time slot, the search continues backward until a valid downlink time slot is found.

[0229] For periodic or non-continuous CSI reporting, if the CSI report is associated with multiple channel measurement resources (such as multiple CSI-RS / SSBs used for channel measurement), then n CSI_ref It is greater than or equal to This ensures that the CSI reference resource corresponding to the CSI report is located at the minimum of the effective downlink time slot.

[0230] For aperiodic events, if the downlink control information (DCI) used to trigger the CSI report is in the same time slot as the CSI report, then the CSI reference resource is located in the time slot of the DCI; otherwise, n CSI_ref It is greater than or equal to This ensures that the CSI reference resource corresponding to the CSI report is located at the minimum of the effective downlink time slot. Z′ represents the number of symbols contained in a time slot, and Z′ represents the processing time for CSI computation.

[0231] It should be noted that for a downlink time slot to be considered a "valid downlink time slot", the following conditions must be met: the downlink time slot must include at least one downlink symbol or flexible symbol configured by higher-layer signaling; and / or, the downlink time slot is not located within a configured measurement gap.

[0232] CSI reference resources can be used to determine the measurement resources associated with CSI reporting. This is because network devices can configure at least one measurement resource for CSI measurement to terminal devices. This at least one measurement resource can include the CSI reference resource corresponding to the CSI report and the measurement resources associated with the CSI report. The measurement resources associated with the CSI report are no later than the CSI reference resource corresponding to the CSI report. That is, the time-domain location of the measurement resources associated with the CSI report is before the CSI reference resource corresponding to the CSI report. In other words, measurement resources located before the CSI reference resource corresponding to the CSI report can be used as the measurement resources associated with the CSI report. Which measurements can be used as the measurement resources associated with the CSI report can be determined through higher-layer signaling configuration, protocol specifications, pre-configuration, or by the terminal device itself.

[0233] Therefore, CSI processing based on measurement resources no later than CSI reference resources can be understood as performing at least one of CSI measurement, CSI calculation, or CSI reporting based on measurement resources no later than CSI reference resources.

[0234] CSI's fallback mechanism

[0235] When a terminal device performs a certain CSI process, the CSI process may have drawbacks, fail to execute successfully, or fail to achieve the expected results. Therefore, this embodiment introduces a rollback mechanism for CSI processes.

[0236] A rollback mechanism for CSI processing refers to a mechanism or method used when a CSI process has flaws, fails to execute successfully, or fails to achieve the expected results. This mechanism aims to allow the CSI process to return to, be restored to, or be revoked to a processable, executable, or predictable state.

[0237] For example, taking AI-based CSI processing as an example, the application of AI technology to CSI processing can bring both advantages and disadvantages. For instance, AI-based CSI processing may have poor performance or high resource requirements, leading to drawbacks such as failure to execute successfully or failure to achieve the expected results. Therefore, in the CSI processing rollback mechanism, the terminal device can roll back the AI-based CSI processing.

[0238] It should be noted that, compared to non-AI-based CSI processing, AI-based CSI processing requires the use of AI technology, which typically requires more resources (such as memory, computing power, or power) or higher terminal device capabilities. Therefore, when rolling back AI-based CSI processing, it is usually done by rolling back to non-AI-based CSI processing or not performing CSI processing at all.

[0239] Furthermore, regarding the CSI processing fallback mechanism, the network device in this embodiment can enable or disable the CSI processing fallback mechanism through network configuration or network indication, pre-configuration, pre-definition, standard protocol specifications, or default methods. Thus, when the CSI processing fallback mechanism is enabled, the terminal device can use it. When the CSI processing fallback mechanism is disabled, the terminal device cannot use it. Additionally, this embodiment involves fallback methods or fallback triggering conditions within the CSI processing fallback mechanism. These will be explained in detail below.

[0240] [Rollback Method]

[0241] The rollback method refers to the specific method or strategy used to roll back CSI processing. For example, the rollback method could be to roll back one type of CSI processing to another, or to roll back one type of CSI processing to the point where no CSI processing is performed. Furthermore, since there are different types of CSI processing, this embodiment can employ different rollback methods for different types of CSI processing.

[0242] For example, taking AI-based CSI processing as an example, as shown in Table 1, the rollback methods include Rollback Method 1, Rollback Method 2, and Rollback Method 3. Rollback Method 1 rolls back one AI-based CSI process to another AI-based CSI process; Rollback Method 2 rolls back one AI-based CSI process to a non-AI-based CSI process; and Rollback Method 3 rolls back one AI-based CSI process to a process where CSI processing is not used. Not using CSI processing can be understood as not performing at least one of the following: CSI measurement, CSI calculation, CSI reporting, or CSI update.

[0243] It should be understood that the rollback method in this embodiment is not limited to that shown in Table 1, and may include other rollback methods, without specific limitations.

[0244] Table 1

[0245] The following example illustrates the rollback process for different types of CSI handling.

[0246] For example, taking the rollback of AI-based CSI prediction and CSI compression as an example, the rollback can be performed as follows: AI-based CSI prediction and CSI compression can be rolled back to AI-based CSI prediction, or back to AI-based CSI prediction and non-AI-based CSI compression, or back to AI-based CSI compression, or back to other AI-based CSI processing, or back to non-AI-based CSI prediction and AI-based CSI compression, or back to non-AI-based CSI prediction and non-AI-based CSI compression, or back to CSI processing based on measurement resources no later than the CSI reference resources, or back to other non-AI-based CSI processing, or back to no CSI processing. It should be understood that the rollback of AI-based CSI prediction and CSI compression in this embodiment is not limited to the above methods and may include other rollback methods, which are not specifically limited.

[0247] For example, taking the rollback of AI-based CSI prediction as an example, the AI-based CSI prediction can be rolled back to AI-based CSI compression, or back to other AI-based CSI processing, or back to a combination of non-AI CSI prediction and AI-based CSI compression, or back to a combination of non-AI CSI prediction and non-AI CSI compression, or back to a non-AI CSI prediction, or back to non-AI CSI compression, or back to CSI processing based on measurement resources no later than the CSI reference resources, or back to other non-AI-based CSI processing, or back to not using CSI processing. It should be understood that the rollback of AI-based CSI prediction in this embodiment is not limited to the above methods and may include other rollback methods, which are not specifically limited.

[0248] For example, taking the rollback of AI-based CSI compression as an example, the rollback can be performed as follows: AI-based CSI compression can be rolled back to AI-based CSI prediction, or back to other AI-based CSI processing, or back to a combination of non-AI CSI prediction and AI-based CSI compression, or back to a combination of non-AI CSI prediction and non-AI CSI compression, or back to a combination of non-AI CSI prediction and non-AI CSI compression, or back to CSI processing based on measurement resources no later than the CSI reference resources, or back to other non-AI-based CSI processing, or back to no CSI processing at all. It should be understood that the rollback of AI-based CSI compression in this embodiment is not limited to the above methods and may include other rollback methods, which are not specifically limited.

[0249] For example, taking the rollback of non-AI-based CSI prediction and CSI compression as an example, the rollback can be performed as follows: the non-AI-based CSI prediction and CSI compression can be rolled back to non-AI-based CSI prediction, or back to non-AI-based CSI compression, or back to CSI processing based on measurement resources no later than the CSI reference resources, or back to other non-AI-based CSI processing, or back to no CSI processing at all. It should be understood that the rollback of non-AI-based CSI prediction and CSI compression in this embodiment is not limited to the above methods and may include other rollback methods, which are not specifically limited.

[0250] For example, taking the rollback of non-AI-based CSI predictions as an example, the rollback can be performed by reverting the non-AI-based CSI prediction to non-AI-based CSI compression, or to CSI processing based on measurement resources no later than the CSI reference resources, or to other non-AI-based CSI processing, or to not using CSI processing at all. It should be understood that the rollback of non-AI-based CSI predictions in this embodiment is not limited to the above methods and may include other rollback methods, which are not specifically limited.

[0251] For example, taking the rollback of non-AI-based CSI compression as an example, the rollback can be performed by reverting from non-AI-based CSI compression to non-AI-based CSI prediction, or to CSI processing based on measurement resources no later than the CSI reference resources, or to other non-AI-based CSI processing, or to not using CSI processing. It should be understood that the rollback of non-AI-based CSI compression in this embodiment is not limited to the above methods and may include other rollback methods, without specific limitations.

[0252] It should be noted that, regarding the rollback method, the network device in this embodiment can indicate or configure the rollback method to the terminal device through higher-layer signaling (such as RRC signaling or MAC signaling), DCI, or system information. In this way, the terminal device can roll back the CSI processing according to the rollback method indicated or configured by the network.

[0253] [Revert Trigger Conditions]

[0254] A rollback trigger condition can refer to the conditions or events that must be met to trigger a rollback of a certain CSI process. For example, a rollback trigger condition could be that the performance information of the CSI process does not meet preset requirements, or that the resource requirements of the CSI process exceed the capabilities of the terminal device, or that the device status information of the terminal device does not support the CSI process.

[0255] It should be noted that the fallback trigger condition is network configuration or network indication, preconfiguration, predefinition, standard protocol specification, or default specification.

[0256] In addition, since there are different types of CSI processing, this embodiment can use different rollback trigger conditions for different types of CSI processing.

[0257] For example, taking AI-based CSI processing as an example, as shown in Table 2, the types of rollback trigger conditions include rollback trigger condition 1, rollback trigger condition 2, and rollback trigger condition 3. Among them, rollback trigger condition 1 is when the performance information of AI-based CSI processing does not meet the preset requirements; rollback trigger condition 2 is when the resource requirement information of AI-based CSI processing exceeds the capabilities of the terminal device; and rollback trigger condition 3 is when the device status information of the terminal device does not support AI-based CSI processing.

[0258] It should be understood that the rollback triggering conditions in this embodiment are not limited to those shown in Table 2, and may include other rollback triggering conditions, which are not specifically limited.

[0259] Table 2

[0260] "Performance information of CSI processing"

[0261] The performance information of CSI processing can represent the relevant performance under the execution of CSI processing.

[0262] In this way, the terminal device will determine whether the performance information of the CSI processing meets the preset requirements. When the performance information of the CSI processing does not meet the preset requirements, it indicates that the rollback trigger condition has been triggered. At this time, the terminal device will roll back the CSI processing.

[0263] In some possible examples, the performance information of the CSI processing includes at least one of the following: the accuracy of the CSI processing (or accuracy rate, error rate, etc.), the processing time of the CSI processing, the memory usage rate of the CSI processing, the resource utilization rate of the CSI processing, the complexity of the CSI processing, the data distribution characteristics of the CSI processing, or the signal transmission performance information of the CSI processing. It should be understood that the performance information of the CSI processing in this embodiment is not limited to the above content and may include other performance information, which is not specifically limited. These will be described in detail below.

[0264] The accuracy of CSI processing can be expressed as the degree of similarity, matching degree, or error between the processed information obtained from CSI processing and the actual ground truth. The actual ground truth can refer to the true and accurate answer or result expected by this embodiment during CSI processing.

[0265] For example, taking CSI processing as AI-based CSI prediction, the resulting information is CSI prediction information. As another example, taking CSI processing as AI-based CSI prediction and CSI compression, the resulting information is CSI prediction compression information.

[0266] In this way, the terminal device can determine whether the accuracy of the CSI processing meets the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby executing the rollback of the CSI processing.

[0267] Table 3

[0268] It should be noted that, in one possible example, this embodiment may introduce a preset accuracy threshold to determine whether the accuracy of a certain CSI process meets the preset requirements. Specifically, if the accuracy of the CSI process is greater than or equal to the preset accuracy threshold, it indicates that the accuracy of the CSI process does not meet the preset requirements. If the accuracy of the CSI process is less than the preset accuracy threshold, it indicates that the accuracy of the CSI process meets the preset requirements.

[0269] For different types of CSI processing, the preset accuracy threshold can be a network configuration or network indication, a pre-configured threshold, a predefined threshold, a standard protocol specification, or a default threshold. Furthermore, the preset accuracy thresholds corresponding to different types of CSI processing can be the same or different. For example, different types of CSI processing correspond to different preset accuracy thresholds, as shown in Table 3. It should be understood that the correspondence between CSI processing and preset accuracy thresholds in this embodiment is not limited to that shown in Table 3, and may include other correspondences, which are not specifically limited.

[0270] The processing time for CSI processing can represent the time required to complete the CSI processing.

[0271] In this way, the terminal device can determine whether the processing time of the CSI process meets the preset requirements, and decide whether the rollback trigger condition should be triggered. If the preset requirements are met, the rollback trigger condition is triggered, thereby executing the rollback of the CSI process.

[0272] It should be noted that, regarding whether the processing time of a certain CSI process meets the preset requirements, in one possible example, this embodiment may introduce a preset processing time threshold. Specifically, if the processing time of the CSI process is less than the preset processing time threshold, it indicates that the processing time of the CSI process does not meet the preset requirements. If the processing time of the CSI process is greater than or equal to the preset processing time threshold, it indicates that the processing time of the CSI process meets the preset requirements.

[0273] For different types of CSI processing, the preset processing time threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default setting. Furthermore, the preset processing time thresholds for different types of CSI processing can be the same or different.

[0274] The memory usage rate of CSI processing indicates the amount of memory used by CSI processing. Memory refers to the hardware devices or components used to store data and programs.

[0275] In this way, the terminal device can determine whether the memory usage rate of the CSI process meets the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby rolling back the CSI process.

[0276] It should be noted that, in one possible example, this embodiment may introduce a preset memory usage threshold to determine whether the memory usage rate of a certain CSI process meets the preset requirements. Specifically, if the memory usage rate of the CSI process is less than the preset threshold, it indicates that the memory usage rate of the CSI process does not meet the preset requirements. If the memory usage rate of the CSI process is greater than or equal to the preset threshold, it indicates that the memory usage rate of the CSI process meets the preset requirements.

[0277] For different types of CSI processing, the preset memory usage threshold can be a network configuration or network indication, a pre-configured threshold, a predefined threshold, a standard protocol specification, or a default threshold. Furthermore, the preset memory usage thresholds for different types of CSI processing can be the same or different.

[0278] Resource utilization in CSI processing can represent the proportion of various resources used in the CSI processing process (such as CSI processing based on an AI model), or it can represent the proportion of various resources used when performing CSI processing based on an AI model. These resources can include computing power, processing units (such as central processing units (CPUs) or graphics processing units (GPUs), memory, storage units, network bandwidth, or power consumption.

[0279] In this way, the terminal device can determine whether the resource utilization of the CSI process meets the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby rolling back the CSI process.

[0280] It should be noted that, in one possible example, this embodiment may introduce a preset resource utilization threshold to determine whether the resource utilization rate of a certain CSI process meets the preset requirements. Specifically, if the resource utilization rate of the CSI process is less than the preset threshold, it indicates that the resource utilization rate of the CSI process does not meet the preset requirements. If the resource utilization rate of the CSI process is greater than or equal to the preset threshold, it indicates that the resource utilization rate of the CSI process meets the preset requirements.

[0281] For different types of CSI processing, the preset resource utilization threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default setting. Furthermore, the preset resource utilization thresholds for different types of CSI processing can be the same or different.

[0282] The complexity of CSI processing can be described as the degree of complexity in the CSI processing procedure (such as CSI processing based on an AI model). Lower complexity in CSI processing means less computing power, fewer resources, or shorter processing time.

[0283] In this way, the terminal device can determine whether the complexity of the CSI process meets the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby rolling back the CSI process.

[0284] It should be noted that, in one possible example, this embodiment may introduce a preset complexity threshold to determine whether the complexity of a certain CSI process meets the preset requirements. Specifically, if the complexity of the CSI process is less than the preset complexity threshold, it indicates that the complexity of the CSI process does not meet the preset requirements. If the complexity of the CSI process is greater than or equal to the preset complexity threshold, it indicates that the complexity of the CSI process meets the preset requirements.

[0285] For different types of CSI processing, the preset complexity threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default specification. Furthermore, the preset complexity thresholds for different types of CSI processing can be the same or different.

[0286] The data distribution characteristics of CSI processing can represent the data distribution characteristics used in the CSI processing process (mainly for AI-based CSI processing). These data distribution characteristics can be characterized by factors such as the degree or magnitude of data drift.

[0287] Data drift refers to the phenomenon where the data distribution changes after an AI model is deployed. This change can lead to deviations in the AI ​​model's output because the data distribution used during training differs from the actual data distribution after deployment. Generally, the smaller the degree or magnitude of data drift, the better the CSI processing performance and the more it meets the requirements.

[0288] In this way, the terminal device can determine whether the data distribution characteristics of the CSI processing meet the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby rolling back the CSI processing.

[0289] It should be noted that, in one possible example, this embodiment may introduce a preset data distribution characteristic threshold to determine whether the data distribution characteristics processed by a certain CSI meet the preset requirements. Specifically, if the data distribution characteristic processed by the CSI is less than the preset data distribution characteristic threshold, it indicates that the data distribution characteristic processed by the CSI does not meet the preset requirements. If the data distribution characteristic processed by the CSI is greater than or equal to the preset data distribution characteristic threshold, it indicates that the data distribution characteristic processed by the CSI meets the preset requirements.

[0290] For different types of CSI processing, the preset data distribution characteristic threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default setting. Furthermore, the preset data distribution characteristic thresholds corresponding to different types of CSI processing can be the same or different.

[0291] CSI-processed signal transmission performance information can represent the transmission performance of a signal under CSI processing.

[0292] In this way, the terminal device can determine whether the signal transmission performance information of the CSI processing meets the preset requirements, and decide whether to trigger the rollback condition. If the preset requirements are met, the rollback condition is triggered, thereby rolling back the CSI processing.

[0293] For example, the signal transmission performance information processed by the CSI may include at least one of the following: signal-to-noise ratio (SNR), signal-to-interference-plus-noise ratio (SINR), bit error rate (BER), block error rate (BLER), or the probability of negative acknowledgment (NACK) for hybrid automatic repeat request (HARQ). It should be understood that the signal transmission performance information processed by the CSI in this embodiment is not limited to the above-mentioned content and may also include other signal transmission performance information, without specific limitations.

[0294] SNR or SINR can represent the signal quality of a signal under CSI processing. A higher SNR or SINR indicates a stronger signal relative to noise and easier demodulation, signifying better CSI processing performance and greater responsiveness.

[0295] To determine whether the SNR or SINR meets the preset requirements, in one possible example, this embodiment may introduce a preset SNR threshold or a preset SINR threshold. If the SNR or SINR is greater than or equal to the preset SNR threshold or preset SINR threshold, it indicates that the SNR or SINR does not meet the preset requirements. If the SNR or SINR is less than the preset SNR threshold or preset SINR threshold, it indicates that the SNR or SINR meets the preset requirements.

[0296] For different types of CSI processing, the preset SNR threshold or preset SINR threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default specification. Furthermore, the preset SNR threshold or preset SINR threshold corresponding to different types of CSI processing can be the same or different.

[0297] BER or BLER can represent the signal transmission quality of a signal under CSI processing. The smaller the BER or BLER, the stronger the system's anti-interference capability and the higher the signal transmission quality, indicating better CSI processing performance and better meeting the requirements.

[0298] To determine whether the BER or BLER meets the preset requirements, in one possible example, this embodiment may introduce a preset BER threshold or a preset BLER threshold. If the BER or BLER is less than the preset BER threshold or preset BLER threshold, it indicates that the BER or BLER does not meet the preset requirements. If the BER or BLER is greater than or equal to the preset BER threshold or preset BLER threshold, it indicates that the BER or BLER meets the preset requirements.

[0299] For different types of CSI processing, the preset BER threshold or preset BLER threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default specification. Furthermore, the preset BER threshold or preset BLER threshold corresponding to different types of CSI processing can be the same or different.

[0300] The probability of HARQ NACK represents the probability of unsuccessful signal transmission under CSI processing. A lower HARQ NACK probability indicates a lower probability of unsuccessful signal transmission, signifying better CSI processing performance and greater responsiveness to requirements.

[0301] To determine whether the probability of a HARQ NACK meets a preset requirement, in one possible example, this embodiment can introduce a preset probability threshold. Specifically, if the probability of a HARQ NACK is less than the preset probability threshold, it indicates that the probability of a HARQ NACK does not meet the preset requirement. If the probability of a HARQ NACK is greater than or equal to the preset probability threshold, it indicates that the probability of a HARQ NACK meets the preset requirement.

[0302] For different types of CSI processing, the preset probability threshold can be network configuration or network indication, pre-configured, pre-defined, specified by standard protocols, or a default setting. Furthermore, the preset probability thresholds for different types of CSI processing can be the same or different.

[0303] "Resource requirement information processed by CSI"

[0304] The resource requirement information processed by CSI can represent the various resources required for CSI processing. These resources may include computing power, processing units, memory, storage units, network bandwidth, or power consumption, etc.

[0305] It should be noted that terminal devices have their own capabilities, and different terminal devices can have different capabilities. Therefore, a terminal device can determine whether the resource requirements for the CSI processing exceed its capabilities to decide whether to trigger the rollback condition. If the requirements exceed the terminal device's capabilities, the rollback condition is triggered, thus rolling back the CSI processing.

[0306] In some possible examples, the resource requirements information for CSI processing includes at least one of the following: computing power required for CSI processing, processing units required for CSI processing, memory required for CSI processing, storage units required for CSI processing, network bandwidth required for CSI processing, or power required for CSI processing. It should be understood that the resource requirements information for CSI processing in this embodiment is not limited to the above, and may include other resource requirements information, without specific limitations.

[0307] It should be noted that the following statements are relevant to CSI processing: 1. The computing power required for CSI processing exceeds the capabilities of the terminal device. 2. The processing units required for CSI processing exceed the capabilities of the terminal device. 3. The computing power or number of processing units required for CSI processing exceeds the computing power or number of processing units that the terminal device can provide. 4. The memory required for CSI processing exceeds the capabilities of the terminal device. 5. The memory or storage capacity required for CSI processing exceeds the capacity or storage capacity that the terminal device can provide. 6. The storage units required for CSI processing exceed the capabilities of the terminal device. 7. The storage units required for CSI processing exceed the capacity or storage capacity that the terminal device can provide. 8. The network bandwidth required for CSI processing exceeds the capabilities of the terminal device. 9. The network bandwidth or speed required for CSI processing exceeds the capacity or speed that the terminal device can provide. 10. The power required for CSI processing exceeds the capabilities of the terminal device. 11. The power required for CSI processing exceeds the power supply that the terminal device can provide.

[0308] "Device status information of terminal devices"

[0309] Device status information of a terminal device can represent a collection of various parameters and indicators such as the current operating status, operating environment, location, movement, or health of the terminal device.

[0310] In this way, the terminal device can determine whether its device status information supports CSI processing, and decide whether to trigger the rollback condition. If the CSI processing is not supported, the rollback condition is triggered, thereby rolling back the CSI processing.

[0311] In some possible examples, the device status information of the terminal device includes operating status information, mobility status information, location status information, mobility speed information, battery status information, network connection status, or environmental status information, etc. It should be understood that the device status information of the terminal device in this embodiment is not limited to the above content, and may also include other device status information, without specific limitations.

[0312] Operational status information can be used to determine the current operational state of the terminal device, such as power-on, standby, or running. This allows the terminal device to determine whether the operational status information supports CSI processing, and thus decide whether the rollback trigger condition should be triggered. For example, when the terminal device is in standby mode, it may not support CSI processing.

[0313] Mobility status information can be used to determine whether a terminal device is currently in motion, such as whether it is moving or not. This allows the terminal device to determine whether the mobility status information supports CSI processing, and thus decide whether the fallback trigger condition should be triggered. For example, when the terminal device is in motion, it may not support CSI processing.

[0314] Location status information can be used to determine the current geographical location of the terminal device. This allows the terminal device to determine whether the location status information supports CSI processing, and thus decide whether the fallback trigger condition should be triggered. When the terminal device is within a preset location range, it may not support CSI processing.

[0315] Movement speed information can be used to determine the current movement speed of the terminal device. This allows the terminal device to determine whether the movement speed information supports CSI processing, and thus decide whether the fallback trigger condition should be triggered. For example, when the terminal device's movement speed is within a preset movement speed range, the terminal device may not support CSI processing.

[0316] Battery status information can be used to determine the current remaining battery power of a terminal device. This allows the terminal device to determine whether the battery status information supports CSI processing, and thus decide whether to trigger the fallback condition. For example, when the terminal device's remaining battery power is within a preset range, the terminal device may not support CSI processing.

[0317] Network connectivity status can be used to determine whether a terminal device is currently connected to a network and the type of network it is connected to. This allows the terminal device to determine whether the network connectivity status supports CSI processing, and thus decide whether the fallback trigger condition should be triggered. For example, when the terminal device is not connected to a network, it may not support CSI processing.

[0318] Environmental status information can be used to determine the physical parameters of the current surrounding environment of the terminal device, such as temperature, humidity, and light intensity. This allows the terminal device to determine whether the environmental status information supports CSI processing, and thus decide whether to trigger the fallback conditions. For example, if the temperature around the terminal device is within a preset temperature range, the terminal device may not support CSI processing.

[0319] [Rollback Trigger Conditions and Corresponding Rollback Methods]

[0320] It should be noted that this embodiment can establish a comparison or association between rollback trigger conditions and rollback methods through network configuration or network indication, pre-configuration, pre-definition, standard protocol specifications, or default specifications. Different rollback trigger conditions correspond to different rollback methods. Thus, when a rollback trigger condition is triggered, the terminal device can roll back the CSI processing according to the rollback method corresponding to the triggered rollback trigger condition.

[0321] Table 4

[0322] For example, based on Tables 1 and 2, as shown in Table 4, rollback trigger condition 1 corresponds to rollback method 1, rollback trigger condition 2 corresponds to rollback method 2, and rollback trigger condition 3 corresponds to rollback method 3. Thus, when rollback trigger condition 1 is triggered, the terminal device can roll back the CSI processing according to rollback method 1; when rollback trigger condition 2 is triggered, the terminal device can roll back the CSI processing according to rollback method 2; and when rollback trigger condition 3 is triggered, the terminal device can roll back the CSI processing according to rollback method 3.

[0323] It should be understood that the correspondence between the rollback triggering conditions and the rollback methods in this embodiment is not limited to that shown in Table 3, and may include other correspondences, which are not specifically limited.

[0324] [Example of CSI-handled rollback]

[0325] The following embodiment uses the rollback of the first CSI process according to the first rollback method as an example for illustration. As shown in Figure 4, Figure 4 is a flowchart of a communication method according to an embodiment of this application, which specifically includes the following steps:

[0326] S410. The terminal device determines the first rollback method.

[0327] S420. The terminal device rolls back the first CSI process according to the first rollback method, whereby the first CSI process refers to AI-based CSI processing.

[0328] It is evident that when AI technology is applied to CSI processing, it can bring both advantages, such as enabling intelligent CSI processing, improving air interface performance, or reducing air interface overhead, and disadvantages, such as the AI ​​inference process consuming significant computing power or a large discrepancy between the AI's inference results and the actual results. Therefore, this embodiment introduces a rollback mechanism for CSI processing.

[0329] Thus, in the rollback mechanism of CSI processing, when the first CSI processing has problems such as drawbacks, failure to execute successfully, or failure to achieve the expected results, the terminal device can roll back the first CSI processing according to the first rollback method, so that the first CSI processing can return, restore or cancel to a processable, executable or predictable state.

[0330] It should be noted that the first rollback method can be any rollback method used to roll back the first CSI processing. The first CSI processing refers to AI-based CSI processing. For example, the first CSI processing may include AI-based CSI prediction and / or CSI compression. Of course, the first CSI processing may also include other AI-based CSI processing, without specific limitations.

[0331] Regarding the determination of the first rollback method in S410, one possible implementation is as follows:

[0332] The network device configures or indicates the first fallback method to the terminal device through higher-layer signaling (such as RRC signaling or MAC signaling), DCI, or system information, that is, the network configures or indicates the first fallback method. For example, as shown in Figure 5, which is a flowchart of another communication method according to an embodiment of this application, it specifically includes the following steps:

[0333] S510. The network device sends a rollback mode indication information, which is used to indicate the first rollback mode.

[0334] Correspondingly, the terminal device receives the rollback method instruction information.

[0335] The fallback method indication information can be carried by RRC signaling, MAC signaling, DCI or system information.

[0336] S520 is the same as S420, so it will not be described again.

[0337] As can be seen, the fallback method indication information enables the network device to configure or indicate the first fallback method to the terminal device, so that the terminal device can determine the first fallback method through the fallback method indication information. Since the first fallback method is configured or indicated by the network, the terminal device can fall back the first CSI processing according to the network requirements.

[0338] Another possible implementation of determining the first rollback method in S410 is as follows:

[0339] First, the terminal device can determine one or more fallback trigger conditions and the fallback method corresponding to those conditions through network configuration, network indication, pre-configuration, pre-definition, standard protocol specifications, or default specifications. Then, the terminal device can decide whether any of the one or more fallback trigger conditions is triggered. Finally, the terminal device can use the fallback method corresponding to the triggered fallback trigger condition as the first fallback method, thereby determining the first fallback method. For example, as shown in Figure 6, which is a flowchart of another communication method according to an embodiment of this application, the method specifically includes the following steps:

[0340] S610. The terminal device determines one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions.

[0341] S620. If one or more rollback trigger conditions are triggered, the terminal device determines that the rollback method corresponding to the triggered rollback trigger condition is the first rollback method.

[0342] S630 is the same as S420, so it will not be described again.

[0343] As can be seen, the terminal device in this embodiment can decide on its own whether a rollback trigger condition is triggered among the one or more rollback trigger conditions, and roll back the first CSI process according to the rollback method corresponding to the triggered rollback trigger condition.

[0344] In S610, determining one or more rollback trigger conditions and the rollback method corresponding to those one or more rollback trigger conditions can be achieved through network configuration or network indication, pre-configuration, pre-definition, standard protocol specification, or default specification.

[0345] For example, taking network configuration or network indication as an example, as shown in Figure 7, Figure 7 is a flowchart of another communication method according to an embodiment of this application, which specifically includes the following steps:

[0346] S710. The network device sends configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions.

[0347] Correspondingly, the terminal device receives the configuration information.

[0348] S720 is the same as S620, so it will not be described again.

[0349] The S730 is the same as the S420, so we will not go into details about it.

[0350] As can be seen, the configuration information enables the network device to configure or instruct the terminal device on one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, so that the terminal device can determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions through the configuration information.

[0351] For one or more rollback trigger conditions in S610 or S710, one possible implementation is as follows:

[0352] The one or more rollback triggering conditions include at least one of the following: the performance information of the first CSI processing does not meet the preset requirements, the resource requirement information of the first CSI processing exceeds the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing. It should be understood that the one or more rollback triggering conditions in this embodiment are not limited to the above content, and may also include other rollback triggering conditions, which are not specifically limited.

[0353] It should be noted that for the explanation regarding the performance information of the first CSI process not meeting the preset requirements, please refer to the relevant description in the above "Performance Information of CSI Processing" for details in this embodiment, and will not be repeated here.

[0354] For example, the performance information of the first CSI process includes at least one of the following: the accuracy of the first CSI process, the processing time of the first CSI process, the memory usage rate of the first CSI process, the resource utilization rate of the first CSI process, the complexity of the first CSI process, the data distribution characteristics of the first CSI process, or the signal transmission performance information of the first CSI process. It should be understood that the performance information of the first CSI process in this embodiment is not limited to the above content and may include other performance information, which is not specifically limited thereto.

[0355] Regarding the explanation that the resource requirement information for the first CSI processing exceeds the capabilities of the terminal device, this embodiment can refer to the relevant description in the above-mentioned "Resource Requirement Information for CSI Processing", and will not be repeated here.

[0356] For example, the resource requirement information for the first CSI processing includes at least one of the following: computing power required for the first CSI processing, processing units required for the first CSI processing, memory required for the first CSI processing, storage units required for the first CSI processing, network bandwidth required for the first CSI processing, or power required for the first CSI processing. It should be understood that the resource requirement information for the first CSI processing in this embodiment is not limited to the above-mentioned content and may also include other resource requirement information, which is not specifically limited thereto.

[0357] For details regarding the lack of support for first CSI processing in the device status information of terminal devices, please refer to the relevant description in "Device Status Information of Terminal Devices" above. This embodiment will not repeat the details here.

[0358] For example, the device status information of a terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power. It should be understood that the device status information of the terminal device in this embodiment is not limited to the above content and may also include other device status information, without specific limitations.

[0359] In another possible example, after determining in S620 that the fallback method corresponding to the triggered fallback condition is the first fallback method, since the first fallback method is determined by the terminal device itself, the terminal device can feed back the first fallback method to the network device so that the network device can know the fallback method adopted by the terminal device. For example, as shown in Figure 8, which is a flowchart of another communication method according to an embodiment of this application, specifically including the following steps:

[0360] S810 is the same as S610, so it will not be described again.

[0361] S820 is the same as S620, so it will not be described again.

[0362] S830. The terminal device sends rollback mode feedback information, which is used to indicate the first rollback mode.

[0363] Correspondingly, the network device receives feedback information regarding the fallback method.

[0364] S840 is the same as S630, so it will not be described again.

[0365] It is worth noting the order of S830 and S840.

[0366] As can be seen, by feeding back information through the fallback method, the terminal device can report the first fallback method to the network device, so that the network device can know the fallback method adopted by the terminal device.

[0367] In one possible example, the fallback method feedback information is carried in the CSI report. In this way, the terminal device can use the CSI report to provide feedback on the first fallback method to the network device.

[0368] It should be noted that a CSI report can consist of two parts: Part 1 and Part 2. The payload size of Part 1 can be fixed. Part 1 is used to determine the number of information bits in Part 2, and the entire information in Part 1 that needs to be transmitted or decoded before Part 2.

[0369] Since the size of part 1 is fixed, while the size of part 2 is variable and depends on part 1, this embodiment can achieve the following: One approach is to place some important information in part 1, so that even if part 2 is discarded, the terminal device can still report important information to the network device through part 1 for relevant reference, thus avoiding the loss of important information; another approach is to place some information that determines the size of part 2 in part 1, so that the network device can use this information to retrieve part 2, thus avoiding blindly searching part 2 and improving retrieval efficiency; a third approach is to place some information with a small amount of data in part 1, and some information with a large amount of data in part 2, so that the network device can quickly retrieve part 1 because part 1 contains a small amount of information.

[0370] To implement the feedback of the first fallback method to network devices via CSI reports, since a CSI report can consist of Part 1 and Part 2, and Part 1 and Part 2 contain different content, the fallback method feedback information can be in either Part 1 or Part 2. When the fallback method feedback information is important information or determines the size of Part 2, it can be in Part 1, thus helping to avoid the loss of important information or blind detection of Part 2. When the size of the fallback method feedback information is not fixed or has high resource consumption, it can be in Part 2, thus helping to ensure the transmission of the fallback method feedback information.

[0371] For the rollback of the first CSI process according to the first rollback method in S420, S520, S630, or S840, one possible implementation is as follows:

[0372] The first CSI process can be rolled back to the second CSI process according to the first rollback method, or the first CSI process can be rolled back to not performing CSI process according to the first rollback method.

[0373] It is understandable that the first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process.

[0374] It should be noted that the second CSI process is a different CSI process from the first CSI process. The second CSI process can refer to other AI-based CSI processes besides the first CSI process, or it can refer to non-AI-based CSI processes.

[0375] In some possible examples, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0376] For example, the first CSI processing is AI-based CSI prediction and CSI compression, and the second CSI processing is AI-based CSI prediction, or AI-based CSI compression, or non-AI-based CSI prediction, or non-AI-based CSI compression, or non-AI-based CSI prediction and AI-based CSI compression, or non-AI-based CSI prediction and non-AI-based CSI compression, or CSI processing based on measurement resources no later than the CSI reference resources, or other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0377] For example, the first CSI processing is AI-based CSI prediction, and the second CSI processing is AI-based CSI compression, or non-AI-based CSI prediction, or non-AI-based CSI compression, or non-AI-based CSI prediction and AI-based CSI compression, or non-AI-based CSI prediction and non-AI-based CSI compression, or CSI processing based on measurement resources no later than the CSI reference resources, or other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0378] For example, the first CSI processing is AI-based CSI compression, and the second CSI processing is AI-based CSI prediction, or non-AI-based CSI prediction, or non-AI-based CSI compression, or non-AI-based CSI prediction and AI-based CSI compression, or non-AI-based CSI prediction and non-AI-based CSI compression, or CSI processing based on measurement resources no later than the CSI reference resources, or other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0379] Additionally, in one possible example, after rolling back the first CSI process to the second CSI process, the terminal device in this embodiment can determine whether it is necessary to continue rolling back the second CSI process. For example, as shown in FIG9, FIG9 is a flowchart illustrating another communication method according to an embodiment of this application, specifically including the following steps:

[0380] S910 is the same as S410.

[0381] S920. The terminal device rolls back the first CSI processing to the second CSI processing according to the first rollback method.

[0382] S930. The terminal device determines the first rollback trigger condition and the rollback method corresponding to the first rollback trigger condition.

[0383] Among them, the first rollback trigger condition is a rollback trigger condition.

[0384] S940. If the first rollback trigger condition is triggered, the terminal device rolls back the second CSI processing according to the rollback method corresponding to the first rollback trigger condition.

[0385] It is evident that if the first rollback trigger condition is triggered, it indicates that the second CSI process has flaws, cannot be executed successfully, or cannot achieve the expected results. In this case, the terminal device can continue to roll back the second CSI process according to the rollback method corresponding to the first rollback trigger condition, so that the second CSI process can return, restore, or be undone to a processable, executable, or predictable state.

[0386] For the first rollback trigger condition, one possible implementation is as follows: the first rollback trigger condition includes at least one of the following: the performance information of the second CSI processing does not meet the preset requirements, the resource requirement information of the second CSI processing exceeds the terminal device's capacity, or the device status information of the terminal device does not support the second CSI processing.

[0387] It should be noted that for explanations regarding the performance information of the second CSI processing not meeting the preset requirements, this embodiment can refer to the relevant description in the above-mentioned "Performance Information of CSI Processing," and will not be repeated here. For example, the performance information of the second CSI processing includes at least one of the following: the accuracy of the second CSI processing, the complexity of the second CSI processing, the processing time of the second CSI processing, the memory usage rate of the second CSI processing, the resource utilization rate of the second CSI processing, the data distribution characteristics of the second CSI processing, or the signal transmission performance information of the second CSI processing.

[0388] Regarding the explanation that the resource requirements for the second CSI processing exceed the capabilities of the terminal device, this embodiment can refer to the relevant description in the "Resource Requirements for CSI Processing" section above, and will not be repeated here. For example, the resource requirements for the second CSI processing include at least one of the following: computing power required for the second CSI processing, processing unit required for the second CSI processing, memory required for the second CSI processing, storage unit required for the second CSI processing, network bandwidth required for the second CSI processing, or power required for the second CSI processing.

[0389] Regarding the explanation that the terminal device's device status information does not support second CSI processing, this embodiment can be found in the relevant description in "Terminal Device Status Information" above, and will not be repeated here. For example, the terminal device's device status information includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

[0390] Regarding the determination of the first rollback trigger condition and the corresponding rollback method in S930, one possible implementation is: to enable the terminal device to use the first rollback trigger condition and the corresponding rollback method through network configuration or network indication, pre-configuration, pre-definition, standard protocol specification, or default specification.

[0391] Regarding the rollback of the second CSI processing in S940 based on the rollback method corresponding to the first rollback trigger condition, one possible implementation is as follows:

[0392] The second CSI process is rolled back to the third CSI process according to the rollback method corresponding to the first rollback trigger condition, or the second CSI process is rolled back to not executing CSI process.

[0393] The third CSI processing refers to AI-based CSI processing other than the first CSI processing and the second CSI processing, or the third CSI processing refers to non-AI-based CSI processing other than the first CSI processing and the second CSI processing.

[0394] It is understandable that the rollback method corresponding to the first rollback trigger condition is used to roll back the second CSI process to the third CSI process, or the rollback method corresponding to the first rollback trigger condition is used to roll back the second CSI process to not perform CSI process.

[0395] It should be noted that the third CSI process is a different CSI process from the second CSI process. Specifically, the third CSI process can refer to any AI-based CSI process other than the first and second CSI processes, or it can refer to any non-AI-based CSI process other than the first and second CSI processes.

[0396] In some possible examples, the third CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, or other AI-based CSI processing besides the second CSI processing, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, non-AI-based CSI processing, CSI processing based on measurement resources no later than the CSI reference resource, or non-AI-based CSI processing.

[0397] For example, the second CSI processing is AI-based CSI prediction, and the third CSI processing is AI-based CSI compression, or other AI-based CSI processing besides the second CSI processing, or CSI prediction based on non-AI, or CSI compression based on non-AI, or CSI prediction based on non-AI and CSI compression based on AI, or CSI prediction based on non-AI and CSI compression based on non-AI, or CSI processing based on measurement resources no later than the CSI reference resource, or CSI processing based on non-AI.

[0398] For example, the second CSI processing is AI-based CSI compression, and the third CSI processing is AI-based CSI prediction, or other AI-based CSI processing besides the second CSI processing, or CSI prediction based on non-AI, CSI compression based on non-AI, or CSI prediction based on non-AI and CSI compression based on AI, or CSI prediction based on non-AI and CSI compression based on non-AI, or CSI processing based on measurement resources no later than the CSI reference resources, or CSI processing based on non-AI.

[0399] For example, the second CSI processing is based on non-AI CSI prediction and CSI compression, and the third CSI processing is based on non-AI CSI prediction, or non-AI CSI compression, or other AI-based CSI processing besides the first CSI processing, or CSI processing based on measurement resources no later than the CSI reference resources, or non-AI-based CSI processing.

[0400] For example, the second CSI processing is based on non-AI CSI prediction, and the third CSI processing is based on non-AI CSI compression, or CSI processing based on measurement resources no later than the CSI reference resources, or other non-AI based CSI processing besides the second CSI processing.

[0401] For example, the second CSI processing is based on non-AI CSI compression, and the third CSI processing is based on non-AI CSI prediction, or CSI processing based on measurement resources no later than the CSI reference resources, or other AI-based CSI processing besides the second CSI processing.

[0402] In one possible example, after the first CSI process is rolled back according to the first rollback method in S420, S520, S630, or S840, the terminal device in this embodiment can report the completion of the rollback of the first CSI process to the network device so that the network device can know that the rollback of the first CSI process has been completed. For example, as shown in FIG10, FIG10 is a flowchart of another communication method according to an embodiment of this application, which specifically includes the following steps:

[0403] S1010 is the same as S410, so it will not be described again.

[0404] S1020 is the same as S420, so it will not be described again.

[0405] S1030. The terminal device sends result feedback information.

[0406] Correspondingly, the network device receives result feedback information. This result feedback information indicates at least one of the following: the rollback of the first CSI process is complete; the rollback method used to roll back the first CSI process; the type of CSI process after the rollback of the first CSI process; or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0407] Therefore, when the result feedback information indicates that the rollback of the first CSI process is complete, the network device can know that the rollback of the first CSI process is complete through the result feedback information. When the result feedback information indicates the rollback method used to roll back the first CSI process, the network device can know the rollback method used for the first CSI process through the result feedback information. When the result feedback information indicates the type of CSI process after the rollback of the first CSI process, the network device can know the type of CSI process after the rollback of the first CSI process through the result feedback information. When the result feedback information indicates the information obtained based on the type of CSI process after the rollback of the first CSI process, the network device can know the information obtained based on the type of CSI process after the rollback of the first CSI process through the result feedback information.

[0408] In one possible example, the result feedback information is carried by the CSI report. In this way, the terminal device can use the CSI report to provide feedback to the network device on the rollback execution result of the first CSI process.

[0409] It should be noted that since a CSI report can consist of Part 1 and Part 2, and Part 1 and Part 2 contain different content, the result feedback information can be in either Part 1 or Part 2. When the result feedback information is crucial or determines the size of Part 2, it can be in Part 1 to avoid losing important information or blindly checking Part 2. When the size of the result feedback information is variable or resource-intensive, it can be in Part 2 to ensure the transmission of the result feedback information.

[0410] [Activation or deactivation handled by CSI]

[0411] It should be noted that, regarding CSI processing, the network device in this embodiment can instruct or configure the terminal device to activate or deactivate CSI processing via higher-layer signaling (such as RRC signaling or MAC signaling), DCI, or system information. Thus, when CSI processing is activated, the terminal device can perform CSI processing. When CSI processing is deactivated, the terminal device cannot perform CSI processing.

[0412] In addition, activation can mean the same thing as enabling or availability, and deactivation can mean the same thing as disabling or unavailability.

[0413] The following embodiment uses the first CSI processing mentioned above as an example for illustration. For example, as shown in Figure 11, which is a flowchart of another communication method according to an embodiment of this application, it specifically includes the following steps:

[0414] S1110. The network device sends activation instruction information, which is used to indicate whether to activate or deactivate the first CSI process.

[0415] Correspondingly, the terminal device receives the activation instruction information.

[0416] As can be seen, by activating the instruction information, the network device configures or instructs the terminal device to activate or deactivate the first CSI process.

[0417] In another possible example, this embodiment enables the terminal device to determine one or more candidate CSI processes through network configuration or network indication, pre-configuration, pre-definition, standard protocol specifications, or default specifications. The network device then indicates one CSI process from these candidate processes as the first CSI process. Finally, the network device instructs or configures the terminal device to activate or deactivate the first CSI process.

[0418] For example, as shown in Figure 12, which is a flowchart of another communication method according to an embodiment of this application, the method specifically includes the following steps:

[0419] S1210. The network device sends CSI processing indication information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0420] Correspondingly, the terminal device receives CSI processing instruction information.

[0421] S1220 is the same as S1110, so it will not be described again.

[0422] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is configured or indicated by the network, the terminal device can execute the relevant CSI process according to the network-required CSI process. Then, the network device configures or instructs the terminal device to activate or deactivate the first CSI process through activation instruction information.

[0423] The following is an example description of a communication device according to this embodiment.

[0424] The above mainly describes the solution of the embodiments of this application from the perspective of the method. The functional units of a communication device according to this embodiment are illustrated below. It is understood that, in order to achieve the above functions, the terminal device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this embodiment can be implemented in hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this embodiment.

[0425] This application embodiment can divide the terminal device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software program module. It should be noted that the unit division in this application embodiment is illustrative and only represents a logical functional division, while other division methods may be used in actual implementation.

[0426] In the case of using integrated units, FIG13 is a functional unit block diagram of a communication device according to an embodiment of the present application. The communication device 1300 includes a determining unit 1301 and a back-up unit 1302.

[0427] Optionally, the determining unit 1301 can be a module unit for determining the rollback method of information, etc., and there is no specific limitation thereto. The determining unit 1301 may include a receiving unit, which is a module unit for receiving and processing information or signals, etc., and there is no specific limitation thereto.

[0428] Optionally, the rollback unit 1302 can be a module unit used for rollback processing of CSI processing, etc., and there are no specific limitations on this.

[0429] Optionally, the communication device 1300 may also include a transmitting unit. The transmitting unit can be a module unit used for transmitting signals, information, etc., and there are no specific limitations on this.

[0430] Optionally, the communication device 1300 may further include a storage unit for storing computer program code or instructions executed by the communication device 1300. The storage unit may be a memory.

[0431] Optionally, the communication device 1300 may be a chip or a chip module.

[0432] Optionally, the determining unit 1301 can be integrated into the communication unit. The communication unit can be a communication interface, transceiver, transceiver circuit, etc.

[0433] Optionally, the rollback unit 1302 can be integrated into the processing unit.

[0434] It should be noted that the processing unit can be a processor or controller, such as a baseband processor, baseband chip, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this embodiment. The processing unit can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0435] Optionally, the communication device 1300 is used to perform any of the steps performed by the terminal device, chip, or chip module as described in the above method embodiments.

[0436] In specific implementation, the determining unit 1301 and the backoff unit 1302 are used to execute any of the steps in the above method embodiments, and when performing actions such as sending or receiving, other units can be selectively called to complete the corresponding operation. A detailed description follows.

[0437] Determining unit 1301 is used to determine the first rollback method;

[0438] The rollback unit 1302 is used to roll back the first CSI process according to the first rollback method. The first CSI process refers to AI-based CSI processing.

[0439] It is evident that when AI technology is applied to CSI processing, it can bring both advantages, such as enabling intelligent CSI processing, improving air interface performance, or reducing air interface overhead, and disadvantages, such as the AI ​​inference process consuming significant computing power or a large discrepancy between the AI's inference results and the actual results. Therefore, this embodiment introduces a rollback mechanism for CSI processing.

[0440] Thus, in the rollback mechanism of CSI processing, when the first CSI processing (i.e., AI-based CSI processing) has drawbacks, fails to execute successfully, or fails to achieve the expected results, the terminal device can roll back the first CSI processing according to the first rollback method, so that the first CSI processing can return, restore or cancel to a processable, executable or predictable state.

[0441] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 13 can be found in the description of the method embodiment shown above, and will not be repeated here.

[0442] In some possible examples, in terms of rolling back the first CSI process according to the first rollback method, the rollback unit 1302 is used to:

[0443] The first CSI process can be rolled back to the second CSI process according to the first rollback method, or the first CSI process can be rolled back to not performing CSI process according to the first rollback method;

[0444] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0445] In some possible examples, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0446] In some possible examples, after the first CSI process is rolled back to the second CSI process according to the first rollback method, the rollback unit 1302 is further configured to:

[0447] Determine the first rollback trigger condition and the corresponding rollback method;

[0448] If the first rollback trigger condition is triggered, the second CSI process will be rolled back according to the rollback method corresponding to the first rollback trigger condition.

[0449] In some possible examples, the first rollback trigger condition includes at least one of the following:

[0450] The performance information of the second CSI processing does not meet the preset requirements, the resource requirements of the second CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the second CSI processing.

[0451] In some possible examples, the performance information of the second CSI processing includes at least one of the following: the accuracy of the second CSI processing, the processing time of the second CSI processing, the memory usage of the second CSI processing, the resource utilization of the second CSI processing, the complexity of the second CSI processing, the data distribution characteristics of the second CSI processing, or the signal transmission performance information of the second CSI processing; or,

[0452] The resource requirements for the second CSI processing include at least one of the following: computing power required for the second CSI processing, processing units required for the second CSI processing, memory required for the second CSI processing, storage units required for the second CSI processing, network bandwidth required for the second CSI processing, or power required for the second CSI processing; or,

[0453] The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

[0454] In some possible examples, in terms of rolling back the second CSI processing according to the rollback method corresponding to the first rollback trigger condition, the rollback unit 1302 is used to:

[0455] The second CSI process is rolled back to the third CSI process according to the rollback method corresponding to the first rollback trigger condition, or the second CSI process is rolled back to not executing CSI process.

[0456] The third CSI processing refers to AI-based CSI processing other than the first CSI processing and the second CSI processing, or the third CSI processing refers to non-AI-based CSI processing other than the first CSI processing and the second CSI processing.

[0457] In some possible examples, the third CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, or other AI-based CSI processing besides the second CSI processing, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, non-AI-based CSI processing, CSI processing based on measurement resources no later than the CSI reference resource, or non-AI-based CSI processing.

[0458] In some possible examples, in determining the first rollback method, the determining unit 1301 is used for:

[0459] Receive rollback mode indication information, which is used to indicate the first rollback mode.

[0460] In some possible examples, in determining the first rollback method, the determining unit 1301 is used for:

[0461] Determine one or more rollback trigger conditions and the rollback method corresponding to one or more rollback trigger conditions;

[0462] If one or more rollback trigger conditions are triggered, the rollback method corresponding to the triggered rollback trigger condition is determined to be the first rollback method.

[0463] In some possible examples, the determining unit 1301 is used to: determine one or more rollback trigger conditions and the rollback method corresponding to one or more rollback trigger conditions.

[0464] Receive configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to one or more rollback trigger conditions.

[0465] In some possible examples, one or more fallback trigger conditions include at least one of the following:

[0466] The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

[0467] In some possible examples, the performance information of the first CSI process includes at least one of the following: the accuracy of the first CSI process, the processing time of the first CSI process, the memory usage of the first CSI process, the resource utilization of the first CSI process, the complexity of the first CSI process, the data distribution characteristics of the first CSI process, or the signal transmission performance information of the first CSI process; or,

[0468] The resource requirements for the first CSI processing include at least one of the following: computing power required for the first CSI processing, processing units required for the first CSI processing, memory required for the first CSI processing, storage units required for the first CSI processing, network bandwidth required for the first CSI processing, or power required for the first CSI processing; or...

[0469] The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

[0470] In some possible examples, the communication device 1300 also includes a transmitting unit;

[0471] The sending unit is used to send rollback mode feedback information after determining that the rollback mode corresponding to the first rollback trigger condition is the first rollback mode. The rollback mode feedback information is used to indicate the first rollback mode.

[0472] In some possible examples, rollback feedback information is carried by the CSI report.

[0473] In some possible examples, the communication device 1300 also includes a transmitting unit;

[0474] The transmitting unit is configured to transmit result feedback information after backing down the first channel state information (CSI) processing according to the first back-down method. The result feedback information is used to indicate at least one of the following: the back-down of the first CSI processing is completed, the back-down method used to back down the first CSI processing, the type of CSI processing after the back-down of the first CSI processing, or information obtained based on the type of CSI processing after the back-down of the first CSI processing.

[0475] In some possible examples, the results feedback information is carried by the CSI report.

[0476] The following is an example description of another communication device in this embodiment.

[0477] The above mainly describes the solutions of the embodiments of this application from the perspective of the method. The following is an example illustration of the functional units of another communication device according to this embodiment. It is understood that, in order to achieve the above functions, the network device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this embodiment can be implemented in hardware or a combination of hardware and computer software. Whether a certain function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this embodiment.

[0478] This application embodiment can divide the network device into functional units according to the above method example. For example, each function can be divided into different functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software program module. It should be noted that the unit division in this application embodiment is illustrative and only represents a logical functional division, while other division methods may be used in actual implementation.

[0479] In the case of using integrated units, FIG14 is a functional unit block diagram of another communication device according to an embodiment of the present application. The communication device 1400 includes a transmitting unit 1401.

[0480] Optionally, the transmitting unit 1401 can be a module unit used for transmitting signals, information, etc., and there are no specific limitations on this.

[0481] Optionally, the communication device 1400 may also include a receiving unit. The receiving unit can be a module unit for receiving and processing signals, information, etc., and there are no specific limitations on this.

[0482] Optionally, the communication device 1400 may further include a storage unit for storing computer program code or instructions executed by the communication device 1400. The storage unit may be a memory.

[0483] Optionally, the communication device 1400 may be a chip or a chip module.

[0484] Optionally, the transmitting unit 1401 can be integrated into the communication unit. The communication unit can be a communication interface, transceiver, transceiver circuit, etc.

[0485] Optionally, the communication device 1400 may also include a processing unit.

[0486] It should be noted that the processing unit can be a processor or controller, such as a baseband processor, baseband chip, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this embodiment. The processing unit can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0487] Optionally, the communication device 1400 is used to perform any of the steps performed by a chip, chip module, or network device as described in the above method embodiments.

[0488] In specific implementation, the sending unit 1401 is used to perform any of the steps in the above method embodiments, and when performing actions such as sending, it can selectively call other units to complete the corresponding operations. A detailed description follows.

[0489] In some possible examples, the sending unit 1401 is used for:

[0490] Send rollback method indication information. The rollback method indication information is used to indicate the first rollback method. The first rollback method is used to roll back the first CSI process. The first CSI process refers to AI-based CSI process.

[0491] As can be seen, the fallback method indication information enables the network device to configure or indicate the first fallback method to the terminal device, so that the terminal device can determine the first fallback method through the fallback method indication information. Since the first fallback method is configured or indicated by the network, the terminal device can fall back the first CSI processing according to the network requirements.

[0492] Optionally, the first rollback method is used to roll back the first CSI process, including:

[0493] The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process;

[0494] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0495] Optionally, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0496] Optionally, the communication device 1400 may also include a receiving unit;

[0497] The receiving unit is configured to receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0498] Optionally, the results feedback information is carried in the CSI report.

[0499] In some possible examples, the sending unit 1401 is used for:

[0500] Send configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; wherein, the rollback method corresponding to one of the one or more rollback trigger conditions is the first rollback method, which is used to roll back the first CSI process, and the first CSI process refers to the AI-based CSI process.

[0501] As can be seen, the configuration information enables the network device to configure or instruct the terminal device on one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, so that the terminal device can determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions through the configuration information.

[0502] Optionally, one or more rollback trigger conditions include at least one of the following:

[0503] The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

[0504] Optionally, the performance information processed by the first CSI may include at least one of the following:

[0505] The accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing.

[0506] Optionally, the communication device 1400 may also include a receiving unit;

[0507] The receiving unit is used to receive fallback mode feedback information after sending configuration information. The fallback mode feedback information is used to indicate the first fallback mode.

[0508] Optionally, rollback feedback information is carried in the CSI report.

[0509] Optionally, the first rollback method is used to roll back the first CSI process, including:

[0510] The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process;

[0511] The second CSI processing refers to any AI-based CSI processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

[0512] Optionally, the second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

[0513] Optionally, the communication device 1400 may also include a receiving unit;

[0514] The receiving unit is configured to receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

[0515] Optionally, the results feedback information is carried in the CSI report.

[0516] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 14 can be found in the description of the method embodiment shown above, and will not be repeated here.

[0517] The following is an example description of another communication device in this embodiment.

[0518] In the case of using integrated units, FIG15 is a functional unit composition block diagram of a communication device according to an embodiment of the present application. The communication device 1500 includes a receiving unit 1501.

[0519] Optionally, the receiving unit 1501 is a module unit for receiving and processing information or signals, etc., and there are no specific limitations on it.

[0520] Optionally, the communication device 1500 may also include a transmitting unit. The transmitting unit can be a module unit for transmitting signals, information, etc., and there are no specific limitations on this.

[0521] Optionally, the communication device 1500 may further include a storage unit for storing computer program code or instructions executed by the communication device 1500. The storage unit may be a memory.

[0522] Optionally, the communication device 1500 may be a chip or a chip module.

[0523] Optionally, the receiving unit 1501 can be integrated into the communication unit. The communication unit can be a communication interface, transceiver, transceiver circuit, etc.

[0524] Optionally, the receiving unit 1501 can be integrated into the processing unit.

[0525] It should be noted that the processing unit can be a processor or controller, such as a baseband processor, baseband chip, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this embodiment. The processing unit can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0526] Optionally, the communication device 1500 is used to perform any of the steps performed by the terminal device, chip, or chip module as described in the above method embodiments.

[0527] In specific implementation, the receiving unit 1501 is used to perform any of the steps in the above method embodiments, and when performing actions such as sending, it can selectively call other units to complete the corresponding operations. A detailed description follows.

[0528] Receiving unit 1501 is configured to receive CSI processing indication information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0529] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0530] In some possible examples, the receiving unit 1501 is also configured to: receive CSI processing indication information before receiving CSI processing indication information, the CSI processing indication information being used to indicate a first CSI processing from one or more candidate CSI processing.

[0531] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 15 can be found in the description of the method embodiment shown above, and will not be repeated here.

[0532] The following is an example description of another communication device in this embodiment.

[0533] In the case of using integrated units, FIG16 is a functional unit block diagram of another communication device according to an embodiment of the present application. The communication device 1600 includes a transmitting unit 1601.

[0534] Optionally, the transmitting unit 1601 can be a module unit used for transmitting signals, information, etc., and there are no specific limitations on this.

[0535] Optionally, the communication device 1600 may also include a receiving unit. The receiving unit can be a module unit for receiving and processing signals, information, etc., and there are no specific limitations on this.

[0536] Optionally, the communication device 1600 may further include a storage unit for storing computer program code or instructions executed by the communication device 1600. The storage unit may be a memory.

[0537] Optionally, the communication device 1600 may be a chip or a chip module.

[0538] Optionally, the transmitting unit 1601 can be integrated into the communication unit. The communication unit can be a communication interface, transceiver, transceiver circuit, etc.

[0539] Optionally, the communication device 1600 may also include a processing unit.

[0540] It should be noted that the processing unit can be a processor or controller, such as a baseband processor, baseband chip, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this embodiment. The processing unit can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0541] Optionally, the communication device 1600 is used to perform any of the steps performed by a chip, chip module, or network device as described in the above method embodiments.

[0542] In specific implementation, the sending unit 1601 is used to perform any of the steps in the above method embodiments, and when performing actions such as sending, it can selectively call other units to complete the corresponding operations. A detailed description follows.

[0543] The sending unit 1601 is configured to send CSI processing indication information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0544] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0545] In some possible examples, the sending unit 1601 is also configured to send CSI processing indication information before sending CSI processing indication information, the CSI processing indication information being used to indicate a first CSI processing from one or more candidate CSI processing.

[0546] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 16 can be found in the description of the method embodiment shown above, and will not be repeated here.

[0547] The structure of a terminal device in this embodiment is illustrated below.

[0548] Please refer to Figure 17, which is a schematic diagram of the structure of a terminal device according to an embodiment of this application. The terminal device 1700 may include a processor 1710, a memory 1720, and a communication bus for connecting the processor 1710 and the memory 1720.

[0549] Optionally, the memory 1720 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM). The memory 1720 is used to store the program code executed by the terminal device 1700 and the data channel transmitted.

[0550] Optionally, the terminal device 1700 also includes a communication interface for receiving and transmitting data channels.

[0551] Optionally, the terminal device 1700 can be the first terminal device mentioned above.

[0552] Optionally, the processor 1710 can be one or more CPUs. If the processor 1710 is a CPU, the CPU can be a single-core CPU or a multi-core CPU.

[0553] Optionally, the processor 1710 can be a baseband chip, a chip, a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0554] In some possible examples, the processor 1710 in the terminal device 1700 is used to execute the computer program or instructions 1721 stored in the memory 1720 to perform the following operations:

[0555] Determine the first rollback method;

[0556] The first CSI process is rolled back according to the first rollback method. The first CSI process refers to AI-based CSI process.

[0557] It is evident that when AI technology is applied to CSI processing, it can bring both advantages, such as enabling intelligent CSI processing, improving air interface performance, or reducing air interface overhead, and disadvantages, such as the AI ​​inference process consuming significant computing power or a large discrepancy between the AI's inference results and the actual results. Therefore, this embodiment introduces a rollback mechanism for CSI processing.

[0558] Thus, in the rollback mechanism of CSI processing, when the first CSI processing has problems such as drawbacks, failure to execute successfully, or failure to achieve the expected results, the terminal device can roll back the first CSI processing according to the first rollback method, so that the first CSI processing can return, restore or cancel to a processable, executable or predictable state.

[0559] In some possible examples, the processor 1710 in the terminal device 1700 is used to execute the computer program or instructions 1721 stored in the memory 1720 to perform the following operations:

[0560] Receive CSI processing instruction information, which is used to indicate a first CSI process from one or more candidate CSI processes.

[0561] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0562] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above. The terminal device 1700 can be used to execute the method embodiment described above in this embodiment, and will not be described again here.

[0563] The structure of a network device according to this embodiment is illustrated below.

[0564] Please refer to Figure 18, which is a schematic diagram of the structure of a network device according to an embodiment of this application. The network device 1800 includes a processor 1810, a memory 1820, and a communication bus for connecting the processor 1810 and the memory 1820.

[0565] Optionally, the memory 1820 may include, but is not limited to, RAM, ROM, EPROM or CD-ROM, and the memory 1820 may be used to store related instructions and data channels.

[0566] Optionally, the network device 1800 also includes a communication interface for receiving and transmitting data channels.

[0567] Optionally, the processor 1810 can be one or more CPUs. If the processor 1810 is a CPU, the CPU can be a single-core CPU or a multi-core CPU.

[0568] Optionally, the processor 1810 can be a baseband chip, a chip, a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0569] In some possible examples, the processor 1810 in network device 1800 is used to execute a computer program or instruction 1821 stored in memory 1820 to perform the following operations:

[0570] Send rollback method indication information. The rollback method indication information is used to indicate the first rollback method. The first rollback method is used to roll back the first CSI process. The first CSI process refers to AI-based CSI process.

[0571] As can be seen, the fallback method indication information enables the network device to configure or indicate the first fallback method to the terminal device, so that the terminal device can determine the first fallback method through the fallback method indication information. Since the first fallback method is configured or indicated by the network, the terminal device can fall back the first CSI processing according to the network requirements.

[0572] In some possible examples, the processor 1810 in network device 1800 is used to execute a computer program or instruction 1821 stored in memory 1820 to perform the following operations:

[0573] Send configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; wherein, the rollback method corresponding to one of the one or more rollback trigger conditions is the first rollback method, which is used to roll back the first CSI process, and the first CSI process refers to the AI-based CSI process.

[0574] As can be seen, the configuration information enables the network device to configure or instruct the terminal device on one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, so that the terminal device can determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions through the configuration information.

[0575] In some possible examples, the processor 1810 in network device 1800 is used to execute a computer program or instruction 1821 stored in memory 1820 to perform the following operations:

[0576] Send CSI processing indication information, which is used to indicate the first CSI process from one or more candidate CSI processes.

[0577] As can be seen, the network device designates one CSI process from one or more candidate CSI processes as the first CSI process through CSI processing instruction information. Since the first CSI process is network configured or network-instructed, the terminal device can execute the relevant CSI process according to the network-required CSI process.

[0578] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above. The network device 1800 can be used to execute the method embodiment described above in this embodiment, and will not be described again here.

[0579] The following provides examples illustrating other relevant aspects of this embodiment.

[0580] Optionally, the above method embodiments can be applied to terminal devices or applied within terminal devices. That is, the executing entity of the above method embodiments can be a terminal device, a chip, a chip module, or a module, etc., without specific limitations.

[0581] Optionally, the above method embodiments can be applied to network devices or applied within network devices. That is, the executing entity of the above method embodiments can be a network device, a chip, a chip module, or a module, etc., without specific limitations.

[0582] This application also provides a chip, including a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps described in the above method embodiments.

[0583] This application also provides a chip module, including a transceiver component and a chip. The chip includes a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps described in the above method embodiments.

[0584] This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement the steps described in the above method embodiments.

[0585] This application also provides a computer program product, including a computer program or instructions that, when executed, implement the steps described in the above method embodiments.

[0586] This application also provides a communication system, including the terminal device and the network device described above.

[0587] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0588] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0589] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0590] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0591] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on a processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented using a software program that runs on a processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0592] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A communication method, characterized in that, include: Determine the first rollback method; The first channel state information (CSI) processing is rolled back according to the first rollback method. The first CSI processing refers to CSI processing based on artificial intelligence (AI).

2. The method according to claim 1, characterized in that, The step of rolling back the first CSI processing according to the first rollback method includes: The first CSI process is rolled back to the second CSI process according to the first rollback method, or the first CSI process is rolled back to not performing CSI process according to the first rollback method; The second CSI processing refers to other AI-based CSI processing besides the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

3. The method according to claim 2, characterized in that, After the first CSI process is rolled back to the second CSI process according to the first rollback method, the method further includes: Determine the first rollback trigger condition and the rollback method corresponding to the first rollback trigger condition; If the first rollback trigger condition is triggered, the second CSI processing is rolled back according to the rollback method corresponding to the first rollback trigger condition.

4. The method according to claim 3, characterized in that, The first rollback trigger condition includes at least one of the following: The performance information of the second CSI processing does not meet the preset requirements, the resource requirements of the second CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the second CSI processing.

5. The method according to claim 4, characterized in that, The performance information of the second CSI processing includes at least one of the following: the accuracy of the second CSI processing, the processing time of the second CSI processing, the memory usage rate of the second CSI processing, the resource utilization rate of the second CSI processing, the complexity of the second CSI processing, the data distribution characteristics of the second CSI processing, or the signal transmission performance information of the second CSI processing; or, The resource requirements for the second CSI processing include at least one of the following: computing power required for the second CSI processing, processing units required for the second CSI processing, memory required for the second CSI processing, storage units required for the second CSI processing, network bandwidth required for the second CSI processing, or power required for the second CSI processing; or, The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

6. The method according to claim 3, characterized in that, The step of rolling back the second CSI processing according to the rollback method corresponding to the first rollback trigger condition includes: The second CSI process is rolled back to the third CSI process according to the rollback method corresponding to the first rollback trigger condition, or the second CSI process is rolled back to not performing CSI process. The third CSI process refers to an AI-based CSI process other than the first CSI process and the second CSI process, or the third CSI process refers to a non-AI-based CSI process other than the first CSI process and the second CSI process.

7. The method according to any one of claims 1-6, characterized in that, The determination of the first rollback method includes: Receive rollback mode indication information, which is used to indicate the first rollback mode.

8. The method according to any one of claims 1-6, characterized in that, The determination of the first rollback method includes: Determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; If one or more rollback trigger conditions are triggered, the rollback method corresponding to the triggered rollback trigger condition is determined to be the first rollback method.

9. The method according to claim 8, characterized in that, The determination of one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions includes: Receive configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions.

10. The method according to claim 8 or 9, characterized in that, The one or more rollback trigger conditions include at least one of the following: The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

11. The method according to claim 10, characterized in that, The performance information of the first CSI processing includes at least one of the following: the accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing; or, The resource requirements for the first CSI processing include at least one of the following: computing power required for the first CSI processing, processing units required for the first CSI processing, memory required for the first CSI processing, storage units required for the first CSI processing, network bandwidth required for the first CSI processing, or power required for the first CSI processing; or, The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

12. The method according to any one of claims 8-11, characterized in that, After determining that the rollback method corresponding to the first rollback trigger condition is the first rollback method, the method further includes: Send rollback method feedback information, which is used to indicate the first rollback method.

13. The method according to claim 12, characterized in that, The rollback method feedback information is carried in the CSI report.

14. The method according to any one of claims 1-13, characterized in that, After the first channel state information (CSI) processing is rolled back according to the first rollback method, the method further includes: Send result feedback information, which is used to indicate at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

15. The method according to claim 14, characterized in that, The feedback information is carried in the CSI report.

16. A communication method, characterized in that, include: Send back-off mode indication information, the back-off mode indication information is used to indicate a first back-off mode, the first back-off mode is used to back off the first channel state information (CSI) processing, the first CSI processing refers to CSI processing based on artificial intelligence (AI).

17. The method according to claim 16, characterized in that, The first rollback method is used to roll back the first CSI process, including: The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process; The second CSI processing refers to other AI-based CSI processing besides the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

18. The method according to claim 17, characterized in that, The second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

19. The method according to claim 16, characterized in that, Also includes: Receive result feedback information, which is used to indicate at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

20. The method according to claim 19, characterized in that, The feedback information is carried in the CSI report.

21. A communication method, characterized in that, include: Send configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; Wherein, the fallback method corresponding to one of the fallback triggering conditions is the first fallback method, the first fallback method is used to fall back the first channel state information (CSI) processing, and the first CSI processing refers to CSI processing based on artificial intelligence (AI).

22. The method according to claim 21, characterized in that, The one or more rollback trigger conditions include at least one of the following: The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

23. The method according to claim 22, characterized in that, The performance information of the first CSI process includes at least one of the following: The accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing.

24. The method according to any one of claims 21-23, characterized in that, Following the sending of configuration information, the following is also included: Receive rollback method feedback information, which is used to indicate the first rollback method.

25. The method according to any one of claims 21-24, characterized in that, The first rollback method is used to roll back the first CSI process, including: The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process; The second CSI processing refers to AI-based processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

26. The method according to any one of claims 21-25, characterized in that, Also includes: Receive result feedback information, which is used to indicate at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

27. A communication method, characterized in that, include: Receive activation indication information, which is used to indicate the activation or deactivation of the first channel state information (CSI) processing, wherein the first CSI processing refers to CSI processing based on artificial intelligence (AI).

28. The method according to claim 27, characterized in that, Before receiving the activation indication information, the following is also included: Receive CSI processing indication information, which is used to indicate the first CSI process from one or more candidate CSI processes.

29. A communication method, characterized in that, include: Send activation indication information, which is used to indicate whether to activate or deactivate the first channel state information (CSI) processing, wherein the first CSI processing refers to CSI processing based on artificial intelligence (AI).

30. The method according to claim 29, characterized in that, Before sending the activation indication information, the following is also included: Send CSI processing indication information, which is used to indicate the first CSI process from one or more candidate CSI processes.

31. A communication device, characterized in that, include: The determining unit is used to determine the first rollback method; The rollback unit is used to roll back the first channel state information (CSI) processing according to the first rollback method, wherein the first CSI processing refers to CSI processing based on artificial intelligence (AI).

32. The apparatus according to claim 31, characterized in that, In the aspect of rolling back the first CSI process according to the first rollback method, the rollback unit is configured to: The first CSI process is rolled back to the second CSI process according to the first rollback method, or the first CSI process is rolled back to not performing CSI process according to the first rollback method; The second CSI processing refers to other AI-based CSI processing besides the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

33. The apparatus according to claim 32, characterized in that, The rollback unit is also used for: Determine the first rollback trigger condition and the rollback method corresponding to the first rollback trigger condition; If the first rollback trigger condition is triggered, the second CSI processing is rolled back according to the rollback method corresponding to the first rollback trigger condition.

34. The apparatus according to claim 33, characterized in that, The first rollback trigger condition includes at least one of the following: The performance information of the second CSI processing does not meet the preset requirements, the resource requirements of the second CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the second CSI processing.

35. The apparatus according to claim 34, characterized in that, The performance information of the second CSI processing includes at least one of the following: the accuracy of the second CSI processing, the processing time of the second CSI processing, the memory usage rate of the second CSI processing, the resource utilization rate of the second CSI processing, the complexity of the second CSI processing, the data distribution characteristics of the second CSI processing, or the signal transmission performance information of the second CSI processing; or, The resource requirements for the second CSI processing include at least one of the following: computing power required for the second CSI processing, processing units required for the second CSI processing, memory required for the second CSI processing, storage units required for the second CSI processing, network bandwidth required for the second CSI processing, or power required for the second CSI processing; or, The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

36. The apparatus according to claim 33, characterized in that, In the aspect of rolling back the second CSI processing according to the rollback method corresponding to the first rollback trigger condition, the rollback unit is used to: The second CSI process is rolled back to the third CSI process according to the rollback method corresponding to the first rollback trigger condition, or the second CSI process is rolled back to not performing CSI process. The third CSI process refers to an AI-based CSI process other than the first CSI process and the second CSI process, or the third CSI process refers to a non-AI-based CSI process other than the first CSI process and the second CSI process.

37. The apparatus according to any one of claims 31-36, characterized in that, In determining the first rollback method, the determining unit is used to: Receive rollback mode indication information, which is used to indicate the first rollback mode.

38. The apparatus according to any one of claims 31-36, characterized in that, In determining the first rollback method, the determining unit is used to: Determine one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; If one or more rollback trigger conditions are triggered, the rollback method corresponding to the triggered rollback trigger condition is determined to be the first rollback method.

39. The apparatus according to claim 38, characterized in that, In determining one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions, the determining unit is configured to: Receive configuration information, which is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions.

40. The apparatus according to claim 38 or 39, characterized in that, The one or more rollback trigger conditions include at least one of the following: The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

41. The apparatus according to claim 40, characterized in that, The performance information of the first CSI processing includes at least one of the following: the accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing; or, The resource requirements for the first CSI processing include at least one of the following: computing power required for the first CSI processing, processing units required for the first CSI processing, memory required for the first CSI processing, storage units required for the first CSI processing, network bandwidth required for the first CSI processing, or power required for the first CSI processing; or, The device status information of the terminal device includes at least one of the following: the terminal device is in motion, the terminal device's moving speed is within a preset range, or the terminal device's remaining battery power.

42. The apparatus according to any one of claims 38-41, characterized in that, The communication device further includes a transmitting unit; The sending unit is used to send rollback mode feedback information, which is used to indicate the first rollback mode.

43. The apparatus according to claim 38, characterized in that, The rollback method feedback information is carried in the CSI report.

44. The apparatus according to any one of claims 31-43, characterized in that, The communication device further includes a transmitting unit; The sending unit is used to send result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

45. The apparatus according to claim 44, characterized in that, The feedback information is carried in the CSI report.

46. ​​A communication device, characterized in that, include: The transmitting unit is used to transmit fallback mode indication information, which is used to indicate a first fallback mode. The first fallback mode is used to fall back the first channel state information (CSI) processing. The first CSI processing refers to CSI processing based on artificial intelligence (AI).

47. The apparatus according to claim 46, characterized in that, The first rollback method is used to roll back the first CSI process, including: The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process; The second CSI processing refers to other AI-based CSI processing besides the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

48. The apparatus according to claim 47, characterized in that, The second CSI processing includes at least one of the following: AI-based CSI prediction, AI-based CSI compression, non-AI-based CSI prediction, non-AI-based CSI compression, non-AI-based CSI prediction and AI-based CSI compression, non-AI-based CSI prediction and non-AI-based CSI compression, CSI processing based on measurement resources no later than the CSI reference resource, other AI-based CSI processing besides the first CSI processing, or non-AI-based CSI processing.

49. The apparatus according to claim 46, characterized in that, The communication device further includes a receiving unit; The receiving unit is configured to receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

50. The apparatus according to claim 49, characterized in that, The feedback information is carried in the CSI report.

51. A communication device, characterized in that, include: A sending unit is used to send configuration information, wherein the configuration information is used to configure one or more rollback trigger conditions and the rollback method corresponding to the one or more rollback trigger conditions; Wherein, the fallback method corresponding to one of the fallback triggering conditions is the first fallback method, the first fallback method is used to fall back the first channel state information (CSI) processing, and the first CSI processing refers to CSI processing based on artificial intelligence (AI).

52. The apparatus according to claim 51, characterized in that, The one or more rollback trigger conditions include at least one of the following: The performance information of the first CSI processing does not meet the preset requirements, the resource requirements of the first CSI processing exceed the capabilities of the terminal device, or the device status information of the terminal device does not support the first CSI processing.

53. The apparatus according to claim 52, characterized in that, The performance information of the first CSI process includes at least one of the following: The accuracy of the first CSI processing, the processing time of the first CSI processing, the memory usage rate of the first CSI processing, the resource utilization rate of the first CSI processing, the complexity of the first CSI processing, the data distribution characteristics of the first CSI processing, or the signal transmission performance information of the first CSI processing.

54. The apparatus according to any one of claims 51-53, characterized in that, Following the sending of configuration information, the following is also included: Receive rollback method feedback information, which is used to indicate the first rollback method.

55. The apparatus according to any one of claims 50-54, characterized in that, The first rollback method is used to roll back the first CSI process, including: The first rollback method is used to roll back the first CSI process to the second CSI process, or the first rollback method is used to roll back the first CSI process to not perform CSI process; The second CSI processing refers to AI-based processing other than the first CSI processing, or the second CSI processing refers to non-AI-based CSI processing.

56. The apparatus according to any one of claims 51-55, characterized in that, The communication device also includes a receiving unit; The receiving unit is configured to receive result feedback information, which indicates at least one of the following: the rollback of the first CSI process is completed, the rollback method used to roll back the first CSI process, the type of CSI process after the rollback of the first CSI process, or information obtained based on the type of CSI process after the rollback of the first CSI process.

57. A communication device, characterized in that, include: The receiving unit is used to receive activation indication information, which is used to indicate the activation or deactivation of the first channel state information (CSI) processing, wherein the first CSI processing refers to CSI processing based on artificial intelligence (AI).

58. The apparatus according to claim 57, characterized in that, The receiving unit is also used for: Receive CSI processing indication information, which is used to indicate the first CSI process from one or more candidate CSI processes.

59. A communication device, characterized in that, include: The transmitting unit is used to transmit activation indication information, which is used to indicate the activation or deactivation of the first channel state information (CSI) processing, wherein the first CSI processing refers to CSI processing based on artificial intelligence (AI).

60. The apparatus according to claim 59, characterized in that, The transmitting unit is further configured to: Send CSI processing indication information, which is used to indicate the first CSI process from one or more candidate CSI processes.

61. A terminal device, comprising a processor, a memory, and a computer program or instructions stored in the memory, characterized in that, The processor executes the computer program or instructions to implement the steps of the method according to any one of claims 1-15, 27 or 28.

62. A network device, comprising a processor, a memory, and a computer program or instructions stored in the memory, characterized in that, The processor executes the computer program or instructions to implement the steps of the method according to any one of claims 16-20, 21-26, 29 or 30.

63. A chip, comprising a processor and a communication interface, characterized in that, The processor performs the steps of the method according to any one of claims 1-30 through the communication interface.

64. A computer-readable storage medium, characterized in that, It stores a computer program or instructions that, when executed, implement the steps of the method as described in any one of claims 1-30.

Images