Information reporting method and apparatus used in node for wireless communication

Abstract

Disclosed in the present application are an information reporting method and apparatus used in a node for wireless communication. The method comprises: a first node receiving a first information set, wherein the first information set indicates a first configuration, and the first configuration is used for configuring first information reporting; the first information reporting depends on an output of a first operation, or the first information reporting is generated by means of falling back to a non-AI generation mode; the first configuration indicates the first operation, and the first operation is AI-based; and whether the first information reporting supports falling back to a non-AI generation mode depends on whether an input of the first operation depends on an output of another AI-based operation. The method and apparatus support AI-based information reporting, and are capable of determining whether information reporting supports falling back to a non-AI generation mode, thereby improving the accuracy of information reporting, and improving the flexibility, robustness, and overall performance of a system.

Description

A method and apparatus for information reporting in nodes used in wireless communication

[0001] This application claims priority to Chinese Patent Application No. 202411001636.8, filed on July 24, 2024, entitled "A Method and Apparatus for Information Reporting in a Node Used in Wireless Communication", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to schemes and apparatus for information reporting in wireless communication systems. Background Technology

[0003] In traditional wireless communication, the UE (User Equipment) reports various auxiliary information obtained through measurements of downlink signals and / or channels, such as channel information, beam management-related auxiliary information, and positioning-related auxiliary information. Channel information includes, but is not limited to, one or more of CRI (CSI-RS Resource Indicator), RI (Rank Indicator), PMI (Precoding Matrix Indicator), CQI (Channel Quality Indicator), or beam indicators. The UE can use this information to select appropriate transmission parameters or report this information. The network equipment selects appropriate transmission parameters for the UE based on the reported information, such as the cell to be used, MCS (Modulation and Coding Scheme), TPMI (Transmitted Precoding Matrix Indicator), and TCI (Transmission Configuration Indication). Furthermore, UE reporting can be used to optimize network parameters, such as improving cell coverage and switching base stations on / off based on the UE's location.

[0004] With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the increasing demands on system performance, traditional measurement and reporting methods incur significant redundancy overhead. Therefore, in NR (New Radio) Rel-18 (Release-18), research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and design. Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. Furthermore, AI / ML is also a key candidate technology for future 6G communications. Summary of the Invention

[0005] The applicant's research revealed that when AI / ML functions are introduced, existing measurement mechanisms, reporting mechanisms, and related configuration signaling may not be able to meet the needs of AI / ML. To address this issue, this application discloses a solution. It should be noted that while the NR system is used as an example in the above description, this application is also applicable to scenarios such as future 6G systems, achieving similar technical effects. Furthermore, although this application is initially intended for AI / ML scenarios, it can also be applied to other non-AI / ML scenarios, such as traditional CSI (Channel State Information) reporting schemes. Moreover, adopting a unified design scheme for different scenarios (such as other non-AI / ML scenarios, including but not limited to Vehicle to Everything (V2X), capacity enhancement systems, short-range communication systems, NTN (Non-Terrestrial Network), IoT (Internet of Things), and URLLC (Ultra-Reliable Low Latency Communication) networks) also helps reduce hardware complexity and cost. Unless otherwise specified, embodiments and features in any node of this application can be applied to any other node. Unless otherwise specified, embodiments and features in any node of this application can be arbitrarily combined with each other.

[0006] In particular, the interpretation of terms, nouns, functions, and variables in this application (unless otherwise specified) can be found in the definitions of the 3GPP specification protocols TS28, TS36, TS38, and TS37 series. Where necessary, 3GPP standards TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.321, TS38.331, TS38.305, TS38.304, and TS37.355 can be consulted to aid in understanding this application.

[0007] This application discloses a method used in a first node of wireless communication, characterized by comprising:

[0008] Receive a first set of information; the first set of information indicates a first configuration, the first configuration being used to configure the first information reporting; the first information reporting depends on the output of a first operation, or the first information reporting is generated by a fallback to a non-AI generation method;

[0009] Wherein, the first configuration indicates the first operation, and the first operation is based on AI; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0010] According to one aspect of this application, the first node is a user equipment.

[0011] According to one aspect of this application, the first node is a terminal.

[0012] According to one aspect of this application, the first node is a relay node.

[0013] As one example, the user equipment is a terminal.

[0014] As an example, the AI ​​(Artificial Intelligence) includes ML (Machine Learning).

[0015] As an example, the first node deploys the first operation.

[0016] As an example, the first operation is obtained by loading.

[0017] As an example, the problem this application aims to solve includes: how to determine whether information reporting supports reverting to a non-AI generation method.

[0018] As an example, the essence of the above method includes: whether information reporting supports reverting to a non-AI generation method depends on whether the AI ​​operation used to obtain the information reporting depends on other AI operations.

[0019] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0020] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0021] As an example, the advantages of the above method include: supporting the fallback to non-AI generated information reporting methods when supporting AI-based information reporting.

[0022] As an example, the advantages of the above method include: supporting processing based on multiple operations and improving the robustness of the system.

[0023] As an example, the advantages of the above method include: improving the accuracy of information reporting and reducing system overhead.

[0024] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0025] As an example, the advantages of the above method include: enhancing the flexibility of the system and better adapting to different transmission conditions and application scenarios.

[0026] As an example, the benefits of the above method include: improving the overall performance of the system.

[0027] According to one aspect of this application, the first information reporting is characterized by defaulting to whether it supports falling back to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation.

[0028] As an example, the essence of the above method includes: using a default approach to determine whether information reporting supports reverting to a non-AI generation method.

[0029] According to one aspect of this application, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0030] As an example, the essence of the above method includes: using higher-level signaling indications to determine whether information reporting supports falling back to a non-AI generation method.

[0031] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0032] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0033] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0034] As an example, the advantages of the above method include: enhanced system flexibility.

[0035] According to one aspect of this application, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is by default.

[0036] As an example, the essence of the above method includes: using a default approach to determine whether information reporting supports reverting to a non-AI generation method.

[0037] According to one aspect of this application, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0038] As an example, the essence of the above method includes: using higher-level signaling indications to determine whether information reporting supports falling back to a non-AI generation method.

[0039] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0040] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0041] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0042] As an example, the advantages of the above method include: enhanced system flexibility.

[0043] According to one aspect of this application, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0044] As an example, the essence of the above method includes: using higher-level signaling indications to determine whether information reporting supports falling back to a non-AI generation method.

[0045] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0046] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0047] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0048] According to one aspect of this application, the first information reporting does not support a fallback to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; and the first information reporting supports a fallback to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0049] As an example, the essence of the above method includes: information reporting that relies on a single AI operation does not support reverting to a non-AI generation method.

[0050] As an example, the essence of the above method includes: supporting the fallback of information reporting that relies on multiple AI operations to a non-AI generation method.

[0051] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0052] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0053] As an example, the advantages of the above method include: supporting information reporting based on both AI and non-AI generation methods.

[0054] According to one aspect of this application, it is characterized by comprising:

[0055] Send the first information report;

[0056] Specifically, when the first information reporting supports reverting to a non-AI generation method, the first information reporting depends on the output of the first operation, or the first information reporting is generated by reverting to a non-AI generation method; when the first information reporting does not support reverting to a non-AI generation method, the first information reporting depends on the output of the first operation.

[0057] As an example, the problem this application aims to solve includes: how to determine the generation of information reports.

[0058] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0059] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0060] As an example, the advantages of the above method include: supporting information reporting that reverts to a non-AI generated method.

[0061] As an example, the advantages of the above method include: adapting to different application scenarios or terminals, and having good flexibility and adaptability.

[0062] According to one aspect of this application, the first information reporting supports reverting to a non-AI generation method; when the second condition is met, the first information reporting is generated in a reverted non-AI generation method; when the second condition is not met, the first information reporting depends on the output of the first operation.

[0063] As an example, the essence of the above method includes: determining the generation of information reporting based on whether a second condition is met.

[0064] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0065] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0066] As an example, the advantages of the above method include: supporting information reporting that reverts to a non-AI generated method.

[0067] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0068] As an example, the advantages of the above method include: supporting information reporting based on both AI and non-AI generation methods.

[0069] As an example, the advantages of the above method include: adapting to different application scenarios or terminals, and having good flexibility and adaptability.

[0070] As an example, the advantages of the above method include: improving the accuracy and reliability of information reporting and enhancing the overall performance of the system.

[0071] According to one aspect of this application, it is characterized by comprising:

[0072] When the first condition is met, the first information report is not updated;

[0073] The first information report does not support reverting to a non-AI generation method.

[0074] As an example, the problem this application aims to solve includes: how to determine whether to update information reporting.

[0075] As an example, the essence of the above method includes: determining whether to update the information report based on whether a first condition is met.

[0076] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0077] As an example, the advantages of the above method include: not updating expired information reports, reducing computational overhead, and improving system transmission efficiency.

[0078] As an example, the advantages of the above method include: minimal changes to the standard and improved forward and backward compatibility of the system.

[0079] As an example, the advantages of the above method include: improving the flexibility of the system.

[0080] According to one aspect of this application, it is characterized by comprising:

[0081] When the first condition is met, the transmission of the first information is abandoned.

[0082] The first information report does not support reverting to a non-AI generation method.

[0083] As an example, the problem this application aims to solve includes: how to determine whether to abandon information reporting.

[0084] As an example, the essence of the above method includes: determining whether to abandon information reporting based on whether a first condition is met.

[0085] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the processing of information reporting.

[0086] As an example, the advantages of the above method include: abandoning the reporting of failed information, reducing resource overhead, and improving transmission efficiency.

[0087] As an example, the advantages of the above method include: minimal changes to the standard and improved forward and backward compatibility of the system.

[0088] As an example, the advantages of the above method include: improving the flexibility of the system.

[0089] According to one aspect of this application, the first information set indicates M configurations, the first configuration being one of the M configurations, where M is a positive integer greater than 1; the first configuration includes a first type of indication, the first type of indication in the first configuration being used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, the first reference operation depending on a second configuration, the second configuration being one of the M configurations.

[0090] As an example, the advantages of the above method include ensuring that the sending and receiving ends have a consistent understanding of the configuration and processing of information reporting.

[0091] As an example, the advantages of the above method include: supporting the association of one information report and multiple configurations through the first type of indication, simplifying system design and improving system flexibility.

[0092] As an example, the advantages of the above method include: multiple configurations for obtaining a single information report, improving the accuracy of information reporting, reducing latency, lowering reporting overhead, and improving overall system performance.

[0093] As an example, the advantages of the above method include: adapting to different application scenarios or terminals, and having good flexibility and adaptability.

[0094] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0095] Send a first set of information; the first set of information indicates a first configuration, the first configuration being used to configure the first information reporting; the first information reporting depends on the output of the first operation, or the first information reporting is generated by a fallback to a non-AI generation method;

[0096] Wherein, the first configuration indicates the first operation, and the first operation is based on AI; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0097] According to one aspect of this application, the second node is a base station.

[0098] According to one aspect of this application, the second node is a relay node.

[0099] According to one aspect of this application, the second node is a user equipment.

[0100] As one example, the user equipment is a terminal.

[0101] As an example, the target recipient of the first information set deploys the first operation.

[0102] As an example, the first operation is obtained by loading.

[0103] As an example, the AI ​​(Artificial Intelligence) includes ML (Machine Learning).

[0104] According to one aspect of this application, the first information reporting is characterized by defaulting to whether it supports falling back to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation.

[0105] According to one aspect of this application, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0106] According to one aspect of this application, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is by default.

[0107] According to one aspect of this application, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0108] According to one aspect of this application, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0109] According to one aspect of this application, the first information reporting does not support a fallback to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; and the first information reporting supports a fallback to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0110] According to one aspect of this application, it is characterized by comprising:

[0111] Receive the first information report;

[0112] Specifically, when the first information reporting supports reverting to a non-AI generation method, the first information reporting depends on the output of the first operation, or the first information reporting is generated by reverting to a non-AI generation method; when the first information reporting does not support reverting to a non-AI generation method, the first information reporting depends on the output of the first operation.

[0113] According to one aspect of this application, it is characterized by comprising:

[0114] Abandon receiving the first information report;

[0115] Specifically, when the first information reporting supports reverting to a non-AI generation method, the first information reporting depends on the output of the first operation, or the first information reporting is generated by reverting to a non-AI generation method; when the first information reporting does not support reverting to a non-AI generation method, the first information reporting depends on the output of the first operation.

[0116] As one embodiment, the second node monitors whether the first information report is sent by the target recipient of the first information set.

[0117] As one embodiment, the second node determines on its own whether to give up receiving the first information report.

[0118] According to one aspect of this application, the first information reporting supports reverting to a non-AI generation method; when the second condition is met, the first information reporting is generated in a reverted non-AI generation method; when the second condition is not met, the first information reporting depends on the output of the first operation.

[0119] According to one aspect of this application, it is characterized by comprising:

[0120] When the first condition is met, the target receiver of the first information set does not update the first information report;

[0121] The first information report does not support reverting to a non-AI generation method.

[0122] According to one aspect of this application, it is characterized by comprising:

[0123] When the first condition is met, the target receiver of the first information set abandons sending the first information report;

[0124] The first information report does not support reverting to a non-AI generation method.

[0125] According to one aspect of this application, the first information set indicates M configurations, the first configuration being one of the M configurations, where M is a positive integer greater than 1; the first configuration includes a first type of indication, the first type of indication in the first configuration being used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, the first reference operation depending on a second configuration, the second configuration being one of the M configurations.

[0126] This application discloses a terminal, characterized in that the terminal includes: one or more processors and a memory;

[0127] The memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions. The one or more processors invoke the computer instructions to cause the terminal to execute the method in the first node.

[0128] As one example, the terminal is a user equipment.

[0129] This application discloses a base station, characterized in that the base station includes: one or more processors and a memory;

[0130] The memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions. The one or more processors invoke the computer instructions to cause the base station to perform the method in the second node.

[0131] This application discloses a first node used for wireless communication, characterized in that it comprises:

[0132] A first processor receives a first set of information; the first set of information indicates a first configuration, which is used to configure first information reporting; the first information reporting depends on the output of a first operation, or the first information reporting is generated by a fallback to a non-AI generation method.

[0133] Wherein, the first configuration indicates the first operation, and the first operation is based on AI; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0134] This application discloses a second node used for wireless communication, characterized in that it comprises:

[0135] The second processor sends a first information set; the first information set indicates a first configuration, which is used to configure the first information reporting; the first information reporting depends on the output of the first operation, or the first information reporting is generated by a fallback to a non-AI generation method.

[0136] Wherein, the first configuration indicates the first operation, and the first operation is based on AI; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0137] As an example, compared with conventional solutions, this application has the following advantages:

[0138] Ensure consistency in the understanding of information reporting configuration and processing between the sending and receiving ends;

[0139] Supports AI-based information reporting;

[0140] Supports reverting to information reporting methods other than AI generation;

[0141] It supports multiple AI-based or non-AI-based operations for obtaining information reporting;

[0142] Improve the accuracy of information reporting and reduce reporting delays and costs;

[0143] To better adapt to various application scenarios or terminals, and improve the system's flexibility and adaptability;

[0144] Enhance the reliability and robustness of the system;

[0145] Improve the system's forward and backward compatibility;

[0146] Simplify system design and reduce the complexity of solution implementation;

[0147] Improve the overall performance of the system. Attached Figure Description

[0148] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0149] Figure 1 illustrates a flowchart of a first information set according to an embodiment of this application;

[0150] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0151] Figure 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application;

[0152] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0153] Figure 5 illustrates a flowchart of wireless transmission according to an embodiment of this application;

[0154] Figure 6 illustrates whether the first information reporting according to an embodiment of this application supports reverting to a non-AI generation method;

[0155] Figure 7 illustrates whether the first information reporting according to another embodiment of this application supports reverting to a non-AI generation method;

[0156] Figure 8 illustrates whether the first information reporting according to another embodiment of this application supports reverting to a non-AI generation method;

[0157] Figure 9 illustrates whether the first information reporting according to another embodiment of this application supports reverting to a non-AI generation method;

[0158] Figure 10 shows a schematic diagram of the first information reporting according to an embodiment of this application;

[0159] Figure 11 illustrates a schematic diagram of the relationship between a first operation and a first reference operation according to an embodiment of this application;

[0160] Figures 12A and 12B respectively illustrate schematic diagrams of a first node deploying a first given operation according to an embodiment of this application;

[0161] Figure 13 illustrates a schematic diagram of the deployment of AI / ML functions in a RAN (Radio Access Network) domain according to an embodiment of this application;

[0162] Figure 14 shows a schematic diagram of the deployment of AI / ML functions of a UE according to an embodiment of this application;

[0163] Figure 15 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0164] Figure 16 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application;

[0165] Figure 17 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0166] Figure 18 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0167] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Considering performance, flexibility, complexity, overhead, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, such as, but not limited to, the embodiments in Figure 1 and the embodiments in Figures 5-18, the embodiments in Figure 5 and the embodiments in Figures 6-18, etc.

[0168] Example 1

[0169] Example 1 illustrates a flowchart of a first information set according to an embodiment of this application, as shown in Figure 1. In Figure 1, 100, each block represents a step.

[0170] In Embodiment 1, the first node receives a first information set in step 101; wherein, the first information set indicates a first configuration, the first configuration being used to configure a first information report; the first information report depends on the output of a first operation, or the first information report is generated by falling back to a non-AI generation method; the first configuration indicates the first operation, the first operation being AI-based; whether the first information report supports falling back to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0171] As one embodiment, the first information set is carried by higher layer signaling.

[0172] As an example, the first information set is carried by RRC (Radio Resource Control) signaling.

[0173] As an example, the first information set is carried by RRC signaling and MAC CE signaling.

[0174] As an example, the first information set includes an RRC IE (Information Element).

[0175] As one embodiment, the first information set includes multiple RRC IEs.

[0176] As one embodiment, the first information set includes some or all of the fields in one or more RRC IEs.

[0177] As one embodiment, the first information set includes one or more IE CSI-ReportConfigs.

[0178] As one embodiment, the first information set includes some or all of the domains in one or more IE CSI-ReportConfig.

[0179] As one embodiment, the first information set includes some or all of the domains in IE ServingCellConfig.

[0180] As one embodiment, the first information set includes some or all of the domains in IE CSI-MeasConfig IE.

[0181] As one embodiment, the first information set includes some or all of the domains in IE ServingCellConfigCommon IE.

[0182] As one embodiment, the first information set includes some or all of the domains in IE ServingCellConfig.

[0183] As one embodiment, the first information set indicating the first configuration includes: the first information set indicating the identifier of the first configuration.

[0184] As one embodiment, the first information set indicating the first configuration includes: the first information set indicating the index of the first configuration.

[0185] As one embodiment, the first information set indicates that the first configuration includes: the first information set includes the first configuration.

[0186] As one embodiment, the first information set indicating the first configuration includes: the first information set includes at least one RRC IE, and the first configuration is carried by the at least one RRC IE.

[0187] As an example, the first configuration includes at least one RRC IE.

[0188] As an example, the first configuration includes M at least one IE CSI-ReportConfig.

[0189] As one embodiment, the first configuration includes some or all of the domains in at least one RRC IE.

[0190] As one embodiment, the first configuration includes some or all of the domains in at least one IE CSI-ReportConfig.

[0191] As an example, the first configuration is carried by at least one RRC IE.

[0192] As an example, the first configuration is carried by at least one IE CSI-ReportConfig.

[0193] As an example, the first configuration indicates at least one of at least one RS resource for the measurement of the first information reporting, the reporting type of the first information reporting, or the reporting amount of the first information reporting.

[0194] As an example, the first configuration indicates at least one of the following: at least one RS resource for the measurement of the first information reporting, at least one RS resource to which the first information reporting is targeted, the reporting type of the first information reporting, or the reporting amount of the first information reporting.

[0195] As a sub-implementation of the above embodiments, the measurement used for the first information reporting refers to: channel measurement used for the first information reporting.

[0196] As a sub-implementation of the above embodiments, the measurement used for the first information reporting refers to at least one of channel measurement or interference measurement used for the first information reporting.

[0197] As a sub-implementation of the above embodiments, the measurement used for the first information reporting refers to: channel measurement and interference measurement used for the first information reporting.

[0198] As a sub-example of the above embodiments, the reporting type indicates at least one of periodic reporting, semi-persistent reporting, or non-periodic reporting.

[0199] As a sub-implementation of the above embodiments, the reporting type indicates at least one of periodic reporting, semi-persistent reporting, non-periodic reporting, or event-triggered reporting.

[0200] As an example, the first information report is used for at least one of performance monitoring, positioning, beam management, CSI prediction, CSI estimation, CSI compression, RLF (radio link failure) prediction, cell handover prediction, or serving cell prediction.

[0201] As one embodiment, the beam management includes at least one of beam prediction, beam switching, beam failure prediction, or beam failure recovery.

[0202] As an example, the first information report includes UCI (Uplink Control Information).

[0203] As an example, the first information is reported and transmitted on PUSCH (Physical Uplink Shared Channel).

[0204] As an example, the first information is reported and transmitted on the PUCCH (Physical Uplink Control Channel).

[0205] As an example, the first information report includes at least one of the following: predicted beam information, predicted CSI, estimated CSI, compressed CSI, confidence information, or performance monitoring results.

[0206] As an example, the first information report includes at least one of performance monitoring results, location information, RLF prediction, beam failure prediction, cell handover prediction, beam handover prediction, or serving cell prediction.

[0207] As an example, the compressed CSI is based on a non-codebook.

[0208] As an example, the compressed CSI is not a reporting quantity defined by 3GPP Rel-18, nor is it a reporting quantity defined by versions prior to 3GPP Rel-18.

[0209] As an example, the compressed CSI is not a reporting quantity defined by 3GPP Rel-19, nor is it a reporting quantity defined by versions prior to 3GPP Rel-19.

[0210] As an example, the compressed CSI is not part of the reporting volume defined by the 5G standard.

[0211] As an example, the channel parameters recovered by the target receiver of the compressed CSI based on the compressed CSI are unknown to the sender of the compressed CSI.

[0212] As an example, the compressed CSI is based on artificial intelligence or machine learning.

[0213] As an example, the compressed CSI is based on a neural network.

[0214] As an example, the compressed CSI is based on CNN (Conventional Neural Networks).

[0215] As an example, the first information reporting includes reporting volumes that do not belong to 3GPP Rel-18 and earlier versions.

[0216] As one example, the first information reporting includes reporting quantities that are not defined in the 5G standard.

[0217] As an example, the first information reporting includes the reporting volume defined in the 6G standard.

[0218] As one example, the first information report includes information generated based on artificial intelligence or machine learning.

[0219] As one example, the first information report includes information generated based on a neural network.

[0220] As an example, the first information report includes information generated based on CNN (Conventional Neural Networks).

[0221] As one example, the first information report includes information generated based on the Transformer.

[0222] As one example, the first information report includes channel information.

[0223] As one embodiment, the channel information includes at least one of beam failure prediction and beam switching prediction.

[0224] As one embodiment, the channel information includes at least one of predicted beam information, switched beam information, predicted CSI, estimated CSI, or compressed CSI.

[0225] As one example, the beam information includes the beam.

[0226] As an example, the beam information includes RSRP (reference signal received power).

[0227] As one embodiment, the beam information includes at least one of resource indication or RSRP.

[0228] As an example, the resource indication in this application is used to indicate beam or RS resources.

[0229] As an example, the resource indication in this application is used to indicate at least one of beam, CSI-RS resource, or SS / PBCH block resource.

[0230] As an example, the resource indication in this application includes at least one of beam indication, CRI (CSI-RS Resource Indicator, Channel State Information Reference Signal Resource Indicator), or SS / PBCH Block Resource Indicator (SSBRI).

[0231] As one example, the channel information includes CSI (channel state information).

[0232] As one example, the channel information includes CSI or beam information.

[0233] As one example, the channel information includes the channel impulse response.

[0234] As one example, the channel information includes small-scale characteristics.

[0235] As one embodiment, the channel information includes one or more of delay spread, Doppler spread, Doppler shift, average delay, or average gain.

[0236] As one example, the channel information includes a channel matrix.

[0237] As an example, the channel matrix is ​​in the spatial-frequency domain.

[0238] As an example, the channel matrix is ​​in the angular-delay domain projection.

[0239] As one embodiment, the channel information includes at least one of the channel's feature values ​​or feature vectors.

[0240] As an example, the channel information includes one or more of the following: beam information, PMI (Precoding Matrix Indicator), CRI (CSI-RS Resource Indicator), CQI (Channel Quality Indicator), RI (Rank Indicator), LI (layer indicator), SSBRI (SS / PBCH Block Resource Indicator), RSRP (Reference Signal Received Power), SINR (Signal-to-Interference-plus-Noise Ratio), Capability Index, and TDCP (Time Domain Channel Properties).

[0241] As one embodiment, the first information report includes information other than channel information.

[0242] As one example, the information other than the channel information includes performance monitoring results.

[0243] As an example, the performance monitoring includes performance monitoring for AI models or AI functions.

[0244] As an example, the performance monitoring includes performance monitoring for the first operation.

[0245] As an example, the performance monitoring results include whether the first operation failed.

[0246] As an example, the performance monitoring includes performance monitoring for the first operation, and the performance monitoring result includes whether the first operation failed.

[0247] As one example, the information other than the channel information includes RLF prediction.

[0248] As one example, the information other than the channel information includes cell handover prediction.

[0249] As one example, the information other than the channel information includes serving cell prediction.

[0250] As one example, the information other than the channel information includes positioning based on artificial intelligence or machine learning.

[0251] As one example, the information other than the channel information includes artificial intelligence or machine learning-assisted positioning.

[0252] As one embodiment, the first information report includes channel information, or one of the information other than channel information.

[0253] As one embodiment, the first information report includes channel information, or at least one of the information other than channel information.

[0254] As an example, a configuration indicating an operation includes: the configuration directly indicating the operation.

[0255] As an example, a configuration indicating an operation includes: the configuration indirectly indicating the operation.

[0256] As an example, a configuration indicating an operation includes: the configuration explicitly indicating the operation.

[0257] As an example, a configuration indicating an operation includes: the configuration implicitly indicating the operation.

[0258] As an example, a configuration indicating an operation includes: an index of the configuration indicating the operation.

[0259] As an example, a configuration indicating that an operation includes: the configuration includes an index of the operation.

[0260] As an example, a configuration indicating an operation includes: the configuration includes configuration information for the operation.

[0261] As an example, a configuration indicating an operation includes: the configuration being used to configure the operation.

[0262] As an example, a configuration indicating an operation includes: the configuration includes identification information of the operation.

[0263] As one embodiment, a configuration indicating an operation includes: the configuration indicating a first type identifier, the first type identifier indicating the operation.

[0264] As an example, a configuration indicating an operation includes: the configuration includes a first type identifier that indicates the operation.

[0265] As one embodiment, a configuration indicating an operation includes: the configuration indicating a first type of identifier, the operation being associated with the first type of identifier.

[0266] As an example, a configuration indicating an operation includes: the configuration includes a first type identifier, and the operation is associated with the first type identifier.

[0267] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of solution implementation.

[0268] As an example, the advantages of the above method include: improving system flexibility and adapting to different terminals and transmission environments.

[0269] As an example, the first type of identifier is a non-negative integer.

[0270] As an example, the first type of identifier is a string.

[0271] As an example, the first type of identifier is used to identify AI models.

[0272] As an example, the first type of identifier is used to identify AI entities.

[0273] As an example, the first type of identifier is used to identify AI functions.

[0274] As an example, the advantages of the above method include: identifying an AI entity or function through the first type of identifier, simplifying system design, and unifying the understanding of different AI entities or functions across multiple nodes.

[0275] As an example, the first type of identifier is a model identifier.

[0276] As an example, the first type of identifier is used to identify an AI model.

[0277] As an example, the first type of identifier is used by the first node to identify an AI model.

[0278] As an example, the first type of identifier is used by the first node to determine the AI ​​model adopted by the first reference operation.

[0279] As an example, the advantages of the above method include: using the first type of identifier to identify an AI model / entity / function simplifies system design and unifies the understanding of different AI entities / functions across multiple nodes.

[0280] As an example, the first type of identifier is used to identify or indicate a set of resources.

[0281] As one embodiment, the first type of identifier is used to identify or indicate a set of resources, the measurement of which is used to obtain a training dataset.

[0282] As an example, the first type of identifier is used to identify or indicate a set of resources.

[0283] As an example, the first type of identifier is used to identify or indicate the training dataset.

[0284] As an example, the benefits of the above method include: identifying the inferences generated by an AI training or AI training dataset by identifying the AI ​​training or AI training dataset, establishing consensus among different AI functions, and further simplifying system design.

[0285] As one embodiment, the first operation being associated with the first type of identifier includes: the first operation being identified by the first type of identifier.

[0286] As an example, the first operation being associated with the first type of identifier includes: the AI ​​model used in the first operation being identified by the first type of identifier.

[0287] As one embodiment, the first operation associated with the first type of identifier includes: the AI ​​entity included in the first operation is identified by the first type of identifier.

[0288] As one embodiment, the first operation being associated with the first type of identifier includes: the AI ​​function to which the first operation is used is identified by the first type of identifier.

[0289] As one embodiment, the first operation associated with the first type of identifier includes: the AI ​​entity performing the first operation is identified by the first type of identifier.

[0290] As one embodiment, the first operation associated with the first type of identifier includes: the first type of identifier being used by the first node to determine the AI ​​model adopted by the first operation.

[0291] As an example, the advantages of the above method include: identifying an AI model / entity / function through the first type of identifier, simplifying the design and unifying the understanding of different AI models / entities / functions across multiple nodes.

[0292] As one embodiment, the first operation associated with the first type of identifier includes: the first type of identifier being used to identify or indicate a set of RS resources, and measurements of the set of RS resources being used to obtain a training dataset for the first operation.

[0293] As one embodiment, the first operation associated with the first type of identifier includes: the training for obtaining the first operation is identified by the first type of identifier.

[0294] As one embodiment, the first operation being associated with the first type of identifier includes: the dataset used for training the first operation being identified by the first type of identifier.

[0295] As an example, the benefits of the above method include: identifying the inferences generated by an AI training or AI training dataset by identifying the AI ​​training or AI training dataset, establishing consensus among different AI functions, and further simplifying the design.

[0296] As one embodiment, the first operation associated with the first type of identifier includes: the first operation performing spatial beam prediction for a second type of resource set based on measurements of a first type of resource set, the second type of resource set depending on the first type of identifier.

[0297] As an example, the advantages of the above method include: reducing RS overhead and reducing feedback latency.

[0298] As one embodiment, the first operation associated with the first type of identifier includes: the first operation performing channel information prediction for a second type of resource set based on measurements of the first type of resource set, the second type of resource set depending on the first type of identifier.

[0299] As one embodiment, the first operation associated with the first type of identifier includes: the first operation performing temporal beam prediction for a second type of resource set based on historical measurements of the first type of resource set, the second type of resource set depending on the first type of identifier.

[0300] As an example, the advantages of the above method include: reducing beam feedback delay and improving the real-time performance of beam acquisition.

[0301] As one embodiment, the first operation associated with the first type of identifier includes: the first operation performing temporal channel information prediction for a second type of resource set based on historical measurements of the first type of resource set, the second type of resource set depending on the first type of identifier.

[0302] As an example, the advantages of the above method include: reducing channel information feedback delay and improving the real-time performance of channel information acquisition.

[0303] As an example, the first operation is based on training or AI.

[0304] In this application, AI (Artificial Intelligence) includes ML (Machine Learning).

[0305] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0306] As an example, a training-based or AI-based operation includes inference.

[0307] As an example, a training-based or AI-based operation includes an AI entity.

[0308] As an example, a training-based or AI-based operation includes an AI entity used for inference.

[0309] As an example, a training-based or AI-based operation includes a portion of an AI entity.

[0310] As an example, a training-based or AI-based operation includes a portion of an AI entity used for inference.

[0311] As an example, a training-based or AI-based operation includes inference for obtaining the first information report.

[0312] As an example, the reasoning includes AI (Artificial Intelligence) inference.

[0313] As an example, a training-based or AI-based operation is based on artificial intelligence or machine learning.

[0314] As an example, a training-based or AI-based operation is based on a neural network.

[0315] As an example, a training-based or AI-based operation is based on CNN (Conventional Neural Networks).

[0316] As an example, a training-based or AI-driven model is obtained through training.

[0317] As an example, a training-based or AI-based operation includes preprocessing.

[0318] As an example, the preprocessing includes one or more of the following: quantization, DFT (Discrete Fourier Transform), matrix decomposition, matrix transformation or projection, quantization, spatial-to-angular-domain transformation, angular-to-spatial-domain transformation, frequency-to-time-domain transformation, time-to-frequency-domain transformation, truncation, padding, mapping, or labeling.

[0319] As an example, the label refers to a mark made with a label.

[0320] As an example, a training-based or AI-based operation includes post-processing.

[0321] As an example, the post-processing includes one or more of DFT, quantization, angular-domain to spatial-domain transformation, spatial-domain to angular-domain transformation, time-domain to frequency-domain transformation, frequency-domain to time-domain transformation, truncation, and padding.

[0322] As an example, a training-based or AI-based operation includes one or more of convolution, pooling, concatenation, and activation.

[0323] As an example, a training-based or AI-based operation includes a fully connected layer.

[0324] As an example, a training-based or AI-based operation includes a pooling layer.

[0325] As an example, a training-based or AI-based operation includes at least one convolutional layer.

[0326] As an example, a training-based or AI-based operation includes at least one encoding layer.

[0327] As an example, an encoding layer includes at least one convolutional layer and one pooling layer.

[0328] As an example, in a convolutional layer, at least one convolutional kernel is used to convolve the input to generate a corresponding feature map, and at least one feature map output by the convolutional layer is reshaped into a vector and input to a fully connected layer; the fully connected layer transforms the vector into an output.

[0329] As an example, some or all of the following operations—convolution kernel size, number of convolutional layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, and number of feature maps—are obtained through training.

[0330] As an example, some or all of the convolution kernel, pooling kernel, pooling function, activation function, parameters of the pooling function, and parameters of the activation function are obtained through training or AI-based operations.

[0331] As an example, the first operation includes AI inference for obtaining CSI.

[0332] As one example, the first operation includes AI inference for obtaining channel information.

[0333] As one example, the first operation includes AI inference for obtaining information other than channel information.

[0334] As an example, the first operation includes AI inference for at least one of beam management, positioning or assisted positioning, CSI prediction, CSI estimation, or CSI compression.

[0335] As an example, the first operation includes AI inference for at least one of performance monitoring, positioning, beam management, CSI prediction, CSI estimation, CSI compression, RLF (radio link failure) prediction, cell handover prediction, or serving cell prediction.

[0336] As an example, the first operation is used for an AI function.

[0337] As one example, the AI ​​function includes AI inference functionality.

[0338] As one example, the AI ​​functionality includes AI training functionality.

[0339] As one example, the AI ​​functionality includes AI management functionality.

[0340] As one example, the AI ​​function includes AI performance monitoring.

[0341] As an example, the training for the first operation is performed by the first node.

[0342] As an example, the training of the first operation is performed by the sender of the first information set.

[0343] As an example, the training for the first operation is performed by the core network.

[0344] As an example, the training of the first operation is performed by an AI training producer.

[0345] As an example, the training of the first operation is performed by the MDA (Management Data Analytics Function).

[0346] As an example, the training of the first operation is performed by the MDA function located at the first node.

[0347] As an example, the training of the first operation is performed by the MDA function of the sender located in the first information set.

[0348] As an example, the training of the first operation is performed by NWDAF (Network Data Analytics Function).

[0349] As an example, the training of the first operation is performed by the MDAS (Management Data Analytics Service) producer.

[0350] As an example, the training of the first operation is performed by the MnS (Management Service) producer.

[0351] As an example, the first operation includes CSI compression based on artificial intelligence or machine learning.

[0352] As an example, the first operation includes an encoder for CSI compression based on artificial intelligence or machine learning.

[0353] As an example, the first operation includes CSI prediction or CSI estimation based on artificial intelligence or machine learning.

[0354] As one example, the first operation includes beam management based on artificial intelligence or machine learning.

[0355] As one embodiment, the beam management includes at least one of beam prediction, beam switching, beam failure prediction, or beam failure recovery.

[0356] As an example, the first operation includes localization based on artificial intelligence or machine learning.

[0357] As one example, the first operation includes artificial intelligence or machine learning-assisted positioning.

[0358] As an example, the input to the first operation includes measurements obtained based on at least one RS resource.

[0359] As an example, the input to the first operation includes channel measurements obtained based on CSI-RS resources or SS / PBCH block resources.

[0360] As an example, the input to the first operation includes interference measurements obtained based on CSI-RS resources or CSI-IM resources.

[0361] As an example, the input to the first operation includes the reception quality of at least one physical channel or physical signal.

[0362] As an example, the input to the first operation includes a matrix or vector obtained by preprocessing the channel matrix obtained from measurements based on at least one RS resource.

[0363] As an example, the output of the first operation includes channel information.

[0364] As an example, the output of the first operation includes a channel matrix.

[0365] As an example, the output of the first operation includes CSI.

[0366] As an example, the output of the first operation includes compressed CSI.

[0367] In one embodiment, the output of the first operation includes the predicted CSI.

[0368] As an example, the output of the first operation includes non-codebook-based CSI.

[0369] As an example, the output of the first operation includes a channel impulse response.

[0370] As an example, the output of the first operation includes small-scale characteristics.

[0371] As an example, the output of the first operation is used to determine one or more precoding matrices.

[0372] In one embodiment, the output of the first operation includes predicted beam information.

[0373] In one embodiment, the output of the first operation includes location information.

[0374] As an example, the output of the first operation includes information other than channel information.

[0375] As an example, the output of the first operation includes at least one of channel information or information other than channel information.

[0376] As one embodiment, the output of the first information reporting depends on the first operation, which includes: the output of the first operation being used to generate the first information report.

[0377] As an example, the first information reporting depends on the output of the first operation, which includes: the output of the first operation is post-processed and used to generate the first information report.

[0378] As an example, the first information reporting depends on the output of the first operation, which includes: all or part of the output of the first operation being post-processed and used to generate the first information report.

[0379] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the first information reporting includes the output of the first operation.

[0380] As one embodiment, the first information reporting depends on the output of the first operation, including: the first information reporting includes all or part of the output of the first operation.

[0381] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the first information reporting includes the post-processed output of the first operation.

[0382] As an example, the post-processing includes one or more of the following: sampling, quantization, truncation, DFT (Discrete Fourier Transform), angular domain to spatial domain transformation, spatial domain to angular domain transformation, time domain to frequency domain transformation, and frequency domain to time domain transformation.

[0383] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the first information reporting includes the truncated and / or quantized output of the first operation.

[0384] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the output of the first operation being truncated and / or quantized and then used to generate the first information report.

[0385] As one embodiment, the first information reporting depends on the output of the first operation, which includes: some or all of the output of the first operation being truncated and / or quantized and then used to generate the first information report.

[0386] As an example, the first information report depends on the output of the first operation, which includes: measurements obtained based on at least one RS resource and the output of the first operation being used to generate the first information report.

[0387] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the reception quality of at least one physical channel or physical signal and the output of the first operation being used to generate the first information reporting.

[0388] As an example, the advantages of the above method include: enhancing the flexibility of the system and better adapting to various transmission conditions and application scenarios.

[0389] As an example, the benefits of the above method include: enhanced backward compatibility of the system.

[0390] As one embodiment, generating the first information report includes: calculating the first information report.

[0391] As one example, how the output of the first operation is used to generate the first information report is determined by the manufacturer of the first node, or is implementation-dependent. Some typical but non-limiting implementations are described below:

[0392] As an example, the output of the first operation includes predicted channel information, and a comparison between the channel information obtained from measurements based on at least one RS resource and the predicted channel information is used to generate the first information report.

[0393] As an example, the output of the first operation includes predicted beam information, and a comparison between the beam information obtained from measurements based on at least one RS resource and the predicted beam information is used to generate the first information report.

[0394] As an example, the output of the first operation includes predicted beam information, and whether the beam information obtained from the measurement of at least one RS resource is the same as the predicted beam information is used to generate the first information report.

[0395] As an example, the output of the first operation includes predicted beam information, and the first information report includes CSI.

[0396] As an example, the output of the first operation includes predicted beam information; when the comparison result between the beam information obtained from the measurement based on at least one RS resource and the predicted beam information is greater than a certain threshold, the first information is reported to indicate that the first operation has failed.

[0397] As an example, the output of the first operation includes predicted beam information; when the predicted beam information is worse than a certain threshold, the first information is reported to indicate that the first operation has failed.

[0398] As an example, the output of the first operation includes predicted beam information; when the predicted beam information is worse than a certain threshold, the first information is reported to indicate beam failure.

[0399] As an example, the output of the first operation includes the predicted RSRP; when the difference between the RSRP measured based on at least one RS resource and the predicted RSRP is greater than a certain threshold, the first information report indicates that the first operation has failed.

[0400] As an example, the output of the first operation includes the predicted link quality; when the difference between the link quality measured based on at least one RS resource and the predicted link quality is greater than a certain threshold, the first information report indicates that the first operation has failed.

[0401] As an example, the output of the first operation includes the predicted link quality; when the predicted link quality is worse than a certain threshold, the first information report indicates RLF or beam failure.

[0402] As an example, the output of the first operation includes predicted beam information, and the first information report includes one of performance monitoring results, RLF prediction, cell handover prediction, or serving cell prediction.

[0403] As an example, the output of the first operation includes predicted channel information, and the first information report includes one of performance monitoring results, RLF prediction, cell handover prediction, or serving cell prediction.

[0404] As an example, the output of the first operation includes location information, and the first information report includes location information.

[0405] As an example, the method for generating the first information report based on the output of the first operation is not based on artificial intelligence or machine learning.

[0406] As an example, the first information set is used to determine whether the input of the first operation depends on the output of another AI-based operation.

[0407] As an example, the first information set is used to indicate whether the input of the first operation depends on the output of another AI-based operation.

[0408] As an example, the first information set explicitly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0409] As an example, the first information set implicitly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0410] As an example, the first information set directly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0411] As an example, the first information set indirectly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0412] As an example, the first information set is used to indicate that the input of the first operation depends on the output of a first reference operation, which is based on training or AI.

[0413] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; the first configuration indicates a second configuration; the input of the first operation depends on the output of a first reference operation, which in turn depends on the second configuration, where the second configuration is one of the M configurations.

[0414] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations, and M is a positive integer greater than 1; the first configuration includes a first type of indication, which is used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, which depends on a second configuration, where the second configuration is one of the M configurations.

[0415] As one embodiment, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; when the first configuration includes a first type of indication, the first type of indication in the first configuration is used to indicate a second configuration, the input of the first operation depends on the output of a first reference operation, the first reference operation depends on the second configuration, where the second configuration is one of the M configurations; when the first configuration does not include a first type of indication, the input of the first operation does not depend on the output of another AI-based operation.

[0416] As an example, the advantages of the above method include: simplifying system design and improving system flexibility.

[0417] As an example, the first information set indicates M operations, where the first operation is one of the M operations, and M is a positive integer greater than 1; the M operations are cascaded, and the execution order of the M operations is one after another; except for the last operation among the M operations, the output of one of the M operations is used to generate the input of the next operation; the first information set indicates the execution order of the M operations.

[0418] As an example, the first information set indicates M operations, where the first operation is one of the M operations, and M is a positive integer greater than 1; the M operations are cascaded, and the execution order of the M operations is one after another; except for the first operation among the M operations, the input of one of the M operations depends on the output of the previous operation; the first information set indicates whether the first operation is the first operation among the M operations.

[0419] As an example, the first information set indicates M operations, where the first operation is one of the M operations, and M is a positive integer greater than 1; the M operations are divided into M1 parts, each of the M1 parts including at least one of the M operations, and M1 is a positive integer greater than 1 and less than M; the M1 parts are cascaded, and the execution order of the M1 parts is one after another; except for the first part of the M1 parts, the input of one part of the M1 parts depends on the output of the previous part; the first information set indicates the execution order of the M1 parts.

[0420] As an example, the first information set indicates M operations, where the first operation is one of the M operations, and M is a positive integer greater than 1; the M operations are divided into M1 parts, and any part of the M1 parts includes at least one operation from the M operations, where M1 is a positive integer greater than 1 and less than M; the M1 parts are cascaded, and the execution order of the M1 parts is one after another; except for the first part of the M1 parts, the input of one part of the M1 parts depends on the output of the previous part; the first information set indicates whether the first operation belongs to the first part of the M1 parts.

[0421] As an example, the advantages of the above method include: supporting joint processing between multiple AI-based operations, improving system flexibility, and improving the accuracy of information reporting.

[0422] As an example, the advantages of the above method include: enhancing the transmission efficiency of the system and improving the overall performance of the system.

[0423] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations, and M is a positive integer greater than 1; the M configurations respectively indicate M operations; the execution order of the M operations is one after another; except for the last operation among the M operations, the output of one of the M operations is used to generate the input of the next operation; the first information set indicates the execution order of the M operations.

[0424] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations, and M is a positive integer greater than 1; the M configurations respectively indicate M operations; the execution order of the M operations is one after another; except for the last operation among the M operations, the output of one of the M operations is used to generate the input of the next operation; the first information set indicates whether the first operation is the first operation among the M operations.

[0425] As an example, the advantages of the above method include reducing the complexity of system implementation.

[0426] As an example, the first configuration is used to determine whether the input of the first operation depends on the output of another AI-based operation.

[0427] As an example, the first configuration is used to indicate whether the input of the first operation depends on the output of another AI-based operation.

[0428] As an example, the first configuration explicitly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0429] As an example, the first configuration implicitly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0430] As an example, the first configuration directly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0431] As an example, the first configuration indirectly indicates whether the input of the first operation depends on the output of another AI-based operation.

[0432] As an example, the first configuration indicates a first reference operation; the input of the first operation depends on the output of the first reference operation, the first reference operation depends on a second configuration, the second configuration being a configuration in the first information set.

[0433] As an example, the first configuration includes a first type of indication, which is used to indicate a first reference operation; the input of the first operation depends on the output of the first reference operation, which depends on a second configuration, which is a configuration in the first information set.

[0434] As an example, when the first configuration includes a first type of indication, the first type of indication in the first configuration is used to indicate a first reference operation; the input of the first operation depends on the output of the first reference operation, the first reference operation depends on a second configuration, the second configuration being a configuration in the first information set; when the first configuration does not include a first type of indication, the input of the first operation does not depend on the output of another AI-based operation.

[0435] As an example, the first configuration indicates the second configuration; the input of the first operation depends on the output of the first reference operation, the first reference operation depends on the second configuration, and the second configuration is a configuration in the first information set.

[0436] As an example, the first configuration includes a first type of indication, which is used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, which depends on the second configuration, which is a configuration in the first information set.

[0437] As an example, when the first configuration includes a first type of indication, the first type of indication in the first configuration is used to indicate a second configuration, the input of the first operation depends on the output of a first reference operation, the first reference operation depends on the second configuration, and the second configuration is a configuration in the first information set; when the first configuration does not include a first type of indication, the input of the first operation does not depend on the output of another AI-based operation.

[0438] As an example, the advantages of the above method include: simplifying system design and improving system flexibility.

[0439] As an example, the first configuration is associated with a second configuration; the input of the first operation depends on the output of a first reference operation, which in turn depends on the second configuration, which is a configuration in the first information set.

[0440] As an example, when the first configuration is associated with the second configuration, the input of the first operation depends on the output of the first reference operation, which in turn depends on the second configuration, which is a configuration in the first information set; when the first configuration is not associated with the second configuration, the input of the first operation does not depend on the output of another AI-based operation.

[0441] As an example, the advantages of the above method include: improving the flexibility of the system.

[0442] As an example, the first information set is used to determine whether the input of the first operation depends on the output of an operation other than the first operation among the M operations.

[0443] As an example, the first information set is used to indicate that the input of the first operation depends on the output of a first reference operation, which is one of the M operations.

[0444] As an example, the first information report being generated in a non-AI generation manner includes: the generation of the first information report does not depend on the first operation.

[0445] As an example, the first information report being generated in a fallback to a non-AI generation method includes: the generation of the first information report does not depend on the output of the first operation.

[0446] As an example, the output of the first information reporting dependent on the first operation includes: the generation of the first information reporting uses an AI model.

[0447] As an example, the output of the first information reporting dependent on the first operation includes: the first information reporting includes information based on artificial intelligence or machine learning.

[0448] As one embodiment, the output of the first information reporting dependent on the first operation includes: the first information reporting includes information generated based on a neural network.

[0449] As an example, the output of the first information reporting dependent on the first operation includes: the first information reporting includes information generated based on CNN (Conventional Neural Networks).

[0450] As one embodiment, the first information reporting depends on the output of the first operation, which includes: the generation of the first information reporting includes the target recipient of the first information set performing the first operation, and the first information reporting depends on the output of the first operation.

[0451] As an example, the output of the first information reporting dependent on the first operation includes: the generation method of the first information reporting is associated with the first type of identifier.

[0452] As an example, the first information report being generated in a non-AI generation manner includes the following: the generation of the first information report is unrelated to the first operation.

[0453] As one embodiment, the first information report being generated in a non-AI generation manner includes: the target recipient of the first information set does not generate the first information report by performing the first operation.

[0454] As one embodiment, the first information report being generated in a non-AI generation manner includes: the generation of the first information report does not include the target recipient of the first information set performing the first operation.

[0455] As one embodiment, the first information report being generated in a fallback to a non-AI generation method includes: the generation of the first information report does not depend on the target recipient of the first information set performing the first operation.

[0456] As an example, the first information report being generated in a non-AI generation manner includes: the generation of the first information report does not depend on an AI-based operation.

[0457] As an example, the first information report being generated in a non-AI generation manner includes: the generation of the first information report did not use an AI model.

[0458] As an example, the first information report is generated in a way that is a fallback to a non-AI generation method, including: the first information report does not include information based on artificial intelligence or machine learning.

[0459] As an example, the first information report is a fallback to a non-AI generation method, including: the first information report does not include information generated based on a neural network.

[0460] As an example, the first information report is a fallback to a non-AI generation method, including: the first information report does not include information generated based on CNN (Conventional Neural Networks).

[0461] As an example, the first information report being generated in a non-AI generation manner includes: the generation method of the first information report is not associated with the first type of identifier.

[0462] As an example, the generation method of the first information report is not associated with the first type of identifier, including: the first information report depends on the output of the first operation, and the first operation is associated with the first type of identifier.

[0463] As one embodiment, the generation method of the first information report not being associated with the first type of identifier includes: the generation method of the first information report does not include the target recipient of the first information set performing a first operation, and the first operation being associated with the first type of identifier.

[0464] As an example, the generation method of the first information report not being associated with the first type of identifier includes: the generation method of the first information report does not use an AI model, and the AI ​​model is identified by the first type of identifier.

[0465] As an example, the generation method of the first information report not being associated with the first type of identifier includes: the first information report is not generated by the AI ​​entity, and the AI ​​entity is identified by the first type of identifier.

[0466] As an example, the generation method of the first information report is not associated with the first type of identifier, including: the first information report is not used for AI functions, and the AI ​​functions are identified by the first type of identifier.

[0467] As an example, the generation method of the first information report is not associated with the first type of identifier, including: the first information report is unrelated to the AI ​​dataset, and the AI ​​training dataset is identified by the first type of identifier.

[0468] As one embodiment, the generation method of the first information report associated with the first type of identifier includes: the generation method of the first information report includes the target recipient of the first information set performing a first operation, the first information report depending on the output of the first operation, and the first operation associated with the first type of identifier.

[0469] As an example, the generation method of the first information report associated with the first type of identifier includes: the generation method of the first information report uses an AI model identified by the first type of identifier.

[0470] As one embodiment, the generation method of the first information report associated with the first type of identifier includes: the AI ​​entity identified by the first type of identifier generates the first information report.

[0471] As one embodiment, the generation method of the first information report associated with the first type of identifier includes: the first information report is generated by an AI entity, and the first type of identifier is used to identify the AI ​​entity.

[0472] As one embodiment, the generation method of the first information report associated with the first type of identifier includes: the first information report is used for AI functions, and the first type of identifier is used to identify the AI ​​functions.

[0473] As an example, the first information set indicates M operations, where the first operation is one of the M operations, and M is a positive integer greater than 1; whether the first information reporting supports rollback to a non-AI generation method depends on whether the input of the first operation depends on the output of an operation other than the first operation among the M operations.

[0474] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; the M configurations respectively indicate M operations, where the first operation is one of the M operations; whether the first information reporting supports rollback to a non-AI generation method depends on whether the input of the first operation depends on the output of an operation other than the first operation among the M operations.

[0475] As an example, the advantages of the above method include: supporting the joint processing of multiple operations, improving the flexibility and overall performance of the system.

[0476] As an example, the first information set indicates M operations, all of which are AI-based, and the first operation is one of the M operations, where M is a positive integer greater than 1; whether the first information reporting supports rollback to a non-AI generation method depends on whether the input of the first operation depends on the output of an operation other than the first operation among the M operations.

[0477] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; the M configurations respectively indicate M operations, all of which are AI-based, and the first operation is one of the M operations; whether the first information reporting supports rollback to a non-AI generation method depends on whether the input of the first operation depends on the output of an operation other than the first operation among the M operations.

[0478] As an example, the advantages of the above method include: supporting the joint processing of multiple AI-based operations, improving the flexibility and overall performance of the system.

[0479] As one embodiment, the first configuration indicates a first reference operation, which is AI-based; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of the first reference operation.

[0480] As one embodiment, the first configuration includes a first type of indication, which is used to indicate a first reference operation, the first reference operation being AI-based; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of the first reference operation.

[0481] As one embodiment, the first configuration indicates the second configuration, the second configuration indicates the first reference operation, and the first reference operation is AI-based; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of the first reference operation.

[0482] As one embodiment, the first configuration is associated with a second configuration, the second configuration indicates a first reference operation, and the first reference operation is AI-based; whether the first information reporting supports reverting to a non-AI generation method depends on whether the input of the first operation depends on the output of the first reference operation.

[0483] As an example, the advantages of the above method include: supporting multiple operations to cascade to complete a function, improving the accuracy of information reporting, and reducing the implementation complexity of the solution.

[0484] As an example, the capability reporting of the first node includes whether it supports reverting to a non-AI generation method.

[0485] As an example, the advantages of the above method include: greater flexibility, adaptability to different terminals, and better forward compatibility.

[0486] As an example, whether the first information report supports reverting to a non-AI generation method is predefined.

[0487] As an example, the default setting is whether the first information reporting supports reverting to a non-AI generation method.

[0488] As an example, when the input of the first operation does not depend on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[0489] As an example, when the input of the first operation depends on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[0490] As an example, the advantages of the above method include reducing the implementation complexity of the system.

[0491] As an example, a higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method.

[0492] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0493] As an example, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0494] As one embodiment, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0495] As an example, the advantages of the above method include: reducing the processing power requirements of the terminal and reducing the terminal's power consumption.

[0496] As an example, the advantages of the above method include: adapting to various different scenarios and terminals, and improving the adaptability and flexibility of the system.

[0497] As an example, whether the first configuration includes a first higher-level parameter and a second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method.

[0498] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method depends on whether the first configuration includes a first higher-level parameter.

[0499] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method depends on whether the first configuration includes a second higher-level parameter.

[0500] As an example, the advantages of the above method include: adapting to various different scenarios and terminals, and improving the adaptability and flexibility of the system.

[0501] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports reverting to a non-AI generation method.

[0502] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0503] As an example, the advantages of the above method include: supporting joint processing of non-AI and AI methods, improving the flexibility and overall performance of the system.

[0504] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting supports reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting does not support reverting to a non-AI generation method.

[0505] As an example, the advantages of the above method include: supporting rollback to a non-AI method to replace the AI ​​method to complete a function, thereby improving the stability and robustness of the system.

[0506] As an example, the advantages of the above method include ensuring the stability and integrity of AI-based functions.

[0507] As an example, the advantages of the above method include: supporting the joint processing of multiple AI-based operations, thereby improving the overall performance of the system.

[0508] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting supports falling back to a non-AI generation method by default; when the input of the first operation depends on the output of another AI-based operation, the first information reporting does not support falling back to a non-AI generation method.

[0509] As an example, the advantages of the above method include ensuring the stability and integrity of functions based on multiple AI operations.

[0510] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting supports falling back to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method.

[0511] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support falling back to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method.

[0512] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports falling back to a non-AI generation method.

[0513] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting does not support falling back to a non-AI generation method.

[0514] As an example, the advantages of the above method include: improving the flexibility and completeness of the system.

[0515] Example 2

[0516] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0517] Figure 2 illustrates network architecture 200. Network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or a 5G+ network architecture, or a 6G network architecture, or a network architecture adopted in future evolutions by 3GPP; network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System), or 6GS (6G System); network architecture 200 includes at least one of UE (User Equipment) 201, RAN (Radio Access Network) 202, core network 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet service 230. The network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes node 203. The RAN may also include other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. Node 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (transmitter-receiver node), or some other suitable term. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; node 203 provides UE 201 with an access point to the core network 210.Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 is connected to the core network 210 via an S1 / NG interface. The core network 210 includes an MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, an S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 is connected to the Internet service 230. Internet services 230 include operator-compliant Internet protocol services, which may specifically include Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0518] As an example, the first node includes the UE201.

[0519] As one embodiment, the second node includes the node 203.

[0520] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0521] As an example, the sender of the first information set includes the node 203.

[0522] As an example, the recipient of the first information set includes the UE201.

[0523] As an example, the sender of the first information report includes the UE201.

[0524] As an example, the recipient of the first information report includes the node 203.

[0525] As an example, the executor of the first operation includes the UE201.

[0526] As an example, the executor of the first reference operation includes the UE201.

[0527] As an example, the executor of the M operations includes the UE201.

[0528] Example 3

[0529] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3.

[0530] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and control plane according to this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE, gNB, or RSU in V2X) and a second communication node device (gNB, UE, or RSU in V2X), or between two UEs, using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (physical layer) signal processing functions. Layer 1 will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the first communication node device and the second communication node device, or between two UEs. Layer L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. It also provides security through encrypted data packets and supports cross-cell mobility between the second communication node devices and the first communication node device. The RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ. The MAC sublayer 302 provides multiplexing between logical and transport channels. It is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among the first communication node devices. Furthermore, the MAC sublayer 302 handles HARQ operations. In the control plane 300, the Radio Resource Control (RRC) sublayer 306 of Layer 3 (L3) is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second and first communication node devices. The user plane 350's radio protocol architecture includes Layer 1 (L1) and Layer 2 (L2). The radio protocol architecture for the first and second communication node devices in the user plane 350 is largely the same as the corresponding layers and sublayers in the control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2 Layer 355, RLC sublayer 353 in L2 Layer 355, and MAC sublayer 352 in L2 Layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS streams and data radio bearers (DRBs) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., a remote UE, server, etc.).

[0531] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node.

[0532] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node.

[0533] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0534] As an example, the first information set is generated in the RRC sublayer 306.

[0535] As an example, the first information set is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0536] As an example, the first information report is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0537] As an example, the first information report is generated in the PHY301 or the PHY351.

[0538] Example 4

[0539] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0540] The first communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0541] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0542] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 layer functionality. In DL (Downlink), the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operation, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for L1 layer (i.e., physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and constellation mapping based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), and M-quadrature amplitude modulation (M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, generating one or more parallel... The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses an inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmit processor 471 into an RF stream, which is then provided to a different antenna 420.

[0543] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any parallel stream destined for the second communication device 450. Symbols on each parallel stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted over the physical channel by the first communication device 410. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2 (L2). The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the DL (Layered Logic), the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer packets from the core network. The upper-layer packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 (L3) for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0544] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functions at the first communication device 410 described in the DL, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on the radio resource allocation of the first communication device 410, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0545] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the receiving function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 layer functions. The controller / processor 475 implements the L2 layer functions. The controller / processor 475 may be associated with a memory 476 that stores program code and data. The memory 476 may be referred to as computer-readable media. The controller / processor 475 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer data packets from the second communication device 450. The upper-layer data packets from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0546] As one embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 450 means at least: receiving a first information set; the first information set indicating a first configuration, the first configuration being used to configure a first information report; the first information report depending on the output of a first operation, or the first information report being generated in a fallback to a non-AI generation method; wherein the first configuration indicates the first operation, the first operation being AI-based; whether the first information report supports a fallback to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0547] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first information set; the first information set indicating a first configuration used to configure a first information report; the first information report depending on the output of a first operation, or the first information report being generated in a fallback to a non-AI-generated manner; wherein the first configuration indicates the first operation, the first operation being AI-based; and whether the first information report supports a fallback to a non-AI-generated manner depends on whether the input of the first operation depends on the output of another AI-based operation.

[0548] As one embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The first communication device 410 means at least: transmitting a first information set; the first information set indicating a first configuration, the first configuration being used to configure a first information report; the first information report depending on the output of a first operation, or the first information report being generated in a fallback to a non-AI generation method; wherein, the first configuration indicating the first operation, the first operation being AI-based; whether the first information report supports a fallback to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0549] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: sending a first information set; the first information set indicating a first configuration used to configure a first information report; the first information report depending on the output of a first operation, or the first information report being generated in a fallback to a non-AI generation method; wherein the first configuration indicates the first operation, the first operation being AI-based; whether the first information report supports fallback to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0550] As an example, the first node in this application includes the second communication device 450.

[0551] As an example, the second node in this application includes the first communication device 410.

[0552] As an example, at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first information set in this application; at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, and the memory 476} is used to transmit the first information set in this application.

[0553] As an example, at least one of the following is used to send the first information report in this application: {the antenna 452, the transmitter / receiver 454, the transmission processor 468, the multi-antenna transmission processor 457, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467}.

[0554] As an example, at least one of the following is used to receive the first information report in this application: the antenna 420, the transmitter / receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, and the memory 476.

[0555] As an example, at least one of the following is used to perform the first operation in this application: {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467}.

[0556] As an example, at least one of the following is used to perform the first reference operation in this application: {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467}.

[0557] As an example, at least one of the following is used to perform the M operations in this application: {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467}.

[0558] As an example, at least one of {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to perform at least one of the M operations in this application.

[0559] Example 5

[0560] Example 5 illustrates a flowchart of wireless transmission according to an embodiment of this application; as shown in Figure 5. In Figure 5, the second node U1 and the first node U2 are communication nodes transmitting via an air interface. In Figure 5, the steps in blocks F50 to F54 are optional, while the steps in blocks F53 and F54 are alternatives.

[0561] For the second node U1, the first information set is sent in step S511; the first information report is received in step S512.

[0562] For the first node U2, the first operation is deployed in step S520; the first information set is received in step S521; the first operation is executed in step S522; the first information report is not updated in step S523; the first information report is sent in step S524; and the sending of the first information report is abandoned in step S525.

[0563] In embodiment 5, the first information set indicates a first configuration, which is used to configure the first information reporting; the first information reporting depends on the output of a first operation, or the first information reporting is generated by falling back to a non-AI generation method; the first configuration indicates the first operation, which is AI-based; whether the first information reporting supports falling back to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[0564] As an example, the first node U2 is the first node in this application.

[0565] As an example, the second node U1 is the second node in this application.

[0566] As one embodiment, the air interface between the second node U1 and the first node U2 includes a wireless interface between the base station equipment and the user equipment.

[0567] As one embodiment, the air interface between the second node U1 and the first node U2 includes a wireless interface between the relay node device and the user equipment.

[0568] As one embodiment, the air interface between the second node U1 and the first node U2 includes a wireless interface between user equipment and user equipment.

[0569] In one embodiment, the second node U1 is the serving cell sustaining base station of the first node U2.

[0570] As an example, step S520 is not present, and the first operation does not require deployment.

[0571] As an example, step S520 exists, where the first operation requires deployment.

[0572] As an example, the first node deploys the first operation.

[0573] As an example, deploying an operation includes: obtaining an operation.

[0574] As an example, deploying an operation includes: loading an operation.

[0575] As one example, deploying an operation includes: submitting a request to load an operation.

[0576] As an example, the advantages include: providing sufficient degrees of freedom for the first node to adapt to various scenarios and terminals, thus exhibiting adaptability and flexibility.

[0577] As an example, the deployment of the first operation precedes the reception of the first information set.

[0578] As an example, the deployment of the first operation is later than the reception of the first information set.

[0579] As an example, the model for the first operation is obtained through training.

[0580] As an example, the first operation is not obtained by loading.

[0581] As an example, the first operation is obtained by loading.

[0582] As one embodiment, the loading includes loading from the serving cell of the first node.

[0583] As one embodiment, the loading includes loading from the sustaining base station of the serving cell of the first node.

[0584] As one example, the loading includes loading from the core network.

[0585] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0586] As an example, the AI ​​training function in the RAN (Radio Access Network) domain is located in the RAN domain-specific management function, while the AI ​​inference function is located in the UE.

[0587] As an example, RAN domain-specific management functions provide AI training function management capabilities and AI inference function management capabilities.

[0588] As an example, the AI ​​training function is located in the RAN domain-specific management function, while the AI ​​inference function is located locally in the gNB.

[0589] As an example, the management capability of AI training is provided by RAN domain-specific management functions, while the management capability of AI inference is provided locally by the gNB.

[0590] As an example, MnF refers to Management Function.

[0591] As an example, both the AI ​​training function and the AI ​​inference function are located in the UE, wherein the UE provides the ability to train and infer.

[0592] As an example, RAN domain-specific management functions provide management capabilities for AI training and AI inference functions.

[0593] As an example, both the AI ​​training function and the AI ​​inference function are located in the gNB.

[0594] As an example, the management capabilities for both AI training and AI inference are provided locally by gNB.

[0595] As an example, the first operation is performed by the physical layer of the first node.

[0596] As an example, the first operation is performed at a higher level than the first node.

[0597] As an example, block F51 exists, and the first node performs the first operation.

[0598] As an example, the first operation fails, box F51 does not exist, and the first node does not perform the first operation.

[0599] As an example, block F51 exists, the first node performs the first operation; the first information reporting depends on the output of the first operation.

[0600] As an example, if box F51 is not present, the first node does not perform the first operation.

[0601] As an example, if box F51 is not present, the first node does not perform the first operation; the first information report is generated in a non-AI generation mode.

[0602] As an example, if box F51 is not present, the first node does not perform the first operation; the first node does not update the first information report.

[0603] As an example, if block F51 is not present, the first node does not perform the first operation; the first node abandons sending the first information report.

[0604] As an example, the first information reporting supports reverting to a non-AI generation method; when the second condition is met, box F51 does not exist, and the first node does not perform the first operation; when the second condition is not met, box F51 exists, and the first node performs the first operation.

[0605] As an example, the first information report supports reverting to a non-AI generation method; if box F51 is not present, the first node does not perform the first operation, and the first information report is generated in a reverted non-AI generation method.

[0606] As an example, the first information reporting supports reverting to a non-AI generation method; if box F51 exists, the first node performs the first operation, and the first information reporting depends on the output of the first operation.

[0607] As an example, the first information reporting supports reverting to a non-AI generation method; when the second condition is met, box F51 does not exist, the first node does not perform the first operation, and the first information reporting is generated in a reverted non-AI generation method; when the second condition is not met, box F51 exists, the first node performs the first operation, and the first information reporting depends on the output of the first operation.

[0608] As an example, the first information reporting does not support reverting to a non-AI generation method; if box F51 exists, the first node performs the first operation, and the first information reporting depends on the output of the first operation.

[0609] As an example, the first information reporting does not support reverting to a non-AI generation method; if box F51 does not exist, the first node does not perform the first operation; if box F52 exists, the first node does not update the first information reporting.

[0610] As an example, the first information reporting does not support rollback to a non-AI generation method; if box F51 is not present, the first node does not perform the first operation; if box F54 is present, the first node abandons sending the first information reporting.

[0611] As an example, the first information report supports reverting to a non-AI generation method; when the second condition is met, the first information report is generated in a non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[0612] As an example, the second condition includes at least one sub-condition; the second condition is satisfied when one of the sub-conditions is satisfied; the second condition is not satisfied when each of the sub-conditions is not satisfied.

[0613] As an example, the second condition includes at least one sub-condition; the second condition is satisfied when each sub-condition in the second condition is satisfied; the second condition is not satisfied when one of the sub-conditions in the second condition is not satisfied.

[0614] As an example, the second condition includes multiple sub-conditions; the second condition is satisfied when one of the sub-conditions is satisfied; the second condition is not satisfied when none of the sub-conditions are satisfied.

[0615] As an example, the second condition includes multiple sub-conditions; the second condition is satisfied when all sub-conditions of the second condition are satisfied; the second condition is not satisfied when one sub-condition of the second condition is not satisfied.

[0616] As one example, the second condition includes: the first operation fails.

[0617] As one example, the second condition includes: the first operation requires retraining.

[0618] As one example, the second condition includes: the first operation needs to be redeployed or reloaded.

[0619] As one embodiment, the second condition includes: recovering the input of the first operation based on the output of the first operation, wherein the difference between the recovered input of the first operation and the actual input of the first operation is greater than a certain threshold.

[0620] As one embodiment, the second condition includes: the first operation fails to achieve the expected performance or performance target.

[0621] As an example, the second condition includes: the output of the first operation includes reliability, which is below a certain threshold.

[0622] As one embodiment, the second condition includes: the output of the first operation includes confidence information, which is below a certain threshold.

[0623] As an example, the second condition includes: the performance target of the ML test or ML simulation of the first operation is lower than a certain threshold.

[0624] As one embodiment, the second condition includes: the first operation is used to obtain predicted beam information, wherein the difference between the predicted beam information and the measured beam information is greater than a certain threshold.

[0625] As one embodiment, the second condition includes: the first operation is used to obtain predicted channel information, wherein the difference between the predicted beam information and the measured channel information is greater than a certain threshold.

[0626] As one embodiment, the second condition includes: the first operation is used to obtain a predicted RSRP, and the difference between the predicted RSRP and the measured RSRP is greater than a certain threshold.

[0627] As one embodiment, the second condition includes: the timer corresponding to the first operation expires.

[0628] As one embodiment, the second condition includes: the timer corresponding to the first operation starts or restarts.

[0629] As one embodiment, the second condition includes: the first operation has not been updated within a time window.

[0630] As one example, the second condition includes: any other operation associated with the first operation fails.

[0631] As one embodiment, the second condition includes: any other operation cascaded with the first operation fails.

[0632] As one embodiment, the second condition includes: any other operation that has an input-output relationship with the first operation fails.

[0633] As one embodiment, the first node sends the first information report; wherein, when the first information report supports reverting to a non-AI generation method, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method.

[0634] As one embodiment, the first node sends the first information report; wherein, when the first information report does not support a fallback to a non-AI generation method, the first information report depends on the output of the first operation.

[0635] As an example, the completeness of the solution is enhanced, and the stability and robustness of the system are improved.

[0636] As an example, when box F52 exists, box F53 exists, the first node does not update the first information report, and the first node sends the first information report.

[0637] As an example, when box F52 exists, box F54 does not exist, the first node does not update the first information report, and the first node sends the first information report.

[0638] As an example, if box F52 is not present and box F53 is present, the first node updates the first information report and sends the first information report.

[0639] As an example, if box F52 is not present and box F54 is present, the first node will abandon sending the first information report.

[0640] As an example, the essence of the above method includes: only updating and sending information reports that have not expired.

[0641] As an example, the advantages of the above method include: reducing system resource overhead and improving overall system performance.

[0642] As an example, when the first condition is not met, the first node sends the first information report, which depends on the output of the first operation; wherein, the first information report does not support rollback to a non-AI generation method.

[0643] As an example, when the first condition is not met, the first node updates the first information report, the first node sends the first information report, and the first information report depends on the output of the first operation; wherein, the first information report does not support rollback to a non-AI generation method.

[0644] As an example, when the first condition is met, the first node does not update the first information report, and the first node sends the first information report; wherein, the first information report does not support rollback to a non-AI generation method.

[0645] As one embodiment, the first node sends the first information report; wherein, the first information report does not support rollback to a non-AI generation method; when the first condition is met, the first processor does not update the first information report.

[0646] As an example, the step of not updating the first information report when the first condition is met includes: updating the first information report when the first condition is not met.

[0647] As one embodiment, the step of not updating the first information report when the first condition is met includes: the first information report is sent regardless of whether the first condition is met.

[0648] As an example, the essence of the above method includes: only updating information reports that have not expired.

[0649] As an example, the advantages of the above method include: reducing the computational resource overhead of the system and improving the overall performance of the system.

[0650] As an example, when the first condition is met, the first node abandons sending the first information report; wherein, the first information report does not support rollback to a non-AI generation method.

[0651] As an example, the step of abandoning the transmission of the first information report when the first condition is met includes: when the first condition is not met, the first node transmits the first information report.

[0652] As an example, when the first condition is met, the first node abandons sending the first information report; when the first condition is not met, the first node sends the first information report; wherein, the first information report does not support rollback to a non-AI generation method.

[0653] As an example, the first information report does not support reverting to a non-AI generation method; the sending of the first information report is subject to preconditions, such as the first condition not being met.

[0654] As an example, the essence of the above method includes: only sending reports of information that has not expired.

[0655] As an example, the advantages of the above method include: reducing system resource overhead and improving system transmission efficiency.

[0656] As one embodiment, the second node monitors whether the first information report is sent by the target recipient of the first information set.

[0657] As one example, the second node determines for itself whether to receive the first information report.

[0658] As one embodiment, the second node determines on its own whether to give up receiving the first information report.

[0659] As an example, the essence of the above method includes enhancing the completeness of the system and solution.

[0660] As an example, the updating of an information report includes: the information report being valid.

[0661] As one example, the updating of an information report includes: the information report being different from the most recent report.

[0662] As one example, the updating of an information report includes the following: the information report may be different from the most recent report.

[0663] As one example, the updating of an information report includes the following: the information report is not necessarily the same as the most recent report.

[0664] As an example, the updating of an information report includes: the information report is based on measurements of at least one RS resource.

[0665] As an example, the updating of an information report includes: the information report is generated based on a measurement of at least the most recent RS timing of at least one RS resource no later than the CSI reference resource of the information report.

[0666] As an example, the updating of an information report includes: the information report being updated based on a measurement of at least the most recent RS timing of at least one RS resource no later than the CSI reference resource of the information report.

[0667] As an example, the information report not being updated includes: the first node is not expected to update the information report.

[0668] As an example, the first node is not expected to update the information report, including whether the information report is actually updated is determined by the first node itself or is implementation-related.

[0669] As an example, the information report not being updated includes: the information report being invalid.

[0670] As an example, the statement that an information report is not updated includes: the information report is not updated based on the most recent report.

[0671] As one example, the information report not being updated includes: the information report being the same as the most recent report.

[0672] As one embodiment, the statement that an information report is not updated includes: the first information report must be the same as the most recent report.

[0673] As an example, the fact that an information report is not updated includes: the information report is unrelated to the measurement of the RS resource used for the measurement of the information report at a time no later than the most recent RS timing of the CSI reference resource for the information report.

[0674] As an example, the information report not being updated includes: the information report includes a default value.

[0675] As an example, the fact that an information report is not updated includes: the information report is unrelated to the measurement of RS resources.

[0676] As an example, the information report not being updated includes: the information report is not generated based on measurements of RS resources.

[0677] As an example, the first condition includes at least one sub-condition; the first condition is satisfied when one of the sub-conditions in the first condition is satisfied; the first condition is not satisfied when each of the sub-conditions in the first condition is not satisfied.

[0678] As an example, the first condition includes at least one sub-condition; the first condition is satisfied when each sub-condition in the first condition is satisfied; the first condition is not satisfied when one of the sub-conditions in the first condition is not satisfied.

[0679] As an example, the first condition includes multiple sub-conditions; the first condition is satisfied when one of the sub-conditions is satisfied; the first condition is not satisfied when none of the sub-conditions are satisfied.

[0680] As an example, the first condition includes multiple sub-conditions; the first condition is satisfied when all sub-conditions of the first condition are satisfied; the first condition is not satisfied when one sub-condition of the first condition is not satisfied.

[0681] As an example, the first condition and the second condition are the same.

[0682] As an example, the first condition and the second condition are different.

[0683] As an example, at least one sub-condition in the first condition does not belong to the second condition.

[0684] As an example, at least one sub-condition in the second condition does not belong to the first condition.

[0685] As an example, the first condition is a subset of the second condition.

[0686] As an example, the second condition is a subset of the first condition.

[0687] As an example, if the first condition is met, then the second condition is also met.

[0688] As an example, if the second condition is met, then the first condition is also met.

[0689] As an example, the benefits of the above method include: improving the flexibility and robustness of the system.

[0690] As one example, the first condition includes: the first operation fails.

[0691] As one example, the first condition includes: the first operation requires retraining.

[0692] As one example, the first condition includes: the first operation requires redeployment or reloading.

[0693] As an example, the first condition includes: recovering the input of the first operation based on the output of the first operation, wherein the difference between the recovered input of the first operation and the actual input of the first operation is greater than a certain threshold.

[0694] As one embodiment, the first condition includes: the first operation fails to achieve the expected performance or performance target.

[0695] As an example, the first condition includes: the output of the first operation includes reliability, which is below a certain threshold.

[0696] As an example, the first condition includes: the output of the first operation includes confidence information, which is below a certain threshold.

[0697] As an example, the first condition includes: the performance target of the ML test or ML simulation of the first operation is lower than a certain threshold.

[0698] As one embodiment, the first condition includes: the first operation is used to obtain predicted beam information, wherein the difference between the predicted beam information and the measured beam information is greater than a certain threshold.

[0699] As one embodiment, the first condition includes: the first operation is used to obtain predicted channel information, wherein the difference between the predicted beam information and the measured channel information is greater than a certain threshold.

[0700] As an example, the first condition includes: the first operation is used to obtain a predicted RSRP, wherein the difference between the predicted RSRP and the measured RSRP is greater than a certain threshold.

[0701] As one example, the first condition includes: the timer corresponding to the first operation expires.

[0702] As one embodiment, the first condition includes: the timer corresponding to the first operation starts or restarts.

[0703] As one embodiment, the first condition includes: the first operation has not been updated within a time window.

[0704] As one example, the first condition includes: any other operation associated with the first operation fails.

[0705] As one embodiment, the first condition includes: any other operation cascaded with the first operation fails.

[0706] As an example, the first condition includes: any other operation that has an input-output relationship with the first operation fails.

[0707] As an example, the first node determines on its own that the first operation has failed.

[0708] As an example, the first node determines on its own that the failure of the first operation occurred in the first processor.

[0709] As an example, the first node relies on the first signaling to determine whether the first operation has failed.

[0710] As an example, the first signaling indicates that the first operation has failed.

[0711] As an example, the first node receives a first signaling message indicating that the first operation has failed.

[0712] As one embodiment, the first signaling indicates a first type of identifier, and the operation associated with the first type of identifier fails; the first operation is associated with the first type of identifier.

[0713] As one embodiment, the first signaling includes higher layer signaling.

[0714] As an example, the first signaling includes RRC (Radio Resource Control) signaling.

[0715] As an example, the first signaling includes MAC CE signaling.

[0716] As one example, the first signaling includes DCI.

[0717] As an example, the first signaling is RRC signaling.

[0718] As an example, the first signaling is MAC CE signaling.

[0719] As an example, the first signaling is DCI.

[0720] As one embodiment, the first node receives a first signaling message, which indicates whether an operation has failed.

[0721] As one embodiment, the first node receives a first signaling message indicating a target identifier and an operation associated with the target identifier failing.

[0722] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0723] As an example, the first node determines for itself whether an operation has failed.

[0724] As an example, the advantages of the above method include: providing sufficient degrees of freedom for the first node, adapting to various different scenarios and terminals, and having adaptability and flexibility.

[0725] Generally, how the first node determines whether an operation has failed is determined by the hardware manufacturer. Below are some non-limiting implementation methods:

[0726] As an example, the first node determines whether an operation has failed by monitoring whether an operation has achieved a given performance target.

[0727] As an example, the first node determines whether the operation has achieved the given performance target by monitoring the reception quality of the signal or channel generated based on the output of an operation.

[0728] As a sub-example of the above embodiments, the output of an operation includes one or more precoding matrices, and the signal or channel generated based on the output of this operation refers to a signal or channel precoded by the one or more precoding matrices.

[0729] As a sub-example of the above embodiments, the output of an operation includes one or more beams, and the signal or channel generated based on the output of this operation refers to a signal or channel employing the one or more beams.

[0730] As a sub-example of the above embodiments, the output of an operation includes one or more CQIs, which are used to determine one or more MCS (Modulation and Coding Schemes). The signal or channel generated based on the output of this operation refers to the signal or channel using the one or more MCSs.

[0731] As an example, the output of an operation includes reliability, and the first node determines whether the operation has achieved the given performance target by the relationship between the reliability and a certain threshold.

[0732] As an example, the output of an operation includes confidence information, and the first node determines whether the operation has achieved the given performance target by the relationship between the confidence information and a certain threshold.

[0733] As an example, the first node determines whether an operation meets the given performance target by performing ML testing or ML simulation on a model of an operation.

[0734] As an example, the first node recovers the input of an operation based on the output of the operation, and then determines whether the operation has achieved the given performance target by comparing the recovered input with the actual input.

[0735] As an example, one operation corresponds to one timer, and the first node determines whether the operation has failed based on whether the timer has expired.

[0736] As an example, an operation failure includes: an operation needs to be retrained.

[0737] As an example, an operation failure includes: an operation requiring redeployment or reloading.

[0738] As an example, if an operation requires retraining, the operation is invalidated.

[0739] As an example, if an operation needs to be redeployed or reloaded, the operation fails.

[0740] As an example, if the first node is retrained for an operation, that operation becomes invalid.

[0741] As an example, if the first node redeploys or reloads an operation, that operation fails.

[0742] As an example, the first node determines for itself whether an operation needs to be retrained.

[0743] As an example, the first node determines for itself whether an operation needs to be redeployed or reloaded.

[0744] As an example, if an operation fails to achieve the expected performance or performance target, the operation is considered to have failed.

[0745] As an example, the first node determines that an operation has failed based on the fact that an operation cannot achieve the expected performance or performance target.

[0746] As an example, if the timer corresponding to an operation expires, the operation becomes invalid.

[0747] As an example, a timer is started or restarted after the training of the corresponding operation is completed.

[0748] As an example, a timer is started or restarted after the deployment of the corresponding operation is completed.

[0749] As an example, a timer is started or restarted after the most recent training of the corresponding operation is completed.

[0750] As an example, a timer is started or restarted after the most recent deployment of the corresponding operation has been completed.

[0751] As an example, a timer is started or restarted after the corresponding operation is performed.

[0752] As an example, a timer is started or restarted after each output of the corresponding operation.

[0753] As an example, when a start instruction for a timer is received, the first node starts or restarts the timer.

[0754] As an example, if an operation is not updated within a time window, the operation fails.

[0755] As an example, updating an operation includes updating the input of the operation.

[0756] As an example, updating an operation includes updating the output of the operation.

[0757] As an example, updating an operation includes updating the AI ​​model associated with the operation.

[0758] As an example, updating an operation includes updating the AI ​​model used in the operation.

[0759] As an example, different operations correspond to their respective time windows.

[0760] As an example, different operations correspond to the same time window.

[0761] As an example, the time windows corresponding to different operations are configured separately.

[0762] As an example, a producer of an operation indicates whether the operation can achieve the expected performance or performance target.

[0763] As an example, an operation fails if any other operation associated with it fails.

[0764] As an example, an operation fails if any other operation cascaded with it fails.

[0765] As an example, an operation fails if any other operation that has an input-output relationship with an operation fails.

[0766] As an example, an operation fails if any other operation that has a direct or indirect input-output relationship with an operation fails.

[0767] As an example, if any other operation associated with an operation fails, the first node determines whether the first operation has failed based on the failed operation.

[0768] As an example, if any other operation cascaded with an operation fails, the first node determines whether the first operation has failed based on the failed operation.

[0769] As an example, if any other operation that has an input-output relationship with an operation fails, the first node determines whether the operation has failed based on the failed operation.

[0770] As an example, if any other operation that has a direct or indirect input-output relationship with an operation fails, the first node determines whether the operation has failed based on the failed operation.

[0771] As an example, if any other operation associated with an operation fails, the first node determines whether the operation has failed based on the relationship between the operation and the failed operation.

[0772] As an example, if any other operation cascaded with an operation fails, the first node determines whether the operation has failed based on the relationship between the operation and the failed operation.

[0773] As an example, if any other operation that has an input-output relationship with an operation fails, the first node determines whether the operation has failed based on the relationship between the operation and the failed operation.

[0774] As an example, if any other operation that has a direct or indirect input-output relationship with an operation fails, the first node determines whether the first operation has failed based on the failed operation. The first node determines whether the first operation has failed based on the relationship between the first operation and the failed operation.

[0775] As an example, if one operation fails, all other operations that take the output of said operation as input also fail.

[0776] As an example, if one operation fails, all other operations that preceded that operation also fail.

[0777] As an example, if one operation fails, all other operations based on that one operation also fail.

[0778] As an example, if one operation fails, all other operations included in that operation also fail.

[0779] As an example, if one operation fails, all other operations associated with that operation also fail.

[0780] Example 6

[0781] Example 6 illustrates a schematic diagram of whether the first information reporting according to an embodiment of this application supports reverting to a non-AI generation method; as shown in Figure 6.

[0782] In Embodiment 6, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is the default, or the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method.

[0783] As an example, when the input of the first operation does not depend on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[0784] As an example, the advantages of the above method include reducing the implementation complexity of the system.

[0785] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0786] As an example, the advantages of the above method include: reducing the processing power requirements of the terminal and reducing the terminal's power consumption.

[0787] As an example, the advantages of the above method include: adapting to various different scenarios and terminals, and improving the adaptability and flexibility of the system.

[0788] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration may include a first higher-level parameter indicating whether the first information reporting supports a fallback to a non-AI generation method.

[0789] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first configuration includes a first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method: when the first configuration includes the first higher-level parameter, the first information reporting supports falling back to a non-AI generation method; when the first configuration does not include the first higher-level parameter, the first information reporting does not support falling back to a non-AI generation method.

[0790] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first configuration includes a first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method: when the first configuration includes the first higher-level parameter, the first information reporting does not support falling back to a non-AI generation method; when the first configuration does not include the first higher-level parameter, the first information reporting supports falling back to a non-AI generation method.

[0791] As an example, the advantages of the above method include: reducing system overhead and simplifying system design.

[0792] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports reverting to a non-AI generation method is a default option, including: the first information reporting supports reverting to a non-AI generation method.

[0793] As an example, the advantages of the above method include: supporting rollback to a non-AI method to replace the AI ​​method to complete a function, thereby improving the stability and robustness of the system.

[0794] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is by default included: the first information reporting does not support falling back to a non-AI generation method.

[0795] As an example, the advantages of the above method include: ensuring that specific functions are completed using AI, improving the accuracy of information reporting and the overall performance of the system.

[0796] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports reverting to a non-AI generation method is a default option, including whether the first information reporting supports reverting to a non-AI generation method depends on the terminal capability.

[0797] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is a default feature, including: the capability reporting of the first node indicating whether the first information reporting supports falling back to a non-AI generation method.

[0798] As an example, when the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is a default feature, including whether the capability reporting of the first node supports falling back to a non-AI generation method.

[0799] As an example, the advantages of the above method include: greater flexibility, adaptability to different terminals, and better forward compatibility.

[0800] Example 7

[0801] Example 7 illustrates a schematic diagram of whether the first information reporting according to another embodiment of this application supports reverting to a non-AI generation method; as shown in Figure 7.

[0802] In Embodiment 7, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is the default, or the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method.

[0803] As an example, when the input of the first operation depends on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[0804] As an example, the advantages of the above method include reducing the implementation complexity of the system.

[0805] As an example, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[0806] As an example, the advantages of the above method include: reducing the processing power requirements of the terminal and reducing the terminal's power consumption.

[0807] As an example, the advantages of the above method include: adapting to various different scenarios and terminals, and improving the adaptability and flexibility of the system.

[0808] As an example, when the input of the first operation depends on the output of another AI-based operation, the first configuration may include a second higher-level parameter indicating whether the first information reporting supports a fallback to a non-AI generation method.

[0809] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first configuration includes a second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method: when the first configuration includes the second higher-level parameter, the first information reporting supports falling back to a non-AI generation method; when the first configuration does not include the second higher-level parameter, the first information reporting does not support falling back to a non-AI generation method.

[0810] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first configuration includes a second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method: when the first configuration includes the second higher-level parameter, the first information reporting does not support falling back to a non-AI generation method; when the first configuration does not include the second higher-level parameter, the first information reporting supports falling back to a non-AI generation method.

[0811] As an example, the advantages of the above method include: reducing system overhead and simplifying system design.

[0812] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports reverting to a non-AI generation method is a default option, including: the first information reporting supports reverting to a non-AI generation method.

[0813] As an example, the advantages of the above method include: supporting joint processing of non-AI and AI methods, improving the flexibility and overall performance of the system.

[0814] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports reverting to a non-AI generation method is defined by default as follows: the first information reporting does not support reverting to a non-AI generation method.

[0815] As an example, the advantages of the above method include: ensuring the integrity of functions based on multiple AI operations, improving the accuracy of information reporting, and enhancing the overall performance of the system.

[0816] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports reverting to a non-AI generation method is a default option, including whether the first information reporting supports reverting to a non-AI generation method depends on the terminal capability.

[0817] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is a default feature, including: the capability reporting of the first node indicating whether the first information reporting supports falling back to a non-AI generation method.

[0818] As an example, when the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation method is a default feature, including whether the capability reporting of the first node supports falling back to a non-AI generation method.

[0819] As an example, the advantages of the above method include: greater flexibility, adaptability to different terminals, and better forward compatibility.

[0820] Example 8

[0821] Example 8 illustrates a schematic diagram of whether the first information reporting according to another embodiment of this application supports falling back to a non-AI generation method; as shown in Figure 8.

[0822] In embodiment 8, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0823] As an example, the first configuration includes at least one of a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports falling back to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[0824] As one embodiment, the first configuration includes both a first higher-level parameter and a second higher-level parameter.

[0825] As an example, the first configuration includes only one of the first higher-level parameters and the second higher-level parameters.

[0826] As one embodiment, the first configuration includes one of a first higher-level parameter and a second higher-level parameter; when the first configuration includes the first higher-level parameter, the input of the first operation does not depend on the output of another AI-based operation, and the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method; when the first configuration includes the second higher-level parameter, the input of the first operation depends on the output of another AI-based operation, and the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method.

[0827] As an example, the advantages of the above method include: reducing signaling overhead and simplifying system design.

[0828] As an example, whether the first configuration includes a first higher-level parameter and a second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method.

[0829] As one embodiment, the first configuration may include a first higher-level parameter and a second higher-level parameter to indicate whether the first information reporting supports reverting to a non-AI generation method: when the input of the first operation does not depend on the output of another AI-based operation, the first configuration may include a first higher-level parameter to indicate whether the first information reporting supports reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first configuration may include a second higher-level parameter to indicate whether the first information reporting supports reverting to a non-AI generation method.

[0830] As an example, the advantages of the above method include: simplifying system design.

[0831] As an example, the first higher-level parameter is a parameter of the layer above the physical layer.

[0832] As an example, the first higher-level parameter is a MAC layer parameter.

[0833] As an example, the first higher-level parameter is an RLC layer parameter.

[0834] As an example, the first higher-level parameter is an RRC layer parameter.

[0835] As one example, the second higher-level parameter is a parameter of the layer above the physical layer.

[0836] As an example, the second higher-level parameter is a MAC layer parameter.

[0837] As an example, the second higher-level parameter is an RLC layer parameter.

[0838] As an example, the second higher-level parameter is an RRC layer parameter.

[0839] As an example, the first higher-level parameter depends on the terminal's reporting capabilities.

[0840] As one example, the second higher-level parameter depends on the terminal's reporting capabilities.

[0841] As an example, the advantages of the above method include: greater flexibility, adaptability to different terminals, and better forward compatibility.

[0842] As an example, the first node determines the first higher-level parameter itself.

[0843] As an example, the first node determines the second higher-level parameter itself.

[0844] As an example, the advantages of the above method include: reducing the processing requirements and power consumption of the first node.

[0845] As one example, the first higher-level parameter and the second higher-level parameter are different.

[0846] As an example, the first higher-level parameter and the second higher-level parameter are of the same type.

[0847] As an example, the first higher-level parameter and the second higher-level parameter are of different types.

[0848] As an example, the advantages of the above method include: improving the flexibility of the system.

[0849] Example 9

[0850] Example 9 illustrates a schematic diagram of whether the first information reporting according to another embodiment of this application supports reverting to a non-AI generation method; as shown in Figure 9.

[0851] In Example 9, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports reverting to a non-AI generation method.

[0852] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support a fallback to a non-AI generation method.

[0853] As an example, the advantages of the above method include: ensuring that AI-based operations complete a specific function and improving the overall performance of the system.

[0854] As an example, when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports a fallback to a non-AI generation method.

[0855] As an example, the advantages of the above method include: supporting joint processing of non-AI and AI methods, improving the flexibility and overall performance of the system.

[0856] As an example, the fact that the first information reporting does not support rollback to a non-AI generation method includes: the first information reporting only supports AI-based generation methods, and the first information reporting depends on the output of the first operation.

[0857] As an example, the fact that the first information reporting does not support reverting to a non-AI generation method includes: the first information reporting depends on the output of the first operation.

[0858] As an example, the first information reporting not supporting rollback to a non-AI generation method includes: the first information reporting only supports AI-based generation methods, and the first information reporting depends on the output of the first operation; when the first condition is not met, the first node sends the first information report.

[0859] As an example, the fact that the first information reporting does not support rollback to a non-AI generation method includes: the first information reporting only supports AI-based generation methods, the first information reporting depends on the output of the first operation; when the first condition is met, the first node does not update the first information reporting.

[0860] As an example, the essence of the above method includes: not updating the reporting of invalid information.

[0861] As an example, the advantages of the above method include: reducing the computational resource overhead of the system.

[0862] As one embodiment, the fact that the first information reporting does not support rollback to a non-AI generation method includes: the first information reporting only supports AI-based generation methods, and the first information reporting depends on the output of the first operation; when the first condition is met, the first node abandons sending the first information reporting.

[0863] As an example, the essence of the above method includes: not sending failure information reports.

[0864] As an example, the advantages of the above method include: reducing system resource overhead and improving system transmission efficiency.

[0865] As an example, the first information reporting supports reverting to a non-AI generation method, which includes: under certain conditions, the first information reporting is generated in a non-AI generation method.

[0866] As one embodiment, the first information reporting supports reverting to a non-AI generation method, including: when the second condition is met, the first information reporting is generated in a non-AI generation method; when the second condition is not met, the first information reporting depends on the output of the first operation.

[0867] As an example, the advantages of the above method include: improving the flexibility of the system.

[0868] Example 10

[0869] Example 10 illustrates a schematic diagram of first information reporting according to an embodiment of this application; as shown in Figure 10.

[0870] In Example 10, the first node sends the first information report; wherein, when the first information report supports reverting to a non-AI generation method, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method; when the first information report does not support reverting to a non-AI generation method, the first information report depends on the output of the first operation.

[0871] As one embodiment, the first node sends the first information report; wherein, when the first information report supports reverting to a non-AI generation method, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method.

[0872] As one embodiment, the first node sends the first information report; wherein, when the first information report supports reverting to a non-AI generation method, the first information report depends on the output of the first operation.

[0873] As one embodiment, the first node sends the first information report; wherein, when the first information report supports reverting to a non-AI generation method, the first information report is generated in a reverted non-AI generation method.

[0874] As one embodiment, the first node sends the first information report; wherein, when the first information report does not support a fallback to a non-AI generation method, the first information report depends on the output of the first operation.

[0875] As an example, when the first information report supports reverting to a non-AI generation method, the first node sends the first information report.

[0876] As an example, when the first information report supports reverting to a non-AI generation method, the first node always updates the first information report and always sends the first information report.

[0877] As an example, when the first information report supports reverting to a non-AI generation method, the first node sends the first information report; wherein, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method depending on whether the second condition is met.

[0878] As an example, when the first information report supports reverting to a non-AI generation method, the first node sends the first information report; wherein, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method and depends on whether the first operation is invalid.

[0879] As an example, when the first information report supports reverting to a non-AI generation method, the first node sends the first information report; wherein, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method depending on whether the second condition is met: when the second condition is met, the first information report is generated by reverting to a non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[0880] As an example, when the first information report supports reverting to a non-AI generation method, the first node sends the first information report; wherein, the first information report depends on the output of the first operation, or the first information report is generated by reverting to a non-AI generation method depending on whether the first operation is invalid: when the first operation is invalid, the first information report is generated by reverting to a non-AI generation method; when the first operation is not invalid, the first information report depends on the output of the first operation.

[0881] As an example, the advantages of the above method include: supporting both AI-based and non-AI-based generation methods for information reporting.

[0882] As an example, the advantages of the above method include: improving the flexibility of the system.

[0883] As an example, the benefits of the above method include: improving the overall performance of the system.

[0884] As an example, when the first information reporting does not support a fallback to a non-AI generation method, whether the first node sends the first information reporting depends on whether the first condition is met.

[0885] As an example, when the first information reporting does not support falling back to the non-AI generation method, whether the first node sends the first information reporting depends on whether the first condition is met: when the first condition is met, the first node abandons sending the first information reporting; when the first condition is not met, the first node sends the first information reporting.

[0886] As an example, when the first information reporting does not support falling back to the non-AI generation method, whether the first node sends the first information reporting depends on whether the first condition is met: when the first condition is met, the first node abandons sending the first information reporting; when the first condition is not met, the first node sends the first information reporting, and the first information reporting depends on the output of the first operation.

[0887] As an example, when the first information reporting does not support a rollback to a non-AI generation method, whether the first node sends the first information reporting depends on whether the first operation fails.

[0888] As an example, when the first information reporting does not support a fallback to a non-AI generation method, whether the first node sends the first information reporting depends on whether the first operation fails: when the first operation fails, the first node abandons sending the first information reporting; when the first operation does not fail, the first node sends the first information reporting.

[0889] As an example, when the first information reporting does not support a fallback to a non-AI generation method, whether the first node sends the first information reporting depends on whether the first operation fails: when the first operation fails, the first node abandons sending the first information reporting; when the first operation does not fail, the first node sends the first information reporting, and the first information reporting depends on the output of the first operation.

[0890] As an example, the advantages of the above method include: not sending failure information reports, thus reducing system resource overhead.

[0891] As an example, the advantages of the above method include: improving the forward and backward compatibility of the system.

[0892] As an example, the benefits of the above method include: improving the overall performance of the system.

[0893] As an example, when the first information report does not support a fallback to a non-AI generation method, the first node always sends the first information report, and whether the first node updates the first information report depends on whether the first condition is met.

[0894] As an example, when the first information report does not support falling back to the non-AI generation method, the first node always sends the first information report. Whether the first node updates the first information report depends on whether the first condition is met: when the first condition is met, the first node does not update the first information report; when the first condition is not met, the first node updates the first information report.

[0895] As an example, when the first information report does not support rollback to a non-AI generation method, the first node always sends the first information report. Whether the first node updates the first information report depends on whether the first condition is met: when the first condition is met, the first node does not update the first information report; when the first condition is not met, the first node updates the first information report. The first information report depends on the output of the first operation.

[0896] As an example, when the first information report does not support a rollback to a non-AI generation method, the first node always sends the first information report, and whether the first node updates the first information report depends on whether the first operation fails.

[0897] As an example, when the first information report does not support rollback to a non-AI generation method, the first node always sends the first information report. Whether the first node updates the first information report depends on whether the first operation fails: when the first operation fails, the first node does not update the first information report; when the first operation does not fail, the first node updates the first information report.

[0898] As an example, when the first information report does not support rollback to a non-AI generation method, the first node always sends the first information report. Whether the first node updates the first information report depends on whether the first operation fails: when the first operation fails, the first node does not update the first information report; when the first operation does not fail, the first node updates the first information report. The first information report depends on the output of the first operation.

[0899] As an example, the advantages of the above method include: not updating the reporting of invalid information, and reducing the computational and measurement resource overhead of the system.

[0900] As an example, the advantages of the above method include: improving the forward and backward compatibility of the system.

[0901] As an example, the benefits of the above method include: improving the overall performance of the system.

[0902] Example 11

[0903] Example 11 illustrates a schematic diagram of the relationship between a first operation and a first reference operation according to an embodiment of this application, as shown in Figure 11. In Figure 11, the M configurations include configuration #1, configuration #2, ..., configuration #M.

[0904] In embodiment 11, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; the first configuration includes a first type of indication, which is used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, which depends on a second configuration, where the second configuration is one of the M configurations.

[0905] As an example, the first information set includes M configurations, where M is a positive integer greater than 1.

[0906] As an example, the M configurations each indicate M operations, and the first reference operation is one of the M operations.

[0907] As one embodiment, the first information set indicates M configurations, where the first configuration is one of the M configurations and M is a positive integer greater than 1; when the first configuration includes a first type of indication, the first type of indication in the first configuration is used to indicate a second configuration, the input of the first operation depends on the output of a first reference operation, the first reference operation depends on the second configuration, where the second configuration is one of the M configurations; when the first configuration does not include a first type of indication, the input of the first operation does not depend on the output of another AI-based operation.

[0908] As an example, the advantages of the above method include: enhancing the stability and integrity of the system.

[0909] As an example, the first type of indication is an identifier.

[0910] As an example, the first type of indication is an index.

[0911] As an example, the first type of indication is a non-negative integer.

[0912] As an example, the first type of indication includes one or more characters.

[0913] As an example, the first class indicator in the first configuration is different from the identifier in the first configuration.

[0914] As an example, the first type indication in the first configuration is not an identifier of the first configuration.

[0915] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to directly indicate the second configuration.

[0916] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to indirectly indicate the second configuration.

[0917] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to explicitly indicate the second configuration.

[0918] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to implicitly indicate the second configuration.

[0919] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to indicate a given configuration, and the first type of indication in the given configuration being used to indicate the second configuration; wherein, the given configuration is a configuration among the M configurations that is different from the first configuration and the second configuration.

[0920] As an example, the first type of indication in the first configuration is used to indicate the second configuration, including: the first type of indication in the first configuration is used to identify the second configuration.

[0921] As an example, the first type of indication in the first configuration is used to indicate that the second configuration includes: the first type of indication in the first configuration is used to associate the second configuration.

[0922] As an example, the first type of indication in the first configuration is used to indicate that the second configuration includes: the first type of indication in the first configuration is an identifier of the second configuration.

[0923] As an example, the first type of indication in the first configuration is used to indicate that the second configuration includes: the first type of indication in the first configuration is an index of the second configuration.

[0924] As one embodiment, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to indicate the identifier of the second configuration.

[0925] As an example, the first type of indication in the first configuration being used to indicate the second configuration includes: the first type of indication in the first configuration being used to indicate the index of the second configuration.

[0926] As an example, the first type of indication in the first configuration is used to indicate that the second configuration includes: the first type of indication in the first configuration is associated with an identifier of the second configuration.

[0927] As an example, the first type of indication in the first configuration is used to indicate that the second configuration includes: the first type of indication in the first configuration is associated with an index of the second configuration.

[0928] As an example, the first reference operation is based on training or AI.

[0929] As an example, the advantages of the above method include: supporting AI-based information reporting.

[0930] As an example, the first reference operation does not require deployment.

[0931] As an example, the first reference operation requires deployment.

[0932] As an example, the first node deploys the first reference operation.

[0933] As an example, the advantages include: providing sufficient degrees of freedom for the first node to adapt to various scenarios and terminals, thus exhibiting adaptability and flexibility.

[0934] As an example, the first reference operation is not obtained by loading.

[0935] As an example, the first reference operation is obtained by loading.

[0936] As an example, the advantages of the above method include reducing the processing power requirements and power consumption of the first node.

[0937] As an example, the training of the first reference operation is performed by the first node.

[0938] As an example, the training of the first reference operation is performed by the sender of the first information set.

[0939] As an example, the training of the first reference operation is performed by the core network.

[0940] As an example, the training of the first reference operation is performed by an AI training producer.

[0941] As an example, the training of the first reference operation is performed by the MDA (Management Data Analytics Function).

[0942] As an example, the training of the first reference operation is performed by the MDA function located at the first node.

[0943] As an example, the training of the first reference operation is performed by the MDA function of the sender located in the first information set.

[0944] As an example, the training of the first reference operation is performed by NWDAF (Network Data Analytics Function).

[0945] As an example, the training of the first reference operation is performed by the MDAS (Management Data Analytics Service) producer.

[0946] As an example, the training of the first reference operation is performed by the MnS (Management Service) producer.

[0947] As an example, the first operation and the first reference operation are jointly trained.

[0948] As an example, the advantages of the above method include: optimizing the first operation and the first reference operation.

[0949] As an example, the first operation and the first reference operation are trained separately.

[0950] As an example, the advantages of the above method include increased flexibility.

[0951] As one embodiment, the training of the first operation depends on the training result of the first reference operation, or the training of the first reference operation depends on the training result of the first operation.

[0952] As an example, the advantages of the above method include achieving a better balance between performance and flexibility.

[0953] As an example, the training of the first operation and the training of the first reference operation are independent.

[0954] As an example, the advantages of the above method include increased flexibility.

[0955] As an example, the first reference operation is used for an AI function.

[0956] As an example, the first reference operation is used for at least one of performance monitoring, positioning, beam management, CSI prediction, CSI estimation, CSI compression, RLF (radio link failure) prediction, cell handover prediction, or serving cell prediction.

[0957] As an example, the first operation and the first reference operation are performed jointly.

[0958] As an example, the advantages of the above method include: supporting the joint processing of multiple AI-based operations, thereby improving the overall performance of the system.

[0959] As an example, the first operation and the first reference operation are cascaded.

[0960] As an example, the first operation and the first reference operation are executed sequentially.

[0961] As an example, the advantages of the above method include: supporting multiple operations to cascade to complete a function, improving the accuracy of information reporting, and reducing the implementation complexity of the solution.

[0962] As an example, the first operation and the first reference operation are executed in parallel.

[0963] As an example, the benefits of the above method include: enhancing the robustness and stability of AI-based solutions.

[0964] As an example, the input of the first operation depends on the output of the first reference operation.

[0965] As one embodiment, the first reference operation depends on a second configuration including: the second configuration instructing the first reference operation.

[0966] As one embodiment, the first reference operation depends on a second configuration including: the second configuration indicating the index of the first reference operation.

[0967] As one embodiment, the first reference operation depends on a second configuration including: the second configuration includes an index of the first reference operation.

[0968] As one embodiment, the first reference operation depends on a second configuration, which includes configuration information for the first reference operation.

[0969] As one embodiment, the first reference operation depends on a second configuration, which is used to configure the first reference operation.

[0970] As one embodiment, the first reference operation depends on a second configuration, which includes identification information of the first reference operation.

[0971] As one embodiment, the first reference operation depends on a second configuration including: the second configuration indicates a first type identifier, the first type identifier being different from a first type indication, and the first reference operation being associated with the first type identifier in the second configuration.

[0972] As one embodiment, the first reference operation depends on a second configuration including: the second configuration includes a first type identifier, which is different from a first type indication, and the first reference operation is associated with the first type identifier in the second configuration.

[0973] As one embodiment, the first reference operation depends on a second configuration including: the second configuration indicates a first type identifier, the first type identifier being different from a first type indication, the first type identifier in the second configuration indicating the first reference operation.

[0974] As one embodiment, the first reference operation depends on a second configuration including: the second configuration includes a first type identifier, which is different from a first type indication, and the first type identifier in the second configuration indicates the first reference operation.

[0975] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of solution implementation.

[0976] As an example, the advantages of the above method include: improving system flexibility and adapting to different terminals and transmission environments.

[0977] As an example, the input to the first operation includes the output of the first reference operation.

[0978] As an example, the input to the first operation includes some or all of the output of the first reference operation.

[0979] As an example, the output of the first reference operation is used to obtain some or all of the input of the first operation.

[0980] As one embodiment, some or all of the output of the first reference operation is used as the input of the first operation.

[0981] As an example, the input to the first operation includes the post-processed output of the first reference operation.

[0982] As an example, the input to the first operation includes at least a portion of the post-processed output of the first reference operation.

[0983] As an example, at least a portion of the output of the first reference operation is post-processed and used as the input of the first operation.

[0984] As an example, the output of the first reference operation and the output of the first operation are different types of information.

[0985] As an example, the output of the first reference operation and the output of the first operation are two of the following: performance monitoring, positioning, beam management, CSI prediction, CSI estimation, CSI compression, RLF (radio link failure) prediction, cell handover prediction, and serving cell prediction.

[0986] As an example, the output of the first reference operation includes channel information, and the output of the first operation includes information other than channel information.

[0987] As an example, the output of the first reference operation includes channel information, and the output of the first operation includes at least one of performance monitoring results, RLF prediction, cell handover prediction, serving cell prediction, or location.

[0988] As an example, the output of the first reference operation includes beam information, and the output of the first operation includes at least one of predicted CSI, estimated CSI, or compressed CSI.

[0989] As an example, the output of the first reference operation includes predicted beam information or switched beam information, and the output of the first operation includes at least one of predicted CSI, estimated CSI, or compressed CSI.

[0990] As an example, the output of the first reference operation includes the predicted CSI, and the output of the first operation includes the compressed CSI obtained by compressing the predicted CSI.

[0991] As an example, the output of the first reference operation includes positioning information, and the output of the first operation includes channel information.

[0992] As an example, the output of the first reference operation includes positioning information, and the output of the first operation includes beam information.

[0993] As an example, the output of the first reference operation includes location information, and the output of the first operation includes at least one of predicted CSI, estimated CSI, or compressed CSI.

[0994] As an example, the output of the first reference operation includes location information, and the output of the first operation includes at least one of performance monitoring results, RLF prediction, cell handover prediction, or serving cell prediction.

[0995] Examples 12A-12B

[0996] Examples 12A-12B illustrate schematic diagrams of deploying a first given operation on a first node according to an embodiment of this application, as shown in Figures 12A-12B respectively.

[0997] In embodiment 12A, the first node requests the first producer to load a first given operation and obtains the first given operation from the first producer. The first given operation is the first operation in this application, the first reference operation, or one of the M operations.

[0998] As one example, the deployment includes obtaining the first given operation.

[0999] As one example, the deployment includes obtaining an AI entity.

[1000] As one example, the deployment includes obtaining an AI entity that performs the first given operation.

[1001] As one example, the deployment includes obtaining an AI entity that includes AI functionality to perform the first given operation.

[1002] As one example, the deployment includes loading the first given operation.

[1003] As one example, the deployment includes submitting a request to load the first given operation.

[1004] As an example, the first given operation is obtained from the serving cell of the first node.

[1005] As an example, the first given operation is loaded from the sustaining base station of the serving cell of the first node.

[1006] As an example, the first given operation is obtained from the core network.

[1007] As an example, the first given operation is obtained from loading from the first producer.

[1008] As an example, the deployment is accomplished by an AI function.

[1009] As an example, the deployment is accomplished by AI functionality deployed on the first node.

[1010] As an example, the deployment is accomplished by an AI deployment function.

[1011] As an example, the deployment is accomplished by the AI ​​deployment function deployed on the first node.

[1012] As an example, the deployment is accomplished using AI inference functionality.

[1013] As an example, the deployment is accomplished by an AI inference function deployed on the first node.

[1014] As an example, the deployment is performed by an AI entity.

[1015] As an example, the deployment is performed by an AI entity deployed on the first node.

[1016] As an example, the deployment is performed by an AI entity with a deployment function.

[1017] As an example, the deployment is performed by an AI entity with deployment capabilities deployed on the first node.

[1018] As an example, the deployment is performed by an AI entity with an inference function.

[1019] As an example, the deployment is performed by an AI entity with inference capabilities deployed on the first node.

[1020] As one embodiment, the deployment includes obtaining the first given operation from a first producer.

[1021] As one embodiment, the deployment includes making a request to the first producer to load the first given operation.

[1022] As one embodiment, the deployment includes loading the first given operation from the first producer.

[1023] As an example, the first producer generates and provides AL entities or AL functions.

[1024] As an example, the first producer is the producer of the first given operation.

[1025] As an example, the first producer includes at least one of the following: AL entity producer, AL function producer, AL deployment producer, AL loading producer, AL training producer, AL inference producer, AL entity deployment producer, AL entity loading producer, and MnS (Management Service) producer.

[1026] As an example, the training for obtaining the first given operation is performed by the first producer.

[1027] As an example, the executor used to obtain the training for the first given operation is different from the first producer.

[1028] In embodiment 12B, the first node requests the second producer to load a first given operation and obtains the first given operation from the first producer. The first given operation is the first operation in this application, the first reference operation, or one of the M operations.

[1029] As one example, the deployment includes obtaining the first given operation.

[1030] As one example, the deployment includes obtaining an AI entity or AI function that performs the first given operation.

[1031] As one example, the deployment includes loading the first given operation.

[1032] As one example, the deployment includes submitting a request to load the first given operation.

[1033] As an example, the deployment is accomplished by AI functionality deployed on the first node.

[1034] As an example, the deployment is accomplished by the AI ​​deployment function deployed on the first node.

[1035] As an example, the deployment is performed by an AI entity with a deployment function.

[1036] As one example, the second producer generates and provides AI entities or AI functions.

[1037] As one example, the second producer includes an MnS (Management Service) producer.

[1038] As an example, the second producer includes the producer of the AI ​​model training.

[1039] As one example, the second producer is the sender of the first information set.

[1040] As one example, the second producer is different from the sender of the first information set.

[1041] As one example, the second producer is the serving cell of the first node.

[1042] As one example, the second producer is the maintenance base station of the serving cell of the first node.

[1043] As one example, the second producer is the core network.

[1044] As an example, the first given operation is obtained from the serving cell of the first node.

[1045] As an example, the first given operation is loaded from the sustaining base station of the serving cell of the first node.

[1046] As an example, the first given operation is obtained from the core network.

[1047] As an example, the training for obtaining the first given operation is performed by the second producer.

[1048] As an example, the second producer is different from the first producer.

[1049] As an example, the first producer generates and provides AL entities or AL functions.

[1050] As an example, the first producer is the producer of the first given operation.

[1051] As an example, the first producer includes at least one of the following: AL entity producer, AL function producer, AL deployment producer, AL loading producer, AL training producer, AL inference producer, AL entity deployment producer, AL entity loading producer, and MnS (Management Service) producer.

[1052] Example 13

[1053] Example 13 illustrates a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment according to one embodiment of this application, as shown in Figure 13. The gNB in ​​Example 13 can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[1054] AI / ML related functions include ML training (also known as AI training, or AI / ML training), ML testing, and ML inference (also known as AI inference, or AI / ML inference), etc. ML training, ML testing, and ML inference functions can be deployed independently or co-located. Deployment of AI / ML related functions can be implemented through software, such as downloading and / or running executable files; or it can be implemented through a combination of software and hardware, such as accelerating specific computing units through hardware to improve computing speed or save power.

[1055] ML training functionality can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functionality for MDA (Management Data Analytics) can be deployed on MDAF (MDA Function); ML training for network data analytics can be deployed on NWDAF (Network Data Analytics Function), meaning the ML training functionality is an MTLF (Model Training Logical Function).

[1056] The ML inference function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML inference function is MDAF, or the ML inference function is AnLF (Analytics logical function) located in NWDAF.

[1057] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[1058] In Example 13, the RAN domain ML training function 1302 is located in the RAN domain management function 1303; while the ML inference function is located in the base station, that is, the AI / ML inference function 1304 is located in gNB 1305, and the AI / ML inference function 1306 is located in gNB 1307.

[1059] In Figure 13, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1303, that is, data interaction with RAN domain MnS (Management Service) consumer / cross-domain management 1301 (as shown by the dashed arrow in Figure 13).

[1060] Optionally, the management of ML inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1301.

[1061] It should be noted that Embodiment 13 is merely a non-limiting implementation method; optionally, the ML training function of the RAN domain may also be deployed in the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[1062] As an example, one of the gNBs (or base stations) in Example 13 is the second node of this application.

[1063] As an example, the second processor in this application includes an AL / ML inference function, namely 1304 or 1306, as shown in Figure 13.

[1064] Example 14

[1065] Example 14 illustrates a schematic diagram of the deployment of AI / ML functionality in a UE according to one embodiment of this application; as shown in Figure 14. The RAN domain ML training function 1405 in Figure 14 is optional.

[1066] UE function 1404 is deployed in the first node of this application, and the UE function 1404 includes AI / ML inference function 1406; the AI / ML inference function 1406 uses an ML model (also known as an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[1067] As an example, the first information report in this application is obtained through inference by the AI / ML inference function 1406.

[1068] As an example, the first processor in this application includes an AL / ML inference function 1406 in Figure 14.

[1069] As an example, the UE function 1404 includes a RAN domain ML training function 1405, which runs training data through an ML model to obtain a relevant loss and adjusts the parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[1070] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capabilities of the UE side.

[1071] Optionally, the UE function 1404 also includes a CN domain ML training function (not shown in Figure 14).

[1072] Optionally, the UE function 1404 also includes an AI / ML deployment function (not shown in Figure 14) for loading ML models and data.

[1073] As an example, the first node indicates whether it supports ML training function (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[1074] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[1075] Optionally, the UE function 1404 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1401, and / or the RAN domain MnF 1402, and / or the cross-domain management system 1403 for management or analysis (as shown by double arrow 1407).

[1076] Optionally, the UE function 1404 is an MnS consumer that loads data from the CN domain MnF (Management Function) 1401, and / or the RAN domain MnF 1402, and / or the cross-domain management system 1403 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1407).

[1077] As an example, the ML model is based on a neural network.

[1078] As an example, the ML model is based on CNN (Conventional Neural Networks).

[1079] As an example, the ML model is based on the Transformer architecture.

[1080] Example 15

[1081] Example 15 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 15. Figure 15(a) includes a third processor, a fourth processor, and a fifth processor, and Figure 15(b) includes a third processor, a fourth processor, a fifth processor, and a sixth processor.

[1082] In Example 15(a), the third processor sends a first dataset to the fourth processor and a second dataset to the fifth processor; the fourth processor generates a target first-type parameter set based on the first dataset, and sends the generated target first-type parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-type parameter set to obtain a first-type output. In Figure 15(a), the first-type feedback is optional.

[1083] In Example 15(b), the third processor sends a first dataset to the fourth processor and a second dataset to the fifth processor; the fourth processor generates a target first-type parameter set based on the first dataset, and sends the generated target first-type parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-type parameter set to obtain a first-type output, and sends the first-type output to the sixth processor. In Figure 15(b), the first-type feedback and the second-type feedback are optional.

[1084] As an example, in Figure 15(a), the fifth processor sends the first type of output to the second node in this application.

[1085] As an example, the fifth processor performs the first operation in this application.

[1086] As an example, the fifth processor performs the first reference operation in this application.

[1087] As an example, the fifth processor sends a first type of feedback to the fourth processor, and the first type of feedback is used to trigger a recalculation or update of the target first type of parameter group.

[1088] As one embodiment, the sixth processor sends a second type of feedback to the third processor, the second type of feedback being used to generate the first dataset or the second dataset, or the second type of feedback being used to trigger the sending of the first dataset or the second dataset.

[1089] As one embodiment, the third processor generates the first dataset and the second dataset based on measurements of a first type of wireless signal, the first type of wireless signal including downlink RS.

[1090] As one embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[1091] As an example, the first information report belongs to the first type of output.

[1092] As an example, the second dataset includes the input of the first operation.

[1093] As an example, the second dataset includes the input of the first reference operation.

[1094] As an example, for the first operation in this application, the second dataset includes information obtained based on the first configuration.

[1095] As an example, for the first operation in this application, the second dataset includes information obtained based on the first configuration and information obtained based on the output of the first reference operation.

[1096] As an example, for the first reference operation in this application, the second dataset includes information obtained based on the second configuration.

[1097] As an example, the first dataset includes training data.

[1098] As an example, the fourth processor belongs to the producer of the first operation.

[1099] As one embodiment, the fourth processor belongs to the producer of the first reference operation.

[1100] As one embodiment, the fourth processor includes an AI training producer.

[1101] As one embodiment, the fourth processor includes an AI training function.

[1102] As an example, the fourth processor is used for model training, and the trained model is described by the target first class of parameter sets.

[1103] As an example, the fourth processor belongs to the first node.

[1104] As an example, the advantages of the above method include avoiding passing the first dataset to the second node.

[1105] As one example, the fourth processor belongs to the second node.

[1106] As an example, the advantages of the above method include: supporting joint training and optimizing system performance.

[1107] As an example, the fourth processor belongs to the core network.

[1108] As an example, the advantages of the above method include: supporting joint training across the entire network and further optimizing system performance.

[1109] As an example, the second dataset includes inference data.

[1110] As one embodiment, the fifth processor includes an AI inference producer.

[1111] As one embodiment, the fifth processor includes an AI inference function.

[1112] As an example, the fifth processor belongs to the first node.

[1113] As an example, the fifth processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[1114] As an example, the first operation is described by the target first type of parameter group.

[1115] As an example, the first reference operation is described by the target first type of parameter group.

[1116] As an example, the target first type of parameter group is used to construct the first operation.

[1117] As an example, the target first type of parameter group is used to construct the first reference operation.

[1118] As an example, the fifth processor generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[1119] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the fourth processing opportunity recalculates the target first type of parameter set.

[1120] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[1121] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[1122] As an example, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of pooling function, or parameters of activation function.

[1123] Example 16

[1124] Example 16 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 16. Figure 16 includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation. In Figure 16, the arrowed lines indicate the sequence of processes.

[1125] In Example 16, the third and fourth operations belong to the first stage, the fifth operation belongs to the second stage, the sixth operation belongs to the third stage, and the seventh operation belongs to the fourth stage.

[1126] As an example, the third operation includes AI training, the fourth operation includes AI testing, the fifth operation includes AI emulation, the sixth operation includes AI entity loading, and the seventh operation includes AI inference.

[1127] As an example, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an emulation phase.

[1128] As an example, the first stage includes AI model training.

[1129] As an example, the first stage includes AI model training and AI testing.

[1130] As an example, the AI ​​includes machine learning (ML) inference.

[1131] As an example, the AI ​​model training includes initial training and re-training of one or a group of AI entities.

[1132] As an example, the training of the AI ​​model depends on training data.

[1133] As an example, the AI ​​model training includes AI entity validation.

[1134] As an example, the AI ​​entity verification is used to evaluate the performance of the AI ​​entity.

[1135] As an example, the AI ​​entity verification relies on verification data.

[1136] As an example, if the AI ​​entity verification results do not meet expectations, the AI ​​model will be retrained.

[1137] As an example, the AI ​​testing includes testing the validated AI entity to estimate the performance of the trained AI model.

[1138] As an example, if the AI ​​test results meet expectations, the AI ​​entity proceeds to the next stage; otherwise, the AI ​​model will be retrained.

[1139] As an example, the AI ​​test relies on test data.

[1140] As an example, the second stage includes AI simulation, which performs inference of AI entities in a simulation environment.

[1141] As an example, the AI ​​simulation estimates the performance of AI entity inference in a simulation environment before using the AI ​​entity.

[1142] As one embodiment, the second stage is optional.

[1143] As an example, the third stage includes AI entity loading, which is to obtain trained AI entities to obtain the desired AI inference capabilities.

[1144] As an example, the third stage is optional.

[1145] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[1146] As an example, the fourth stage includes AI inference.

[1147] As an example, the seventh operation includes the first operation.

[1148] As an example, the seventh operation includes the first reference operation.

[1149] Example 17

[1150] Example 17 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application; as shown in Figure 17. In Figure 17, the processing apparatus 1700 in the first node includes a first processor 1701.

[1151] The first processor 1701 receives the first information set;

[1152] In embodiment 17, the first information set indicates a first configuration, which is used to configure the first information reporting; the first information reporting depends on the output of a first operation, or the first information reporting is generated by falling back to a non-AI generation method; the first configuration indicates the first operation, which is AI-based; whether the first information reporting supports falling back to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[1153] As an example, when the input of the first operation does not depend on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[1154] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[1155] As an example, when the input of the first operation depends on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[1156] As an example, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[1157] As one embodiment, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[1158] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports reverting to a non-AI generation method.

[1159] As one embodiment, the first processor 1701 sends the first information report;

[1160] Specifically, when the first information reporting supports reverting to a non-AI generation method, the first information reporting depends on the output of the first operation, or the first information reporting is generated by reverting to a non-AI generation method; when the first information reporting does not support reverting to a non-AI generation method, the first information reporting depends on the output of the first operation.

[1161] As an example, the first information report supports reverting to a non-AI generation method; when the second condition is met, the first information report is generated in a non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[1162] As an example, when the first information report supports reverting to a non-AI generation method, the first processor 1701 sends the first information report; when the second condition is met, the first information report is generated in a reverted non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[1163] As an example, the first processor 1701 does not update the first information report when the first condition is met; wherein, the first information report does not support rollback to a non-AI generation method.

[1164] As one embodiment, the first processor 1701 abandons sending the first information report when the first condition is met; wherein, the first information report does not support rollback to a non-AI generation method.

[1165] As an example, when the first information report does not support falling back to a non-AI generation method, the first processor 1701 always sends the first information report; when the first condition is met, the first node does not update the first information report; when the first condition is not met, the first node updates the first information report.

[1166] As an example, when the first information reporting does not support falling back to a non-AI generation method, whether the first processor 1701 sends the first information reporting depends on whether the first condition is met: when the first condition is met, the first node abandons sending the first information reporting; when the first condition is not met, the first node sends the first information reporting, and the first information reporting depends on the output of the first operation.

[1167] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations, and M is a positive integer greater than 1; the first configuration includes a first type of indication, which is used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, which depends on a second configuration, where the second configuration is one of the M configurations.

[1168] As an example, the first node determines on its own that the first operation has failed.

[1169] As an example, the first processor 1701 receives a first signaling, which indicates whether the first operation has failed.

[1170] As an example, the first operation is based on training or AI.

[1171] As an example, the first reference operation is based on training or AI.

[1172] As an example, the first operation does not require deployment.

[1173] As an example, the first reference operation does not require deployment.

[1174] As an example, the first processor 1701 deploys the first operation.

[1175] As an example, the first processor 1701 deploys the first reference operation.

[1176] As an example, the first operation is obtained by loading.

[1177] As an example, the first reference operation is obtained by loading.

[1178] As one example, the first node is a user equipment.

[1179] As one example, the user equipment is a terminal.

[1180] As one example, the first node is a terminal.

[1181] As an example, the first node is a relay node device.

[1182] As an example, the first processor 1701 includes at least one of the following in embodiment 4: {antenna 452, receiver / transmitter 454, receiving processor 456, transmitting processor 468, multi-antenna receiving processor 458, multi-antenna transmitting processor 457, controller / processor 459, memory 460, data source 467}.

[1183] Example 18

[1184] Example 18 illustrates a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application; as shown in Figure 18. In Figure 18, the processing apparatus 1800 in the second node includes a second processor 1801.

[1185] The second processor 1801 sends the first information set;

[1186] In embodiment 18, the first information set indicates a first configuration, which is used to configure the first information reporting; the first information reporting depends on the output of a first operation, or the first information reporting is generated by falling back to a non-AI generation method; the first configuration indicates the first operation, which is AI-based; whether the first information reporting supports falling back to a non-AI generation method depends on whether the input of the first operation depends on the output of another AI-based operation.

[1187] As an example, when the input of the first operation does not depend on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[1188] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first configuration includes a first higher-level parameter and the first higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[1189] As an example, when the input of the first operation depends on the output of another AI-based operation, it is the default to whether the first information reporting supports falling back to a non-AI generation method.

[1190] As an example, when the input of the first operation depends on the output of another AI-based operation, the first configuration includes a second higher-level parameter and the second higher-level parameter indicates whether the first information reporting supports a fallback to a non-AI generation method.

[1191] As one embodiment, the first configuration includes a first higher-level parameter and a second higher-level parameter; the first higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation does not depend on the output of another AI-based operation; the second higher-level parameter indicates whether the first information reporting supports reverting to a non-AI generation method when the input of the first operation depends on the output of another AI-based operation.

[1192] As an example, when the input of the first operation does not depend on the output of another AI-based operation, the first information reporting does not support reverting to a non-AI generation method; when the input of the first operation depends on the output of another AI-based operation, the first information reporting supports reverting to a non-AI generation method.

[1193] As one embodiment, the target recipient of the first information set sends the first information report;

[1194] Specifically, when the first information reporting supports reverting to a non-AI generation method, the first information reporting depends on the output of the first operation, or the first information reporting is generated by reverting to a non-AI generation method; when the first information reporting does not support reverting to a non-AI generation method, the first information reporting depends on the output of the first operation.

[1195] As an example, the first information report supports reverting to a non-AI generation method; when the second condition is met, the first information report is generated in a non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[1196] As an example, when the first information report supports reverting to a non-AI generation method, the target recipient of the first information set sends the first information report; when the second condition is met, the first information report is generated in a reverted non-AI generation method; when the second condition is not met, the first information report depends on the output of the first operation.

[1197] As an example, the target recipient of the first information set does not update the first information report when the first condition is met; wherein, the first information report does not support rollback to a non-AI generation method.

[1198] As an example, the target recipient of the first information set abandons sending the first information report when the first condition is met; wherein, the first information report does not support rollback to a non-AI generation method.

[1199] As an example, when the first information report does not support falling back to a non-AI generation method, the target receiver of the first information set always sends the first information report; when the first condition is met, the target receiver of the first information set does not update the first information report; when the first condition is not met, the target receiver of the first information set updates the first information report.

[1200] As an example, when the first information report does not support falling back to a non-AI generation method, whether the target receiver of the first information set sends the first information report depends on whether the first condition is met: when the first condition is met, the target receiver of the first information set abandons sending the first information report; when the first condition is not met, the target receiver of the first information set sends the first information report, and the first information report depends on the output of the first operation.

[1201] As an example, the first information set indicates M configurations, where the first configuration is one of the M configurations, and M is a positive integer greater than 1; the first configuration includes a first type of indication, which is used to indicate a second configuration; the input of the first operation depends on the output of a first reference operation, which depends on a second configuration, where the second configuration is one of the M configurations.

[1202] As an example, the target recipient of the first information set determines that the first operation has failed.

[1203] As an example, the second processor 1801 sends a first signaling, which indicates whether the first operation has failed.

[1204] As one embodiment, the second node monitors whether the first information report is sent by the target recipient of the first information set.

[1205] As one embodiment, the second node determines on its own whether to give up receiving the first information report.

[1206] As one embodiment, the second processor 1801 receives the first information report.

[1207] As one embodiment, the second processor 1801 abandons receiving the first information report.

[1208] As an example, the first operation is based on training or AI.

[1209] As an example, the first reference operation is based on training or AI.

[1210] As an example, the first operation does not require deployment.

[1211] As an example, the first reference operation does not require deployment.

[1212] As an example, the target recipient of the first information set deploys the first operation.

[1213] As an example, the target recipient of the first information set deploys the first reference operation.

[1214] As an example, the first operation is obtained by loading.

[1215] As an example, the first reference operation is obtained by loading.

[1216] In one embodiment, the second node is a base station.

[1217] In one embodiment, the second node is a user equipment.

[1218] As one example, the user equipment is a terminal.

[1219] In one embodiment, the second node is a terminal.

[1220] As one embodiment, the second node is a relay node device.

[1221] As one embodiment, the second processor 1801 includes at least one of the following in embodiment 4: {antenna 420, receiver / transmitter 418, receiver processor 470, transmitter processor 416, multi-antenna receiver processor 472, multi-antenna transmitter processor 471, controller / processor 475, memory 476}.

[1222] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication equipment, vehicles, RSUs, wireless sensors, internet access cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet access cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base stations or system equipment in this application include, but are not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNBs, gNBs, TRPs (Transmitter Receiver Points), GNSS, relay satellites, satellite base stations, airborne base stations, RSUs (Road Side Units), drones, and testing equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[1223] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A method in a first node for wireless communication, characterized by, The method comprises: receiving a first information set; the first information set indicates a first configuration, the first configuration is used for configuring a first information reporting; the first information reporting depends on an output of a first operation, or the first information reporting is generated by falling back to a non-AI generation mode; wherein the first configuration indicates the first operation, the first operation is based on AI; whether the first information reporting supports falling back to a non-AI generation mode depends on whether an input of the first operation depends on an output of another AI-based operation.

2. The method of claim 1, wherein, When the input of the first operation does not depend on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation mode is default, or the first configuration includes a first higher-layer parameter and the first higher-layer parameter indicates whether the first information reporting supports falling back to a non-AI generation mode.

3. The method according to claim 1 or 2, characterized in that, When the input of the first operation depends on the output of another AI-based operation, whether the first information reporting supports falling back to a non-AI generation mode is default, or the first configuration includes a second higher-layer parameter and the second higher-layer parameter indicates whether the first information reporting supports falling back to a non-AI generation mode.

4. The method according to any one of claims 1 to 3, characterized in that, The method comprises: sending the first information set; wherein, when the first information reporting supports falling back to a non-AI generation mode, the first information reporting depends on an output of a first operation, or the first information reporting is generated by falling back to a non-AI generation mode; when the first information reporting does not support falling back to a non-AI generation mode, the first information reporting depends on an output of a first operation.

5. The method according to any one of claims 1 to 4, characterized in that, The first information reporting supports falling back to a non-AI generation mode; when a second condition is met, the first information reporting is generated by falling back to a non-AI generation mode; when the second condition is not met, the first information reporting depends on an output of the first operation.

6. The method according to any one of claims 1 to 5, characterized in that, The method comprises: when a first condition is met, not updating the first information reporting; wherein the first information reporting does not support falling back to a non-AI generation mode.

7. The method according to any one of claims 1 to 5, characterized in that, The method comprises: when a first condition is met, abandoning sending the first information reporting; wherein the first information reporting does not support falling back to a non-AI generation mode.

8. The method according to any one of claims 1 to 7, characterized in that, The first information set indicates M configurations, the first configuration is one of the M configurations, M is a positive integer greater than 1; the first configuration includes a first type of indication, the first type of indication in the first configuration is used to indicate a second configuration; an input of the first operation depends on an output of a first reference operation, the first reference operation depends on a second configuration, the second configuration is one of the M configurations.

9. A terminal, characterized by comprising: The terminal comprises one or more processors and a memory; the memory is coupled with the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, the one or more processors invoke the computer instructions to enable the terminal to perform the method of any one of claims 1-8.

10. A method in a second node for wireless communication, the method comprising: The method comprises: sending a first information set; The first information set indicates a first configuration, and the first configuration is used for configuring a first information reporting; The first information reporting depends on an output of a first operation, or the first information reporting is generated by fallback to a non-AI generation manner. The first configuration indicates the first operation, and the first operation is based on AI; whether the first information reporting supports fallback to a non-AI generation manner depends on whether an input of the first operation depends on an output of another operation based on AI.

11. The method of claim 10, wherein, When the input of the first operation does not depend on the output of the another operation based on AI, whether the first information reporting supports fallback to the non-AI generation manner is default, or the first configuration includes a first higher-layer parameter and the first higher-layer parameter indicates whether the first information reporting supports fallback to the non-AI generation manner.

12. The method according to claim 10 or 11, characterized in that, When the input of the first operation depends on the output of the another operation based on AI, whether the first information reporting supports fallback to the non-AI generation manner is default, or the first configuration includes a second higher-layer parameter and the second higher-layer parameter indicates whether the first information reporting supports fallback to the non-AI generation manner.

13. The method according to any one of claims 10 to 12, characterized in that, comprising: receiving or giving up receiving the first information reporting; When the first information reporting supports fallback to the non-AI generation manner, the first information reporting depends on the output of the first operation, or the first information reporting is generated by fallback to the non-AI generation manner; when the first information reporting does not support fallback to the non-AI generation manner, the first information reporting depends on the output of the first operation.

14. The method according to any one of claims 10 to 13, characterized in that, The first information reporting supports fallback to the non-AI generation manner; when a second condition is met, the first information reporting is generated by fallback to the non-AI generation manner; when the second condition is not met, the first information reporting depends on the output of the first operation.

15. The method according to any one of claims 10 to 14, characterized in that, comprising: When a first condition is met, the target receiver of the first information set does not update the first information reporting; The first information reporting does not support fallback to the non-AI generation manner.

16. The method of any one of claims 10 to 14, wherein, comprising: When a first condition is met, the target receiver of the first information set gives up sending the first information reporting; The first information reporting does not support fallback to the non-AI generation manner.

17. The method of any one of claims 10 to 16, wherein, The first information set indicates M configurations, the first configuration is one of the M configurations, M is a positive integer greater than 1; the first configuration includes a first type of indication, and the first type of indication in the first configuration is used to indicate a second configuration; an input of the first operation depends on an output of a first reference operation, and the first reference operation depends on the second configuration, and the second configuration is one of the M configurations.

18. A base station, comprising: The base station comprises one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is configured to store computer program code, the computer program code comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the base station to perform the method according to any one of claims 10-17.

Images