CSI reporting method and apparatus in node used for wireless communication

Abstract

Disclosed in the present application are a CSI reporting method and apparatus in a node used for wireless communication. The method comprises: a first node receiving a target CSI reporting configuration, wherein the target CSI reporting configuration is used for configuring the reporting of target CSI, and a generation mode of the target CSI is training-based or AI-based; sending a target information block; determining whether to abandon sending the target CSI; and when a first condition is satisfied, abandoning sending the target CSI, wherein determining whether to abandon sending the target CSI depends on whether the first condition is satisfied, the first condition comprises the generation mode of the target CSI being associated with a target identifier, and the target identifier depends on the target information block. The method and apparatus support AI-based CSI reporting and determine whether to send or abandon sending CSI reporting, thereby reducing the resource overheads of a system and improving the overall performance of the system.

Description

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

[0001] This application claims priority to Chinese Patent Application No. 202410825116.2, filed on June 21, 2024, entitled "A Method and Apparatus for CSI 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 CSI (Channel State 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 architecture and deployment requirements. 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, comprising:

[0008] Receive target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI.

[0009] Send the target information block; determine whether to abandon sending the target CSI; when the first condition is met, abandon sending the target CSI;

[0010] The determination of whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; the target identifier depends on the target information block.

[0011] As an example, the AI ​​(Artificial Intelligence) includes ML (Machine Learning).

[0012] As an example, the problem this application aims to solve includes: how to determine whether to send or abandon sending CSI reports.

[0013] As an example, the essence of the above method includes: whether to abandon sending CSI reports depends on whether a first condition is met; when the first condition is met, the sending of CSI reports is abandoned.

[0014] As an example, the essence of the above method includes: when the AI-based CSI generation method is associated with the target identifier, the sending of CSI reports is abandoned.

[0015] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0016] As an example, the advantages of the above method include ensuring consistency in the understanding of CSI reports by the transmitting and receiving ends.

[0017] As an example, the benefits of the above method include improving the accuracy and effectiveness of CSI reporting.

[0018] As an example, the advantages of the above method include: reducing the overhead of CSI reporting and improving system efficiency.

[0019] As an example, the advantages of the above method include: simplifying system design and reducing solution complexity.

[0020] As an example, the benefits of the above method include: enhancing the flexibility and robustness of the system, and better adapting to various transmission conditions and application scenarios.

[0021] As an example, the benefits of the above method include: improving the overall performance of the system.

[0022] According to one aspect of this application, the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set including one or more RS resources; the target CSI indicates at least one resource in a second resource set, the second resource set including resources not belonging to the first resource set.

[0023] As an example, the advantages of the above method include reducing the overhead required to obtain the target CSI.

[0024] As an example, the advantages of the above method include reducing the measurement resources required to obtain the target CSI.

[0025] As an example, the benefits of the above method include: enhancing system flexibility and improving overall system performance.

[0026] According to one aspect of this application, the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurements or interference resource measurements of the target CSI, the first resource set including one or more RS resources; the generation of the target CSI includes performing a first operation, the input of the first operation depending on measurements based on the first resource set, the target CSI depending on the output of the first operation.

[0027] As an example, the first operation is based on training or AI.

[0028] As an example, the advantages of the above method include: supporting AI / ML-based CSI reporting.

[0029] As an example, the benefits of the above method include improving the accuracy and effectiveness of CSI reporting.

[0030] As an example, the benefits of the above method include: improving the overall performance of the system.

[0031] According to one aspect of this application, the generation method of the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

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

[0033] As an example, the benefits of the above method include: enhancing system flexibility and improving overall system performance.

[0034] According to one aspect of this application, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

[0035] As an example, the advantages of the above method include: minimal changes to existing standards and system design, and improved forward and backward compatibility of the system.

[0036] As an example, the benefits of the above method include: enhanced system flexibility and robustness.

[0037] According to one aspect of this application, the target information block indicates the target identifier.

[0038] As an example, the essence of the above method includes: the determination of the target identifier depends on the target information block.

[0039] As an example, the advantages of the above method include: the target information block is adaptable to various transmission scenarios and applications, improving the flexibility of the system.

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

[0041] According to one aspect of this application, it includes:

[0042] Receive at least one information block, wherein the at least one information block configures or indicates at least one signal;

[0043] The target information block is generated based on the reception or measurement of some or all of the signals in the at least one signal.

[0044] As an example, the essence of the above method includes: the target information block carries information about the reception or measurement of the first node signal.

[0045] As an example, the essence of the above method includes: the target identification depends on the reception or measurement of some or all of the signals in the at least one signal.

[0046] As an example, the advantages of the above method include: compatibility with existing system designs and standards, and improved forward and backward compatibility of the system.

[0047] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of implementation.

[0048] As an example, the benefits of the above method include: improved system flexibility and overall performance.

[0049] According to one aspect of this application, the target identifier depends on the at least one information block.

[0050] As an example, the advantages of the above method include: the at least one information block is adaptable to various transmission scenarios and applications, improving the flexibility of the system.

[0051] As an example, the advantages of the above method include: establishing the inherent connections within the system, simplifying the system design, and reducing the complexity of the solution implementation.

[0052] According to one aspect of this application, a first value is greater than a first threshold, the first value depending on the target information block.

[0053] As an example, the essence of the above method includes: introducing a first value and a first threshold, and establishing their association with the target information block.

[0054] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of implementation.

[0055] As an example, the benefits of the above method include: improved system flexibility and overall performance.

[0056] According to one aspect of this application, the triggering condition for the target information block includes a first value greater than a first threshold;

[0057] in,

[0058] The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer;

[0059] or,

[0060] The first value depends on the reception or measurement of some or all of the at least one signal.

[0061] As an example, the essence of the above method includes: the target information block may be triggered only when the first value is greater than the first threshold.

[0062] As an example, the essence of the above method includes: the first value and the first threshold may have different meanings and implementations in different scenarios and applications.

[0063] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of implementation.

[0064] As an example, the advantages of the above method include: enhancing the flexibility and robustness of the system, adapting to different transmission scenarios and applications.

[0065] As an example, the benefits of the above method include: improving the overall performance of the system.

[0066] As one example, the first node is a terminal.

[0067] This application discloses a method used in a second node for wireless communication, comprising:

[0068] Send target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI.

[0069] Receive target information block; determine whether to abandon receiving the target CSI; when the first condition is met, abandon receiving the target CSI;

[0070] Specifically, the target receiver configured to report the target CSI determines whether to abandon sending the target CSI; when a first condition is met, the target receiver configured to report the target CSI abandons sending the target CSI; the determination of whether to abandon sending the target CSI by the target receiver configured to report the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; the target identifier depends on the target information block.

[0071] According to one aspect of this application, the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set including one or more RS resources; the target CSI indicates at least one resource in a second resource set, the second resource set including resources not belonging to the first resource set.

[0072] According to one aspect of this application, the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurements or interference resource measurements of the target CSI, the first resource set including one or more RS resources; the generation of the target CSI includes performing a first operation, the input of the first operation depending on measurements based on the first resource set, the target CSI depending on the output of the first operation.

[0073] According to one aspect of this application, the generation method of the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

[0074] According to one aspect of this application, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

[0075] According to one aspect of this application, the target information block indicates the target identifier.

[0076] According to one aspect of this application, it includes:

[0077] Send at least one information block, wherein the at least one information block configures or indicates at least one signal;

[0078] The target information block is generated based on the reception or measurement of some or all of the signals in the at least one signal.

[0079] According to one aspect of this application, the target identifier depends on the at least one information block.

[0080] According to one aspect of this application, a first value is greater than a first threshold, the first value depending on the target information block.

[0081] According to one aspect of this application, the triggering condition for the target information block includes a first value greater than a first threshold;

[0082] in,

[0083] The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer;

[0084] or,

[0085] The first value depends on the reception or measurement of some or all of the at least one signal.

[0086] This application discloses a terminal, which includes: one or more processors and a memory;

[0087] 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.

[0088] As one example, the terminal is a user equipment.

[0089] This application discloses a base station, which includes: one or more processors and a memory;

[0090] 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.

[0091] This application discloses a first node used for wireless communication, comprising:

[0092] The first receiver receives the target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI.

[0093] The first processor sends a target information block; determines whether to abandon sending the target CSI; when the first condition is met, it abandons sending the target CSI.

[0094] The determination of whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; the target identifier depends on the target information block.

[0095] This application discloses a second node used for wireless communication, comprising:

[0096] The second processor sends a target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI; receives target information blocks; determines whether to abandon receiving the target CSIs; when a first condition is met, it abandons receiving the target CSIs.

[0097] Specifically, the target receiver configured to report the target CSI determines whether to abandon sending the target CSI; when a first condition is met, the target receiver configured to report the target CSI abandons sending the target CSI; the determination of whether to abandon sending the target CSI by the target receiver configured to report the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; the target identifier depends on the target information block.

[0098] As an example, compared with conventional solutions, this application has the following advantages:

[0099] -Supports AI-based CSI reporting;

[0100] -Reduce system measurement resources and overhead;

[0101] -Reduce system CSI reporting resources and overhead;

[0102] - Improve the system's forward and backward compatibility;

[0103] -Enhance the system's flexibility and adaptability;

[0104] - Improve system reliability and robustness;

[0105] -Simplify system design and reduce the complexity of solution implementation;

[0106] - Improve the accuracy and effectiveness of CSI reporting;

[0107] - Enhance the overall performance of the system. Attached Figure Description

[0108] 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:

[0109] Figure 1 illustrates a flowchart of the target CSI reporting configuration, target information block, and target CSI according to an embodiment of this application;

[0110] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0111] 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;

[0112] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0113] Figure 5 illustrates a flowchart of wireless transmission according to an embodiment of this application;

[0114] Figure 6 shows a schematic diagram of a first resource set and a second resource set according to an embodiment of this application;

[0115] Figure 7 illustrates a schematic diagram of a first operation according to an embodiment of this application;

[0116] Figure 8 illustrates a schematic diagram showing how the generation of a target CSI is associated with a target identifier according to an embodiment of this application;

[0117] Figure 9 illustrates a schematic diagram showing how the generation of a target CSI is associated with a target identifier according to another embodiment of this application;

[0118] Figure 10 shows a schematic diagram of a target information block indicating a target identifier according to an embodiment of this application;

[0119] Figure 11 shows a schematic diagram of at least one information block according to an embodiment of this application;

[0120] Figure 12 illustrates a schematic diagram of a target identifier depending on at least one information block according to an embodiment of this application;

[0121] Figure 13 shows a schematic diagram of a first value and a first threshold according to an embodiment of this application;

[0122] Figure 14 shows a schematic diagram of the triggering conditions of a target information block according to an embodiment of this application;

[0123] Figure 15 illustrates a schematic diagram of a second operation according to an embodiment of this application;

[0124] Figure 16 illustrates a schematic diagram of a first operation according to another embodiment of this application;

[0125] Figure 17 shows a schematic diagram of the deployment of a first operation according to an embodiment of this application;

[0126] Figure 18 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;

[0127] Figure 19 shows a schematic diagram of the deployment of AI / ML functions of a UE according to an embodiment of this application;

[0128] Figure 20 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0129] Figure 21 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application;

[0130] Figure 22 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0131] Figure 23 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0132] 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 5-23, the embodiments in Figure 5 and the embodiments in Figures 6-23, etc.

[0133] Example 1

[0134] Example 1 illustrates a flowchart of the target CSI reporting configuration, target information block, and target CSI according to an embodiment of this application, as shown in Figure 1. In Figure 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific temporal relationship between the steps.

[0135] In Embodiment 1, the first node in this application receives the target CSI reporting configuration in step 101; sends the target information block in step 102; determines whether to abandon sending the target CSI in step 103; and abandons sending the target CSI in step 104 when the first condition is met.

[0136] The target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSI is generated based on training or AI; determining whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the target CSI generation method being associated with the target identifier; the target identifier depends on the target information block.

[0137] As an example, the target CSI reporting configuration is carried by higher layer signaling.

[0138] As an example, the target CSI reporting configuration is carried by RRC (Radio Resource Control) signaling.

[0139] As an example, the target CSI reporting configuration is carried by an RRC IE (Information Element).

[0140] As an example, the target CSI reporting configuration is carried by at least one RRC IE.

[0141] As an example, the target CSI reporting configuration includes information from one or more domains in at least one RRC IE.

[0142] As an example, the target CSI reporting configuration includes information from one or more domains of each of a plurality of RRC IEs.

[0143] As one example, the target CSI reporting configuration includes some or all of the domains in the CSI-ReportConfig IE.

[0144] As one example, the target CSI reporting configuration includes some or all of the domains in the ServingCellConfig IE.

[0145] As one example, the target CSI reporting configuration includes some or all of the domains in the CSI-MeasConfig IE.

[0146] As an example, the target CSI reporting configuration includes some or all of the domains in the ServingCellConfigCommon IE.

[0147] As an example, the target CSI reporting configuration includes some or all of the domains in the ServingCellConfigCommonSIB IE.

[0148] As an example, the target CSI reporting configuration is transmitted on the PDSCH.

[0149] As an example, the target CSI reporting configuration configures CSI reporting to be periodic.

[0150] As an example, the target CSI reporting configuration configures CSI reporting to be semi-persistent.

[0151] As an example, the target CSI reporting configuration configures CSI reporting to be aperiodic.

[0152] As an example, the target CSI reporting configuration is an RRC IE.

[0153] As an example, the target CSI reporting configuration belongs to CSI-ReportConfig IE.

[0154] As an example, the target CSI reporting configuration belongs to ServingCellConfig IE.

[0155] As an example, the target CSI reporting configuration belongs to CSI-MeasConfig IE.

[0156] As an example, the target CSI reporting configuration belongs to ServingCellConfigCommon IE.

[0157] As an example, the target CSI reporting configuration belongs to ServingCellConfigCommonSIB IE.

[0158] As an example, the target CSI reporting configuration indicates a first resource set, which is used for at least one of the channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources.

[0159] As one embodiment, the generation method of the target CSI based on training or AI includes: the generation method of the target CSI is based on training; the generation method of the target CSI not based on training or AI includes: the generation method of the target CSI is not based on training.

[0160] As an example, the generation method of the target CSI based on training or AI includes: the generation method of the target CSI is based on AI; the generation method of the target CSI not based on training or AI includes: the generation method of the target CSI is not based on AI.

[0161] As an example, the generation method of the target CSI based on training or AI includes: the generation method of the target CSI uses an AI model; the generation method of the target CSI not based on training or AI includes: the generation method of the target CSI does not use an AI model.

[0162] As an example, the generation method of the target CSI is based on training or AI, including: the target CSI includes information based on artificial intelligence or machine learning; the generation method of the target CSI is not based on training or AI, including: the target CSI does not include information based on artificial intelligence or machine learning.

[0163] As one embodiment, the generation method of the target CSI based on training or AI includes: the target CSI includes information generated based on a neural network; the generation method of the target CSI not based on training or AI includes: the target CSI does not include information generated based on a neural network.

[0164] As one embodiment, the generation method of the target CSI based on training or AI includes: the target CSI includes information generated based on CNN (Conventional Neural Networks); the generation method of the target CSI not based on training or AI includes: the target CSI does not include information generated based on CNN.

[0165] As one embodiment, the generation of the target CSI is based on training or AI, including: the generation of the target CSI includes the sender of the target CSI performing a first operation, the input of the first operation depending on the measurement based on the first resource set, and the target CSI depending on the output of the first operation; the generation of the target CSI is not based on training or AI, including: the generation of the target CSI does not include the sender of the target CSI performing the first operation.

[0166] As one embodiment, the generation of the target CSI is based on training or AI and includes: the generation of the target CSI includes the sender of the target CSI performing a first operation, the input of the first operation depending on a measurement based on the first resource set, the target CSI depending on the output of the first operation, and the first operation being associated with a first type of identifier; the generation of the target CSI is not based on training or AI and includes: the generation of the target CSI does not include the sender of the target CSI performing the first operation.

[0167] As one embodiment, the generation method of the target CSI based on training or AI includes: the target CSI reporting configuration indicates a first type of identifier; the generation method of the target CSI not based on training or AI includes: the target CSI reporting configuration does not indicate a first type of identifier.

[0168] As one embodiment, the generation method of the target CSI based on training or AI includes: the target CSI reporting configuration indicates a first type of identifier, and the first operation is associated with the first type of identifier indicated by the target CSI reporting configuration; the generation method of the target CSI not based on training or AI includes: the target CSI reporting configuration does not indicate a first type of identifier.

[0169] As one embodiment, the generation method of the target CSI based on training or AI includes: the generation of the target CSI is associated with a first type of identifier; the generation method of the target CSI not based on training or AI includes: the generation of the target CSI is not associated with a first type of identifier.

[0170] As an example, the generation of the target CSI is associated with a first type of identifier, including: the generation of the target CSI uses an AI model identified by the first type of identifier.

[0171] As an example, the generation of the target CSI is associated with a first type of identifier, including: the AI ​​entity identified by the first type of identifier generates the target CSI.

[0172] As an example, the generation of the target CSI is associated with a first type of identifier, which includes: the target CSI is generated by an AI entity, and the first type of identifier is used to identify the AI ​​entity or function.

[0173] As an example, the generation of the target CSI is associated with a first type of identifier, including: the generation of the target CSI belongs to an AI function, and the first type of identifier is used to identify the AI ​​function.

[0174] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0175] As an example, the benefits of the above method include: improved system flexibility and overall performance.

[0176] As an example, the target CSI includes at least one CSI reporting volume.

[0177] As an example, the target CSI includes one or more of the following: PMI (Precoding Matrix Indicator), CRI (CSI-RS Resource Indicator), SS / PBCH Block Resource Indicator (SSBRI), beam indicator, resource indicator, CQI (Channel Quality Indicator), RI (Rank Indicator), Layer Indicator (LI), RSRP (Reference Signal Received Power), SINR (Signal-to-noise and Interference Ratio), Capability Index, or TDCP (Time Domain Channel Properties).

[0178] As an example, the target CSI includes a channel matrix.

[0179] As an example, the target CSI includes a feature vector and / or feature values.

[0180] As an example, the target CSI includes a precoding matrix.

[0181] As an example, the target CSI includes one or more of the following: channel matrix, eigenvector, eigenvalue, or precoding matrix.

[0182] As an example, the target CSI includes one or more of the following: beam indicator, CRI (CSI-RS Resource Indicator), SS / PBCH Block Resource indicator (SSBRI), or RSRP (reference signal received power).

[0183] As an example, the target CSI includes one or more of the following: beam indication, number of beams, CRI, SS / PBCH block resource indicator, number of CRI or SSBRI, RSRP, differential RSRP, probability information, or confidence information.

[0184] As an example, the probability information indicates the probability that the corresponding beam is one or more optimal beams.

[0185] As an example, the probability information represents the probability that the corresponding RS resource is one or more optimal RS resources.

[0186] As an example, confidence information indicates the accuracy of RSRP.

[0187] As an example, the confidence information represents the accuracy of the differential RSRP.

[0188] As an example, the essence of the above method includes: monitoring the AI ​​model by reporting relevant performance parameters based on AI's CSI.

[0189] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0190] As an example, the target CSI includes RSRP.

[0191] As an example, the target CSI includes at least one resource indication and RSRP.

[0192] As an example, the target CSI includes at least one resource indication.

[0193] As an example, the target CSI includes at least one resource indicator, one of which is used to indicate a beam or RS resource.

[0194] As an example, the target CSI includes at least one resource indicator, one of which is used to indicate a beam, CSI-RS resource, or SS / PBCH block resource.

[0195] As an example, the target CSI includes at least one resource indicator; one of the resource indicators in the target CSI is used to indicate a beam, or one of the resource indicators in the target CSI is a CRI (CSI-RS Resource Indicator, Channel State Information Reference Signal Resource Indicator) or an SS / PBCH Block Resource Indicator (SSBRI).

[0196] As an example, the target CSI includes a first indication and an RSRP, wherein the first indication is used to indicate a resource.

[0197] As an example, the target CSI includes a first indication and an RSRP, wherein the first indication is used to indicate an RS resource.

[0198] As an example, the target CSI includes beam indication and RSRP.

[0199] As an example, the target CSI includes RS resource indication and RSRP.

[0200] In one embodiment, the target CSI includes a beam indicator or an RS resource indicator.

[0201] As an example, the target CSI includes predicted CSI.

[0202] As an example, the target CSI includes CSI for a future period of time.

[0203] As an example, the target CSI includes predicted beam information.

[0204] As an example, the target CSI includes beam information for a future period of time.

[0205] As an example, the target CSI includes a prediction of temporal CSI.

[0206] As a sub-implementation of the above embodiments, the future time period includes at least one time domain resource following the current time domain resource.

[0207] As a sub-implementation of the above embodiments, the future time period includes at least one time unit after the current time unit.

[0208] As a sub-implementation of the above embodiments, the future time period includes at least one time slot after the current time slot.

[0209] As a sub-implementation of the above embodiments, the future time period includes at least one symbol following the current symbol.

[0210] As an example, the advantages of the above method include: reducing channel measurement overhead.

[0211] As an example, the benefits of the above method include: improving the accuracy and real-time performance of CSI reporting, and enhancing the overall system performance.

[0212] As an example, the target CSI includes compressed CSI.

[0213] As an example, the compressed CSI is based on a non-codebook.

[0214] As an example, the compressed CSI is not a CSI defined by 3GPP Rel-18, nor is it a CSI defined by versions prior to 3GPP Rel-18.

[0215] 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.

[0216] As an example, the advantages of the above method include: saving CSI feedback overhead and improving the overall performance of the system.

[0217] As an example, the target CSI is AI-based.

[0218] As an example, the target CSI is not AI-based.

[0219] As an example, the amount of reporting included in the target CSI depends on whether the generation of the target CSI is based on AI.

[0220] As one example, the amount of reported CSIs included in the target CSIs depends on whether the target CSIs are generated using AI.

[0221] As an example, whether the target CSI includes confidence information depends on whether the target CSI is generated based on AI; the target CSI includes confidence information only when the target CSI is generated based on AI.

[0222] As an example, whether the target CSI is based on a non-codebook depends on whether the target CSI is generated based on training or AI; when the target CSI is generated based on training or AI, the target CSI is based on a non-codebook; when the target CSI is not generated based on training or AI, the target CSI is based on a codebook.

[0223] As an example, when the target CSI is not generated based on training or AI, the target CSI belongs to the CSI defined by 3GPP Rel-18.

[0224] As an example, when the target CSI is generated based on training or AI, the target CSI does not belong to the CSI defined in 3GPP Rel-18 and earlier versions.

[0225] As an example, when the target CSI is generated based on training or AI, the target CSI includes predicted CSI, predicted beam information, or compressed CSI.

[0226] As an example, when the target CSI is generated based on training or AI, the target CSI includes CSI based on artificial intelligence or machine learning.

[0227] As an example, when the target CSI is generated based on training or AI, the target CSI includes CSI generated based on a neural network.

[0228] As an example, when the target CSI is generated based on training or AI, the target CSI includes CSI generated based on CNN (Conventional Neural Networks).

[0229] As an example, the advantages of the above method include: supporting AI-based CSI reporting schemes.

[0230] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0231] As an example, the benefits of the above method include: enhancing system flexibility and improving overall system performance.

[0232] As an example, in the case where the generation of the target CSI is not based on training or AI, how to generate the target CSI is determined by the manufacturer of the first node, or is implementation-related. A typical but non-limiting implementation is described below:

[0233] The first node first performs measurements on the first resource set to obtain the channel parameter matrix H. r×t Where r and t are the number of receiving antennas and the number of antenna ports of the target CSI-RS resource, respectively; for the channel parameter matrix H r×t Power adjustment is performed, and the adjusted channel parameter matrix is ​​as follows: Where P is the assumed ratio of PDSCH EPRE to the target CSI-RS EPRE (i.e., the first power control offset); when using the precoding matrix W t×l Under these conditions, the precoded channel parameter matrix is: Where l is the rank or the number of layers, in one case l is a positive integer no greater than t, in another case the precoding matrix is ​​an identity matrix, in which case t = l; H is calculated using criteria such as SINR (Signal Interference Noise Ratio), EESM (Exponential Effective SINR Mapping), or RBIR (Received Block Mean Mutual Information Ratio). r×t ·W t×l The equivalent channel capacity is calculated, and then the CQI included in the target CSI report is determined from the equivalent channel capacity through methods such as table lookup. Generally, the calculation of the equivalent channel capacity requires the first node to estimate the interference (including noise). The first node can obtain a more accurate measurement of the interference using measurements from the second timing set in this application. Generally, the direct mapping from the equivalent channel capacity to the CQI value depends on receiver performance or hardware-related factors such as modulation scheme.

[0234] As an example, in the case where the generation of the target CSI is based on AI, how to generate the target CSI is determined by the manufacturer of the first node, or is related to implementation. Without loss of generality, the AI ​​model or parameters used to generate the target CSI are determined by the manufacturer of the first node.

[0235] As an example, the generation of the target CSI depends on measurements obtained from the first resource set.

[0236] As an example, the generation of the target CSI depends on channel measurements and / or interference measurements obtained based on the first resource set.

[0237] As an example, measurements based on the first resource set are used to generate the target CSI.

[0238] As an example, channel measurements and / or interference measurements based on the first resource set are used to generate the target CSI.

[0239] As an example, measurements based on one or more RS resources in the first resource set are used to generate the target CSI.

[0240] As an example, a measurement based on the transmission timing of one or more RS resources in the first resource set no later than that of a reference resource is used to generate the target CSI.

[0241] As an example, the target CSI is generated based on a measurement of one or more recent transmission times from one or more RS resources in the first resource set that are no later than the reference resource.

[0242] As an example, the channel measurement obtained based on the first resource set refers to the channel measurement obtained based on at least one reference signal transmitted in the first resource set.

[0243] As an example, the channel measurement obtained based on the first resource set refers to the channel measurement obtained in the first resource set.

[0244] As an example, the channel measurement obtained based on the first resource set includes at least one of the following: channel matrix, raw channel matrix, eigenvector, and eigenvalue.

[0245] As an example, the channel measurements obtained based on the first resource set include one or more of BLER, delay spread, Doppler spread, Doppler shift, average delay, average gain, path loss, and RSRP.

[0246] As an example, interference measurement based on the first resource set refers to interference measurement based on at least one reference signal transmitted in the first resource set.

[0247] As an example, the interference measurement obtained based on the first resource set refers to the interference measurement obtained in the first resource set.

[0248] As an example, the interference measurement obtained based on the first resource set includes at least one of interference power, interference variance, or interference power spectral density.

[0249] As an example, the interference measurement obtained based on the first resource set includes at least one of the following: interference channel matrix, interference covariance matrix, interference eigenvector, interference eigenvalue, and interference beam.

[0250] As one embodiment, the measurement based on the first resource set includes: a channel matrix obtained based on the measurement for the first resource set.

[0251] As one embodiment, the measurement based on the first resource set includes: a matrix or vector obtained by preprocessing the channel matrix obtained based on the measurement for the first resource set.

[0252] As an example, the channel matrix is ​​in the spatial-frequency domain.

[0253] As an example, the channel matrix is ​​in the angular-delay domain projection.

[0254] As an example, the preprocessing includes one or more of the following: quantization, DFT (Discrete Fourier Transform), matrix decomposition, matrix transformation or projection, spatial-to-angular-domain transformation, angular-to-spatial-domain transformation, frequency-to-time-domain transformation and time-to-frequency-domain transformation, truncation, padding, mapping, and labeling.

[0255] As one embodiment, transmitting the target CSI includes: transmitting the target CSI on a first physical channel.

[0256] As one embodiment, transmitting the target CSI includes: transmitting a first signal on a first physical channel; wherein the first signal carries the target CSI.

[0257] As one embodiment, the first signal includes a baseband signal.

[0258] As one embodiment, the first signal includes a wireless signal.

[0259] As one embodiment, the first signal includes a radio frequency signal.

[0260] As one embodiment, the transmission target CSI includes: the target CSI being used, after channel coding, to generate a signal to be transmitted on a first physical channel.

[0261] As one embodiment, the transmission target CSI includes: the target CSI being used to generate a signal to be transmitted on the first physical channel after being channel-coded and modulated.

[0262] As an example, the transmission target CSI includes: the target CSI being used to generate a signal to be transmitted on a first physical channel after bit sequence generation and channel coding.

[0263] As an example, the transmission target CSI includes: the target CSI being used to generate a signal to be transmitted on a first physical channel after bit sequence generation, channel coding, and modulation.

[0264] As an example, the target CSI includes: the target CSI being used to generate a signal to be transmitted on the first physical channel after undergoing bit sequence generation, code block segmentation, CRC attachment, channel coding, rate matching, and code block concatenation.

[0265] As an example, the transmission target CSI includes: the target CSI being multiplexed into the first physical channel after bit sequence generation, code block segmentation and CRC addition, channel coding, rate matching, and code block concatenation.

[0266] As an example, the advantages of the above method include: utilizing existing system designs and standards.

[0267] As an example, the first physical channel is an uplink channel.

[0268] As an example, the first physical channel is PUSCH (Physical Uplink Shared Channel).

[0269] As an example, the first physical channel is PUCCH (Physical Uplink Control Channel).

[0270] As one embodiment, the first physical channel includes a plurality of REs (Resource Elements).

[0271] As an example, the first physical channel occupies at least one symbol in the time domain and at least one subcarrier in the frequency domain.

[0272] As an example, the first physical channel occupies at least one symbol in the time domain and at least one RB (resource block) in the frequency domain.

[0273] Typically, an RE occupies one symbol in the time domain and one subcarrier in the frequency domain.

[0274] As an example, the symbol is a single-carrier symbol.

[0275] As an example, the symbol is a multi-carrier symbol.

[0276] As an example, the symbol is a 6G single-carrier symbol.

[0277] As an example, the symbol is a 6G multi-carrier symbol.

[0278] As an example, the multicarrier symbol is an OFDM (Orthogonal Frequency Division Multiplexing) symbol.

[0279] As an example, the symbols are obtained by passing the output of the transform precoding through OFDM symbol generation.

[0280] As an example, the multi-carrier symbol is an SC-FDMA (Single Carrier-Frequency Division Multiple Access) symbol.

[0281] As an example, the multicarrier symbol is a DFT-S-OFDM (Discrete Fourier Transform Spread OFDM) symbol.

[0282] As an example, the multi-carrier symbol is an FBMC (Filter Bank Multi Carrier) symbol.

[0283] As one embodiment, the multicarrier symbol includes CP (Cyclic Prefix).

[0284] As an example, the advantages of the above method include: utilizing existing system designs and standards.

[0285] Typically, the determination of whether to abandon sending the target CSI depends on whether the first condition is met.

[0286] As an example, the first condition being satisfied includes: the generation method of the target CSI is associated with the target identifier.

[0287] As an example, the first condition being satisfied includes: the generation method of the target CSI is associated with at least one identifier, the at least one identifier including the target identifier.

[0288] As an example, the first condition being satisfied includes: the generation method of the target CSI is associated with a first type of identifier, where the first type of identifier is a target identifier.

[0289] As an example, the first condition being satisfied includes: the generation method of the target CSI is associated with a first type of identifier, and the first type of identifier is associated with the target identifier.

[0290] As an example, the first condition being satisfied includes: the target CSI is generated using an AI model, and the AI ​​model is associated with the target identifier.

[0291] As an example, the first condition being satisfied includes: the generation of the target CSI includes performing a first operation, the first operation being associated with a target identifier.

[0292] As an example, the first condition not being met includes: the method of generating the target CSI is not associated with the target identifier.

[0293] As an example, the first condition not being met includes: the generation method of the target CSI is associated with at least one identifier, and the at least one identifier does not include the target identifier.

[0294] As an example, the first condition not being met includes: the generation method of the target CSI is associated with a first type of identifier, and the first type of identifier is not the target identifier.

[0295] As an example, the first condition not being met includes: the target CSI is not generated based on training or AI.

[0296] As an example, the first condition not being met includes: the target CSI is generated without using an AI model.

[0297] As an example, the first condition not being met includes: the generation method of the target CSI does not include performing the first operation.

[0298] As an example, the first condition not being met includes: the generation method of the target CSI is not associated with the first type of identifier.

[0299] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0300] As an example, the advantages of the above method include: improving system flexibility and simplifying system design.

[0301] As an example, the first node abandons sending the target CSI only when the first condition is met.

[0302] As an example, when the first condition is met, the first node ignores the target CSI.

[0303] As an example, when the first condition is met, the first node abandons sending the target CSI and ignores the target CSI.

[0304] As an example, when the first condition is met, the first node sends the target CSI, and the target CSI is not updated.

[0305] As an example, when the first condition is not met, the first node sends the target CSI, and the target CSI is valid.

[0306] As an example, when the first condition is met, the first node abandons sending the target CSI; when the first condition is not met, the first node sends the target CSI.

[0307] As an example, when the first condition is met, the first node abandons sending the target CSI; when the first condition is not met, the first node sends the target CSI, and the target CSI is valid.

[0308] As an example, when the generation method of the target CSI is associated with the target identifier, the first node abandons sending the target CSI; when the generation method of the target CSI is not associated with the target identifier, the first node sends the target CSI.

[0309] As an example, when the generation method of the target CSI is associated with the target identifier, the first node abandons sending the target CSI; when the generation method of the target CSI is not associated with the target identifier, the first node sends the target CSI, and the target CSI is valid.

[0310] As an example, the benefits of the above method include: improved system flexibility and overall performance.

[0311] As an example, the benefits of the above method include: improving the stability and robustness of the system.

[0312] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0313] As an example, the target CSI being valid includes: the target CSI being an updated CSI.

[0314] As an example, the target CSI is valid if it is different from the most recent CSI reported on the first PUSCH that was configured for the target CSI.

[0315] As an example, the target CSI is valid if the target CSI is different from the most recent CSI reported on the first PUSCH that was configured for the target CSI.

[0316] As an example, the target CSI is valid if the target CSI is not necessarily the same as the most recent CSI reported on the first PUSCH that was configured for the target CSI.

[0317] As an example, the target CSI is valid by measuring the most recent RS timing of a CSI reference resource in the first resource set that is no later than the target CSI, depending on whether the target CSI is different from the most recent CSI reported configuration on the first PUSCH earlier than the target CSI.

[0318] As an example, the target CSI is effectively defined as follows: the target CSI is generated based on the measurement of the most recent RS timing of at least the CSI reference resources in the first resource set that are no later than the target CSI.

[0319] As an example, the target CSI is validly defined as follows: the target CSI is a CSI updated based on the most recent RS timing of at least one CSI reference resource in the first resource set that is no later than the target CSI.

[0320] As an example, the target CSI is effectively defined as follows: the target CSI is generated based on measurements of RS resources in the first resource set.

[0321] As an example, the target CSI is valid if it is updated based on the measurement of RS resources in the first resource set.

[0322] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0323] As an example, the method of generating the target CSI is associated with the target identifier, including: the method of generating the target CSI uses an AI model identified by the target identifier.

[0324] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI does not use the AI ​​model identified by the target identifier.

[0325] As one example, the generation method of the target CSI is associated with the target identifier, including: the AI ​​entity identified by the target identifier generates the target CSI.

[0326] As an example, the method of generating the target CSI without being associated with the target identifier includes: the generator of the target CSI is not the AI ​​entity identified by the target identifier.

[0327] As one example, the generation method of the target CSI associated with the target identifier includes: the target CSI is generated by an AI entity, and the target identifier is used to identify the AI ​​entity or function.

[0328] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI is generated by the AI ​​entity, and the target identifier is not used to identify the AI ​​entity or function.

[0329] As an example, the generation method of the target CSI is associated with the target identifier, including: the target CSI is used for the AI ​​function identified by the target identifier.

[0330] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI is not used for the AI ​​function identified by the target identifier.

[0331] As an example, the method of generating the target CSI is associated with the target identifier, which includes: the method of generating the target CSI is associated with at least one identifier, and the at least one identifier includes the target identifier.

[0332] As an example, the method of generating the target CSI is not associated with the target identifier, including: the method of generating the target CSI is associated with at least one identifier, wherein the at least one identifier does not include the target identifier.

[0333] As an example, the method of generating the target CSI is associated with the target identifier, including: the method of generating the target CSI is associated with a first type of identifier, and the first type of identifier is associated with the target identifier.

[0334] As an example, the method of generating the target CSI not being associated with the target identifier includes: the method of generating the target CSI being associated with a first type of identifier, and the first type of identifier not being associated with the target identifier.

[0335] As one embodiment, the method of generating the target CSI associated with the target identifier includes: the method of generating the target CSI includes performing a first operation, the first operation being associated with the target identifier.

[0336] As an example, the method of generating the target CSI that is not associated with the target identifier includes: the method of generating the target CSI includes performing a first operation, the first operation being unrelated to the target identifier.

[0337] As an example, the method of generating the target CSI and associating it with the target identifier includes: the method of generating the target CSI and associating it with the target identifier through the target CSI reporting configuration.

[0338] As an example, the method of generating the target CSI is not associated with the target identifier, including: the method of generating the target CSI is not associated with the target identifier through the target CSI reporting configuration.

[0339] As one embodiment, the generation method of the target CSI is associated with the target identifier, including: the target CSI reporting configuration indicates the target identifier; the target CSI reporting configuration indicates the generation method of the target CSI.

[0340] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI reporting configuration indicates a first type of identifier; the target CSI reporting configuration indicates the generation method of the target CSI; and the target identifier is not a first type of identifier.

[0341] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0342] As an example, the advantages of the above method include: improving the flexibility of the system and adapting to different scenarios and applications.

[0343] As an example, the target identifier is a non-negative integer.

[0344] As an example, the target identifier is a string.

[0345] As an example, the target identifier is a model identifier.

[0346] As an example, the target identifier is used to identify an AI model, AI entity, or AI function.

[0347] As an example, the target identifier is used by the first node to identify an AI model, AI entity, or AI function.

[0348] As an example, the target CSI reporting configuration indicates the use of an AI model, AI entity, or AI function by indicating the target identifier.

[0349] As an example, the target CSI reporting configuration obtains input of AI entities / functions / inferences associated with the target identifier by instructing the target identifier.

[0350] As an example, the advantages of the above method include: identifying an AI model, AI entity, or AI function through the target identifier, simplifying system design, and unifying the understanding of different AI models, AI entities, or AI functions across multiple nodes.

[0351] As one example, the target identifier is used to identify or indicate a set of resources.

[0352] As one embodiment, the target identifier is used to identify or indicate a set of resources, the measurement of which is used to obtain a training dataset.

[0353] As one example, the target identifier is used to identify or indicate a set of resources.

[0354] As an example, the target identifier is used to identify or indicate the training dataset.

[0355] 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.

[0356] As one embodiment, the target identifier depends on the target information block, which includes: the target information block being used to determine the target identifier.

[0357] As one embodiment, the target identifier depends on the target information block, including: the target information block indicating the target identifier.

[0358] As one embodiment, the target identifier depends on the target information block including: the target information block explicitly indicates the target identifier.

[0359] As one embodiment, the target identifier depends on the target information block including: the target information block implicitly indicates the target identifier.

[0360] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of system implementation.

[0361] As one embodiment, the target identifier depends on the target information block, which includes: the target information block indicating at least one identifier, the at least one identifier including the target identifier.

[0362] As one embodiment, the target identifier depends on the target information block including: the target information block indicates a first type of identifier, which is associated with the target identifier.

[0363] As an example, the advantages of the above method include: improving the flexibility of the system and adapting to different scenarios and applications.

[0364] As one embodiment, the target identifier depending on the target information block includes: the target identifier depending on at least one information block, and the at least one information block including the target information block.

[0365] As one embodiment, the target identifier depending on the target information block includes: the target identifier depending on at least one information block, and the target information block depending on at least one information block.

[0366] As one embodiment, the target identifier depending on the target information block includes: the target identifier depending on at least one information block, and the target information block being generated from the at least one information block.

[0367] As one embodiment, the target identifier depending on the target information block includes: the target identifier depending on at least one information block, the at least one information block configuring or indicating at least one signal, the target information block being generated based on the reception or measurement of some or all of the at least one signal.

[0368] As an example, the advantages of the above method include: improving the flexibility and adaptability of the system.

[0369] As one embodiment, the target identifier depends on the target information block, which includes: the target information block indicating at least one AI model, AI entity, or AI function, the at least one AI model, AI entity, or AI function being associated with the target identifier.

[0370] As one embodiment, the target identifier depends on the target information block, which includes: the target information block indicating the AI ​​model, AI entity, or AI function identified by the target identifier.

[0371] As one embodiment, the target identifier depends on the target information block including: the target information block indicates that the AI ​​model identified by the target identifier has failed or malfunctioned.

[0372] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0373] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0374] As an example, the benefits of the above method include: improving the accuracy and effectiveness of CSI reporting and improving the overall performance of the system.

[0375] As one embodiment, the target identifier depends on the target information block, which includes: the target information block indicating the performance metrics of the AI ​​model identified by the target identifier.

[0376] As one example, the performance metrics include probability information.

[0377] As an example, the AI ​​model is used for beam management, and the probability information indicates the probability that the corresponding beam is one or more optimal beams.

[0378] As an example, the AI ​​model is used for beam management, and the probability information represents the probability that the corresponding RS resource is one or more optimal RS resources.

[0379] As an example, the performance metric includes the difference between the actual measured RSRP and the predicted RSRP.

[0380] As an example, the performance metrics include at least one of L1-RSRP and L1-SINR.

[0381] As one example, the performance metrics include confidence information.

[0382] As an example, the confidence information indicates the accuracy of RSRP.

[0383] As an example, the confidence information represents the accuracy of the differential RSRP.

[0384] As an example, the AI ​​model performs CSI prediction and / or CSI compression, and the performance metrics include the difference between the actual measured channel matrix and the predicted channel matrix.

[0385] As an example, the AI ​​model performs CSI prediction and / or CSI compression, and the performance metrics include SGCS (cosine similarity) between the actual measured channel matrix and the predicted channel matrix.

[0386] As an example, the AI ​​model performs CSI prediction and / or CSI compression, and the performance metrics include the difference between the actual measured channel feature vector (eigenvector) and the predicted channel feature vector (eigenvector).

[0387] As an example, the AI ​​model performs CSI prediction and / or CSI compression, and the performance metrics include SGCS (cosine similarity) between the actual measured channel feature vector (eigenvector) and the predicted channel feature vector (eigenvector).

[0388] As an example, the AI ​​model performs CSI prediction and / or CSI compression, and the performance metrics include the difference between the actual measured PMI (Precoding Matrix Indicator) and the predicted PMI (Precoding Matrix Indicator).

[0389] As an example, the AI ​​model CSI prediction and / or CSI compression, the performance metric includes SGCS (cosine similarity) between the actual measured PMI (Precoding Matrix Indicator) and the predicted PMI (Precoding Matrix Indicator).

[0390] As an example, the performance metric is a system physical layer performance metric.

[0391] As an example, the performance metric is a system link layer performance metric.

[0392] As an example, the performance metric is a higher-level performance metric of the system.

[0393] As an example, the performance index is the overall system performance index.

[0394] As an example, the performance metrics include one or more of the following: signal-to-noise ratio, link data rate, peak rate, throughput, traffic density, average user data rate, minimum user data rate, bit error rate, block error rate, bit error rate, spectral efficiency, energy efficiency, data transmission latency, air interface latency, number of link connections, number of device connections, and maximum mobility support.

[0395] As an example, the essence of the above method includes: monitoring the AI ​​model by reporting relevant performance parameters based on AI's CSI.

[0396] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0397] As one embodiment, the target identifier depending on the target information block includes: the target information block includes first information, and the target identifier depends on the first information.

[0398] As one embodiment, the target identifier depends on the target information block including: the target information block includes one or more HARQ-ACK bits, and the target identifier depends on the one or more HARQ-ACK bits.

[0399] As one embodiment, the target identifier depends on the target information block, which includes the number of times one or more AI models have failed or malfunctioned, and the target identifier depends on the number of times the one or more AI models have failed or malfunctioned.

[0400] As an example, the benefits of the above method include: improving the stability and robustness of the system.

[0401] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0402] As one embodiment, the target identifier depending on the target information block includes: the target information block indicating a first value, and the target identifier depending on the first value.

[0403] As one embodiment, the target identifier depending on the target information block includes: the target information block indicating a first value, and the target identifier depending on the first value and a first threshold.

[0404] As one embodiment, the target identifier depends on the target information block, which includes: the target information block indicating a first value, and the target identifier depending on the magnitude relationship between the first value and a first threshold.

[0405] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0406] Example 2

[0407] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0408] 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.

[0409] As an example, the first node in this application includes the UE201.

[0410] As an example, the second node in this application includes the gNB203.

[0411] As one example, the UE 201 includes a mobile phone.

[0412] As one embodiment, the UE 201 includes vehicles, including automobiles.

[0413] As an example, the gNB203 is a macrocell base station.

[0414] As an example, the gNB203 is a microcell base station.

[0415] As an example, the gNB203 is a pico cell base station.

[0416] As an example, the gNB203 is a femtocell.

[0417] As an example, the gNB203 is a base station device that supports large latency differences.

[0418] As one example, the gNB203 is a flight platform device.

[0419] As an example, the gNB203 is a satellite device.

[0420] As one embodiment, the gNB203 is a test device (e.g., a transceiver device simulating part of the functions of a base station, a signaling tester).

[0421] As an example, the radio link from the UE 201 to the gNB 203 is an uplink, which is used to perform uplink transmissions.

[0422] As an example, the radio link from the gNB203 to the UE201 is a downlink, which is used to perform downlink transmissions.

[0423] As an example, the radio link between the UE 201 and the gNB 203 includes a cellular link.

[0424] As an example, the UE 201 and the gNB 203 are connected via the Uu air interface.

[0425] As an example, the sender of the target CSI reporting configuration includes the gNB203.

[0426] As an example, the recipient of the target CSI reporting configuration includes the UE 201.

[0427] As an example, the sender of the target information block includes the UE 201.

[0428] As an example, the recipient of the target information block includes the gNB203.

[0429] As an example, the sender of the first resource set includes the gNB203.

[0430] As an example, the recipient of the first resource set includes the UE201.

[0431] As an example, the sender of the target CSI includes the UE 201.

[0432] As an example, the recipient of the target CSI includes the gNB203.

[0433] As an example, the UE 201 supports a 6G system.

[0434] As one example, the gNB203 supports a 6G system.

[0435] As an example, the UE 201 supports at least a 5G system.

[0436] As an example, the gNB203 supports at least 5G systems.

[0437] As an example, the UE 201 supports AI.

[0438] As an example, the gNB203 supports AI.

[0439] Example 3

[0440] 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.

[0441] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and a control plane according to this application, as shown in Figure 3.

[0442] Figure 3 is a schematic diagram illustrating an embodiment of the radio protocol architecture for the user plane 350 and the control plane 300. Figure 3 shows the radio protocol architecture for the control plane 300 between the first communication node device (UE, gNB, or RSU in V2X) and the 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. The L1 layer 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 and second communication node devices, or between two UEs. L2 layer 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. PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. PDCP sublayer 304 also provides security through encrypted data packets and supports cross-cell mobility between second communication node devices and the first communication node device. RLC sublayer 303 provides upper layer data packet segmentation and reassembly, retransmission of lost data packets, and data packet reordering to compensate for out-of-order reception due to HARQ. MAC sublayer 302 provides multiplexing between logical and transport channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell between the first communication node devices. MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3) of the control plane 300 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 radio protocol architecture of user plane 350 includes layer 1 (L1 layer) and layer 2 (L2 layer). The radio protocol architecture for the first and second communication node devices in user plane 350 is largely the same as the corresponding layers and sublayers in 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.).

[0443] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0444] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0445] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0446] As an example, the target CSI reporting configuration is generated in the RRC306.

[0447] As an example, the signals in the first resource set are generated by the PHY301 or the PHY351.

[0448] As an example, the target information block is generated in the PHY301 or the PHY351.

[0449] As an example, the target information block is generated in MAC302 or MAC352.

[0450] As an example, the target CSI is generated in the PHY301 or the PHY351.

[0451] As an example, the target CSI is generated in MAC302 or MAC352.

[0452] Example 4

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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), M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based and non-codebook-based precoding, and beamforming processing, generating one or more parallel streams. 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 subsequently uses Inverse Fast Fourier Transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. 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 transmitter processor 471 into an radio frequency stream, which is then provided to different antennas 420.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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 includes at least: receiving a target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSI is generated based on training or AI; sending a target information block; determining whether to abandon sending the target CSI; abandoning sending the target CSI when a first condition is met; wherein, determining whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the target CSI's generation method being associated with a target identifier; the target identifier depending on the target information block.

[0461] 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, generates actions including: receiving a target CSI reporting configuration; the target CSI reporting configuration being used to configure the reporting of target CSIs; the target CSIs being generated based on training or AI; sending a target information block; determining whether to abandon sending the target CSIs; and abandoning sending the target CSIs when a first condition is met; wherein determining whether to abandon sending the target CSIs depends on whether the first condition is met; the first condition includes the target CSIs being generated in a manner associated with a target identifier; and the target identifier depending on the target information block.

[0462] 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 includes at least: transmitting a target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the generation method of the target CSI is based on training or AI; receiving a target information block; determining whether to abandon receiving the target CSI; abandoning receiving the target CSI when a first condition is met; wherein, the target recipient of the target CSI reporting configuration determines whether to abandon sending the target CSI; when the first condition is met, the target recipient of the target CSI reporting configuration abandons sending the target CSI; the determination of whether to abandon sending the target CSI by the target recipient of the target CSI reporting configuration depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with a target identifier; the target identifier depends on the target information block.

[0463] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program, which generates actions when executed by at least one processor, the actions including: sending a target CSI reporting configuration; the target CSI reporting configuration being used to configure the reporting of target CSIs; the target CSI being generated based on training or AI; receiving a target information block; determining whether to abandon receiving the target CSI; abandoning receiving the target CSI when a first condition is met; wherein, the target recipient of the target CSI reporting configuration determines whether to abandon sending the target CSI; when the first condition is met, the target recipient of the target CSI reporting configuration abandons sending the target CSI; the determination of whether to abandon sending the target CSI by the target recipient of the target CSI reporting configuration depends on whether the first condition is met; the first condition includes the target CSI generation method being associated with a target identifier; the target identifier depending on the target information block.

[0464] As an example, the first node in this application includes the second communication device 450.

[0465] As an example, the second node in this application includes the first communication device 410.

[0466] 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 target CSI reporting configuration; 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 target CSI reporting configuration.

[0467] 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 RS resources in the first resource set; 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 RS resources in the first resource set.

[0468] As an example, at least one of {the antenna 420, the receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the controller / processor 475, and the memory 476} is used to receive the target information block; at least one of {the antenna 452, the transmitter 454, the transmitting processor 468, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the target information block.

[0469] As an example, at least one of {the antenna 420, the receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the controller / processor 475, and the memory 476} is used to receive the target CSI; and at least one of {the antenna 452, the transmitter 454, the transmitting processor 468, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the target CSI.

[0470] Example 5

[0471] 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 F51 to F55 are optional.

[0472] For the second node U1, the second operation is deployed in step S511; the target CSI reporting configuration is sent in step S512; a signal is sent in the first resource set in step S513; the target information block is received in step S514; it is determined in step S515 whether to abandon receiving the target CSI; when the first condition is met in step S516, the reception of the target CSI is abandoned; and the second operation is executed in step S517.

[0473] For the first node U2, in step S521, a first operation is deployed; in step S522, the target CSI reporting configuration is received; in step S523, a signal is received in the first resource set; in step S524, the first operation is executed; in step S525, a target information block is sent; in step S526, it is determined whether to abandon sending the target CSI; in step S527, when the first condition is met, the sending of the target CSI is abandoned.

[0474] In Example 5, the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSI is generated based on training or AI; determining whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes that the target CSI generation method is associated with the target identifier; the target identifier depends on the target information block.

[0475] As an example, the first node U2 is the first node in this application.

[0476] As an example, the second node U1 is the second node in this application.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] In one embodiment, the second node U1 is the serving cell sustaining base station of the first node U2.

[0481] As an example, the step in block F53 of Figure 5 is present; the method used in the first node for wireless communication includes: receiving a signal in the first resource set.

[0482] As an example, the step in block F53 of Figure 5 is present; the method used in the second node for wireless communication includes: transmitting a signal in the first resource set.

[0483] As an example, sending a signal in the first resource set means sending a wireless signal in the first resource set.

[0484] As an example, sending a signal in the first resource set means sending a reference signal in the first resource set.

[0485] As an example, receiving a signal in the first resource set means receiving a wireless signal in the first resource set.

[0486] As an example, receiving a signal in the first resource set means receiving a reference signal in the first resource set.

[0487] As an example, in Figure 5, when the target CSI is generated based on training or AI, the step in block F54 is present.

[0488] As an example, the steps in block F52 of Figure 5 are present.

[0489] As an example, in Figure 5, when the target CSI is generated based on training or AI, the steps in box F54 and box F55 are present, and the first node and the second node adopt a two-sided AI model.

[0490] As an example, in Figure 5, when the target CSI is generated based on training or AI, the step in box F54 exists, the step in box F55 does not exist, and the first node adopts a single-side AI model.

[0491] As an example, the steps in block F51 of Figure 5 are present, and the method described above for the second node used in wireless communication includes: deploying the second operation.

[0492] As an example, the deployment of the second operation precedes the transmission of the target CSI reporting configuration.

[0493] As an example, the deployment of the second operation is later than the sending of the target CSI reporting configuration.

[0494] As an example, the steps in block F55 of Figure 5 are present, and the method described above for the second node used in wireless communication includes: performing the second operation.

[0495] As an example, in Figure 5, when the target CSI is generated based on training or AI, the steps in box F54 and box F55 are present. The first operation is used for CSI compression, the second operation is used for CSI recovery, and the first node and the second node adopt a two-sided AI model.

[0496] As an example, in Figure 5, when the target CSI is generated based on training or AI, the step in box F54 exists, and the step in box F55 does not exist. The first operation is used for beam prediction, and the first node adopts a single-side AI model.

[0497] As an example, the deployment of the first operation precedes the receipt of the target CSI reporting configuration.

[0498] As an example, the deployment of the first operation is later than the receipt of the target CSI reporting configuration.

[0499] As an example, the output of the first operation includes the target CSI; the input of the second operation includes the target CSI.

[0500] As an example, the first node is a user (consumer).

[0501] As an example, the first node is the user of the AI ​​function.

[0502] As an example, the first node is the user of AI inference.

[0503] As an example, the first node is the user who trained the AI.

[0504] As an example, the first node is an MnS (Management Service) user.

[0505] As an example, the first node is the producer of AI inference.

[0506] As an example, the first node is the AI ​​training producer.

[0507] Example 6

[0508] Example 6 illustrates a schematic diagram of a first resource set and a second resource set according to an embodiment of this application, as shown in Figure 6. In Figure 6, resources #1, ..., resources #n, ... represent resources in the first resource set; resources #1, ..., resources #m, ... represent resources in the second resource set.

[0509] In Embodiment 6, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI indicates at least one resource in a second resource set, which includes resources that do not belong to the first resource set.

[0510] As one example, the first resource set includes one or more RS resources.

[0511] As one embodiment, the first resource set includes one or more downlink RS resources.

[0512] As an example, the first resource set includes periodic RS resources.

[0513] As an example, the first resource set includes semi-persistent RS resources.

[0514] As one embodiment, the first resource set includes aperiodic RS resources.

[0515] As one embodiment, the first resource set consists of one or more aperiodic RS resources.

[0516] As an example, the resources in the first resource set include at least one of antenna port, TCI (Transmission Configuration Indication) status, QCL (Quasi Co-Location) information, time-frequency resources, time-frequency code resources, beam, RS resources, vector, or matrix.

[0517] As one embodiment, the first resource set includes one or more RS (Reference Signal) resource sets, and an RS resource set includes one or more RS resources.

[0518] As one embodiment, the first resource set includes at least one of at least a CSI-RS resource set, at least one CSI-SSB (Channel State Information-Synchronization Signal Block) resource set, or at least one CSI-IM (Channel State Information-Interference Measurement) resource set.

[0519] As one embodiment, the first resource set includes at least one RS resource set for channel measurement.

[0520] As one embodiment, the first resource set includes at least one RS resource set for channel measurement and at least one RS resource set for interference measurement.

[0521] As one embodiment, the first resource set includes at least one RS resource set for interference measurement.

[0522] As a sub-example of the above embodiments, a set of RS resources for channel measurement includes one or more RS resources.

[0523] As a sub-example of the above embodiments, an RS resource set for interference measurement includes one or more RS resources.

[0524] As an example, a set of RS resources for channel measurement includes one or more RS resources, wherein any RS resource in the set of RS resources for channel measurement is a CSI-RS resource or a synchronization signal resource.

[0525] As an example, an RS resource set for interference measurement includes one or more RS resources, wherein any RS resource in the RS resource set for interference measurement is a CSI-IM resource or an NZP (non-zero power) CSI-RS resource for interference measurement.

[0526] As one embodiment, the first resource set includes one or more RS resources, and any RS resource in the first resource set is a CSI-RS (Channel State Information Reference Signal) resource or a synchronization signal resource.

[0527] As one embodiment, the synchronization signal resources include at least the resources occupied by the synchronization signal.

[0528] As an example, the synchronization signal resource is an SSB (Synchronization Signal Block).

[0529] As an example, the synchronization signal resource is an SS / PBCH (synchronization signal / physical broadcast channel) block resource.

[0530] As an example, the first resource set consists of at least one aperiodic CSI-RS resource for channel measurement.

[0531] As an example, the first resource set consists of at least one of at least one aperiodic CSI-RS resource for channel measurement, at least one aperiodic CSI-IM resource for interference measurement, or at least one aperiodic NZP CSI-RS resource for interference measurement.

[0532] As one embodiment, the first resource set consists of one or more aperiodic RS resources; the first resource set consists of at least one of at least one aperiodic CSI-RS resource for channel measurement, at least one aperiodic CSI-IM resource for interference measurement, or at least one aperiodic NZP CSI-RS resource for interference measurement.

[0533] As an example, the first resource set consists of at least one CSI-RS resource.

[0534] As an example, the first resource set includes at least one of CSI-RS resources or SS / PBCH block resources.

[0535] As one embodiment, the first resource set includes at least one transmission timing of each RS resource in the first resource set no later than that of the reference resource.

[0536] As one embodiment, the first resource set includes at least one transmission timing of each RS resource in at least one RS resource in the first resource set no later than the reference resource.

[0537] As one embodiment, the first resource set includes at least one transmission timing of at least one RS resource in the first resource set no later than that of the reference resource.

[0538] As one embodiment, the first resource set includes at least one RS resource in the first resource set at a transmission time no later than the most recent transmission time of the reference resource.

[0539] As one embodiment, the first resource set includes one or more transmission times of at least one RS resource in the first resource set that are no later than the most recent transmission time of the reference resource.

[0540] As one embodiment, the first resource set includes all transmission times of at least one RS resource in the first resource set no later than the reference resource.

[0541] As an example, the reference resource is a CSI reference resource.

[0542] As an example, the reference resource is the CSI reference resource of the target CSI.

[0543] As an example, the advantages of the above method include: using existing standards and system designs, reducing complexity.

[0544] As an example, when the generation of the target CSI is based on AI, the first resource set includes at least one transmission opportunity for each RS resource in a subset of the RS resources in the first resource set; when the generation of the target CSI is not based on AI, the first resource set includes at least one transmission opportunity for each RS resource in the first resource set.

[0545] As an example, when the generation of the target CSI is based on AI, the first resource set includes at least one transmission opportunity of only the first RS in the first resource set; when the generation of the target CSI is not based on AI, the first resource set includes at least one transmission opportunity of each RS resource in the first resource set.

[0546] As an example, the essence of the above method includes configuring different sets of transmission opportunities for AI-based and non-AI-based schemes, respectively.

[0547] As an example, the advantages of the above method include: it fully considers processing capabilities based on AI and without AI, and has greater flexibility and adaptability.

[0548] As an example, when the generation of the target CSI is based on AI, the first resource set includes one or more transmission times of at least one RS resource in the first resource set that are no later than the reference resource; when the generation of the target CSI is not based on AI, the first resource set includes at least one RS resource in the first resource set that are no later than the reference resource.

[0549] As an example, the essence of the above method includes: for solutions that are not based on AI, using current system designs and standards.

[0550] As an example, the essence of the above method includes: configuring more transmission opportunities for AI-based solutions.

[0551] As an example, the advantages of the above method include: enhanced forward and backward compatibility of the system with minimal changes to existing systems and standards.

[0552] As an example, the target CSI reporting configuration indicates at least one resource configuration, and the at least one resource configuration indicates the first resource set.

[0553] As an example, the target CSI reporting configuration includes at least one resource configuration, which indicates the first resource set.

[0554] As an example, a resource configuration is used to configure CSI resources.

[0555] As an example, a resource configuration is an IE CSI-ResourceConfig.

[0556] As an example, a resource configuration is carried by an RRC IE.

[0557] As an example, a resource configuration is carried by the CSI-ResourceConfig IE.

[0558] As an example, the target CSI reports configuration information indicating the configuration of the first resource set.

[0559] As an example, the target CSI reporting configuration indicates the identifier of the first resource set.

[0560] As an example, the target CSI reporting configuration indicates at least one resource configuration, and the at least one resource configuration indicates the second resource set.

[0561] As an example, the target CSI reporting configuration includes at least one resource configuration, which indicates the second resource set.

[0562] As one embodiment, the second resource set includes the first resource set and resources outside the first resource set.

[0563] As one embodiment, the first resource set includes one or more RS resources, the second resource set includes one or more RS resources, and the second resource set includes the first resource set and RS resources outside the first resource set.

[0564] As an example, the number of resources included in the first resource set is less than the number of resources included in the second resource set.

[0565] As an example, the number of RS resources included in the first resource set is less than the number of RS resources included in the second resource set.

[0566] As one embodiment, the second resource set includes resources that do not belong to the first resource set.

[0567] As one embodiment, the second resource set includes antenna ports that do not belong to the first resource set.

[0568] As one embodiment, the second resource set includes resources that do not belong to the first resource set, and the resources in the second resource set include at least one of antenna ports, TCI status, QCL information, frequency resources, time and frequency code resources, beams, RS resources, vectors, or matrices.

[0569] As one example, the second resource set includes at least one training dataset.

[0570] As an example, the second resource set is used to train an AI model.

[0571] As one embodiment, the second resource set includes one or more RS (Reference Signal) resource sets, and an RS resource set includes one or more RS resources.

[0572] As one embodiment, the second resource set includes at least one of at least a CSI-RS resource set, at least one CSI-SSB (Channel State Information-Synchronization Signal Block) resource set, or at least one CSI-IM (Channel State Information-Interference Measurement) resource set.

[0573] As one embodiment, the second resource set includes at least one RS resource set for channel measurement, and an RS resource set for channel measurement includes one or more RS resources.

[0574] As one embodiment, the second resource set includes at least one RS resource set for channel measurement and at least one RS resource set for interference measurement; an RS resource set for channel measurement includes one or more RS resources, and an RS resource set for interference measurement includes one or more RS resources.

[0575] As one embodiment, the second resource set includes at least one RS resource set for interference measurement; an RS resource set for interference measurement includes one or more RS resources.

[0576] As one embodiment, the second resource set includes one or more RS resources.

[0577] As one embodiment, the second resource set includes one or more downlink RS resources.

[0578] As one embodiment, the second resource set includes one or more RS resources, and any RS resource in the second resource set is a CSI-RS (Channel State Information Reference Signal) resource or a synchronization signal resource.

[0579] As an example, the target CSI reporting configuration indicates at least one resource configuration, and the at least one resource configuration indicates the first resource set and the second resource set.

[0580] As an example, the target CSI reporting configuration includes at least one resource configuration, which indicates the first resource set and the second resource set.

[0581] As an example, the target CSI reporting configuration indicates a resource configuration, wherein the resource configuration indicates the first resource set and the second resource set.

[0582] As an example, the target CSI reporting configuration instruction includes two resource configurations, which respectively indicate the first resource set and the second resource set.

[0583] As an example, the target CSI reports configuration information indicating the configuration of the second resource set.

[0584] As an example, the target CSI reporting configuration indicates the identifier of the second resource set.

[0585] As one embodiment, the target CSI reporting configuration is used to indicate the second resource set from the reference resource set.

[0586] As one example, the target CSI reporting configuration indicates a first type of identifier, and the second resource set depends on the first type of identifier.

[0587] As one embodiment, the second resource set depends on the first type of identifier, which is used to identify the second resource set.

[0588] As one embodiment, the second resource set depends on the first type of identifier, which is used to identify a reference resource set, the reference resource set including the second resource set.

[0589] As one embodiment, the second resource set depends on the first type of identifier, which includes: the first type of identifier is used to identify a reference resource set, the reference resource set including the second resource set, and the target CSI reporting configuration is used to indicate the second resource set from the reference resource set.

[0590] As an example, the target CSI reports information beyond the configuration to indicate the second resource set.

[0591] As one example, the information instructing the target CSI of the second resource set to report beyond the configuration includes higher-level parameters.

[0592] As an example, the information beyond the target CSI reporting configuration for the second resource set includes RRC parameters.

[0593] As an example, the information beyond the target CSI reporting configuration indicating the second resource set includes part or all of an RRC IE domain.

[0594] As one example, the information beyond the configuration for the target CSI to report to the second resource set includes MAC CE.

[0595] As an example, the information beyond the configuration for the target CSI to report to the second resource set includes DCI (downlink control information).

[0596] As an example, the target CSI indicates at least one resource in the first resource set.

[0597] As an example, the target CSI indicates at least one resource in a second resource set, the second resource set including resources that do not belong to the first resource set.

[0598] As an example, when the target CSI is generated based on training or AI, the target CSI indicates at least one resource in a second resource set, the second resource set including resources that do not belong to the first resource set.

[0599] As an example, when the target CSI is generated based on training or AI, the target CSI indicates at least one resource in a second resource set, the second resource set including resources that do not belong to the first resource set; when the target CSI is not generated based on training or AI, the target CSI indicates at least one resource in the first resource set.

[0600] As an example, the advantages of the above method include reducing the overhead required to obtain the target CSI.

[0601] As an example, the advantages of the above method include reducing the measurement resources required to obtain the target CSI.

[0602] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0603] As one embodiment, whether the resource indicated by the target CSI belongs to the first resource set depends on whether the generation of the target CSI is based on training or AI; when the generation of the target CSI is based on training or AI, the resource indicated by the target CSI belongs to the second resource set, and the second resource set includes resources that do not belong to the first resource set; when the generation of the target CSI is not based on training or AI, the resource indicated by the target CSI belongs to the first resource set.

[0604] As one embodiment, whether the RS resource indicated by the target CSI belongs to the first resource set depends on whether the generation of the target CSI is based on training or AI; when the generation of the target CSI is based on training or AI, the resource indicated by the target CSI belongs to the second resource set, and the second resource set includes resources that do not belong to the first resource set; the resource indicated by the target CSI belongs to the first resource set only when the generation of the target CSI is not based on training or AI.

[0605] As an example, the advantages of the above method include: supporting AI-based solutions while remaining compatible with existing systems and standards, thereby improving system flexibility.

[0606] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0607] As an example, the target CSI is generated using AI, and the first node is not required to measure the second resource set.

[0608] As an example, the target CSI is generated using AI, with the first resource set used for measurement and the second resource set used for prediction.

[0609] As an example, the target CSI is generated using AI, with the first resource set used for measurement and the second resource set used for prediction.

[0610] As an example, the target CSI is generated based on AI, and only the first resource set is used for measurement, between the first resource set and the second resource set.

[0611] As one embodiment, using only the first resource set in the first resource set and the second resource set for measurement includes: using only the first resource set in the first resource set and the second resource set for measurement by the first node.

[0612] As one embodiment, the first resource set being used for measurement only in the first resource set and the second resource set includes: the first resource set being used for measurement by the first node, and the first node not being required to measure some or all of the resources in the second resource set.

[0613] As one embodiment, the first node not being required to measure the second resource set includes: the first node not measuring some or all of the resources in the second resource set.

[0614] As one embodiment, the first node not being required to measure the second resource set includes: whether the first node measures some or all of the resources in the second resource set is implementation-related or determined by the first node itself.

[0615] Example 7

[0616] Example 7 illustrates a schematic diagram of a first operation according to an embodiment of this application; as shown in Figure 7.

[0617] In Example 7, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI is generated by performing a first operation, the input of the first operation depends on the measurement based on the first resource set, and the target CSI depends on the output of the first operation.

[0618] As an example, the first operation is based on training or AI.

[0619] As an example, the first operation is obtained through training.

[0620] As an example, the first operation is based on a neural network.

[0621] As one example, the first operation includes an AI entity.

[0622] As an example, the first operation includes a portion of an AI entity.

[0623] As an example, the first operation includes a portion of an AI entity used for inference.

[0624] As an example, the first operation is performed by an AI entity.

[0625] As an example, the first operation is performed by an AI function.

[0626] As an example, the AI ​​function includes at least one of AI inference function, AI training function, and AI management function.

[0627] As one example, the training for obtaining the first operation is performed by the first node.

[0628] As an example, the training for obtaining the first operation is performed by the MDA (Management Data Analytics Function).

[0629] As an example, the training for obtaining the first operation is performed by the MDAS (Management Data Analytics Service) producer.

[0630] As an example, the training for obtaining the first operation is performed by NWDAF (Network Data Analytics Function).

[0631] As an example, the training for obtaining the first operation is performed by the core network.

[0632] As an example, the training for obtaining the first operation is performed by an AI training producer.

[0633] As an example, the first operation includes inference.

[0634] As an example, the first operation is AI inference.

[0635] As an example, the first operation includes AI inference for CSI.

[0636] As an example, the first operation is AI inference for CSI.

[0637] As an example, the first operation includes AI inference for at least one of beam prediction, CSI prediction, CSI estimation, or CSI compression.

[0638] As an example, the benefits of the above method include: improving the performance of CSI (including beam) measurement and reporting, including more accurate CSI, lower reference signal overhead and reporting overhead, thereby improving the overall system performance.

[0639] As an example, the advantages of the above method include: more accurate and complete CSI, lower reference signal overhead, and improved real-time performance of CSI.

[0640] As an example, the first operation requires deployment.

[0641] As an example, the first operation is obtained by loading.

[0642] As an example, the first operation is obtained from the serving cell of the first node.

[0643] As an example, the first operation is obtained from the maintenance base station loading of the serving cell of the first node.

[0644] As an example, the first operation is obtained from the core network.

[0645] As an example, the first operation includes one or more of convolution, pooling, cascading, and activation.

[0646] As an example, the first operation includes at least one of a fully connected layer, a pooling layer, at least one convolutional layer, and at least one coding layer.

[0647] As an example, an encoding layer includes at least one convolutional layer and one pooling layer.

[0648] 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.

[0649] As an example, some or all of the following parameters in the first operation—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.

[0650] 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 in the first operation are obtained through training.

[0651] As one example, the first operation includes preprocessing.

[0652] As an example, the preprocessing includes one or more of matrix decomposition, matrix transformation, and projection.

[0653] As an example, the preprocessing includes one or more of quantization, spatial-to-angular-domain transformation, angular-to-spatial-domain transformation, frequency-to-time-domain transformation, and time-to-frequency-domain transformation.

[0654] As an example, the preprocessing includes at least one of truncation and / or padding, DFT (Discrete Fourier Transform), mapping, and labeling.

[0655] As one example, the first operation includes post-processing.

[0656] As an example, the post-processing includes at least one of DFT (Discrete Fourier Transform), quantization, truncation, and / or padding.

[0657] As an example, the post-processing includes one or more of the following: 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.

[0658] As one embodiment, the measurement based on the first resource set includes uncompressed channel information, and the output of the first operation includes compressed channel information.

[0659] As an example, the advantages of the above method include: it is suitable for channel compression and saves feedback overhead.

[0660] As one embodiment, the measurement based on the first resource set includes measured channel information, and the output of the first operation includes predicted channel information.

[0661] As one embodiment, the measurement based on the first resource set includes channel information obtained from the measurement, and the output of the first operation includes spatial beam prediction.

[0662] As an example, the advantages of the above method include: reducing RS resource overhead and reducing feedback latency.

[0663] As an example, the measurement based on the first resource set includes historical channel information, and the output of the first operation includes predicted channel information.

[0664] As one embodiment, the measurement based on the first resource set includes historical channel information, and the output of the first operation includes temporal beam prediction.

[0665] 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.

[0666] As one embodiment, the measurement based on the first resource set includes current channel information, and the output of the first operation includes channel information after a period of time.

[0667] As an example, the benefits of the above method include: improved CSI accuracy and real-time performance, and reduced RS overhead.

[0668] As one embodiment, the measurement based on the first resource set includes incomplete channel information, while the output of the first operation includes complete channel information.

[0669] As an example, the benefits of the above method include: reducing RS overhead and improving the accuracy and completeness of CSI.

[0670] As an example, the measurement based on the first resource set includes channel information of P1 antenna ports, and the output of the first operation includes channel information of P2 antenna ports, where P1 and P2 are positive integers greater than 1, and P1 is less than P2.

[0671] As a sub-implementation of the above embodiment, the P1 antenna ports are a proper subset of the P2 antenna ports.

[0672] As a sub-implementation of the above embodiment, the P2 antenna ports belong to the second resource set.

[0673] As an example, the input to the first operation also includes the second resource set.

[0674] As an example, the output of the first operation includes one or more of the following: beam indication, CRI (CSI-RS Resource Indicator), SS / PBCH Block Resource indicator (SSBRI), or RSRP (reference signal received power).

[0675] As an example, the output of the first operation includes one or more of PMI, CRI, CQI, RI, LI, SSBRI, RSRP, SINR, capability index, and TDCP.

[0676] As an example, the output of the first operation includes one or more of the following: channel impulse response, small-scale characteristics, and channel matrix.

[0677] As an example, the output of the first operation includes one or more of delay spread, Doppler spread, Doppler shift, average delay, and average gain.

[0678] As an example, the output of the first operation includes the target CSI.

[0679] As an example, the input to the first operation depends on a measurement of the first resource set.

[0680] As an example, the generation of the target CSI is AI-based, and the input of the first operation depends on the measurement of the first resource set.

[0681] As one embodiment, the input dependence of the first operation on measurements based on the first resource set includes: measurements based on the first resource set (channel measurements and / or interference measurements) being used to generate the input of the first operation.

[0682] As an example, the target CSI depends on the output of the first operation.

[0683] As an example, the target CSI depends on the output of the first operation, including: the target CSI includes the output of the first operation.

[0684] As an example, the target CSI depends on the output of the first operation, including: the target CSI includes the post-processed output of the first operation.

[0685] As an example, the target CSI depends on the output of the first operation, which includes: the output of the first operation being used to generate the target CSI.

[0686] As an example, the target CSI depends on the output of the first operation, which is then post-processed and used to generate the target CSI.

[0687] As an example, the input of the first operation depends on the measurement of the first resource set, and the target CSI depends on the output of the first operation.

[0688] As one embodiment, the generation of the target CSI includes performing a first operation, the input of which depends on a measurement based on the first resource set, and the target CSI depends on the output of the first operation.

[0689] As an example, the advantages of the above method include: supporting AI-based solutions and improving the accuracy and real-time performance of information reporting.

[0690] As an example, the benefits of the above method include: improving the overall performance of the system.

[0691] As an example, the first type of identifier is a non-negative integer.

[0692] As an example, the first type of identifier is a string.

[0693] As an example, the first type of identifier is a model identifier.

[0694] As an example, the first type of identifier is used to identify an AI model, AI entity, or AI function.

[0695] As an example, the first type of identifier is used by the first node to identify an AI model, AI entity, or AI function.

[0696] As an example, the target CSI reporting configuration indicates the use of an AI model, AI entity, or AI function by indicating the first type of identifier.

[0697] As an example, the target CSI reporting configuration obtains input of AI entities / functions / inferences associated with the first type of identifier by instructing the first type of identifier.

[0698] As an example, the first type of identifier is used to identify or indicate a set of resources.

[0699] 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.

[0700] As an example, the first type of identifier is used to identify or indicate a set of resources.

[0701] As an example, the first type of identifier is used to identify or indicate the training dataset.

[0702] As an example, the first operation is associated with a first type of identifier.

[0703] As an example, the first operation is associated with a first type of identifier, and the target identifier is a first type of identifier.

[0704] As an example, the target CSI reporting configuration indicates a first type of identifier, and the first operation is associated with the first type of identifier.

[0705] As an example, the target CSI reporting configuration indicates the first operation by indicating the first type of identifier.

[0706] As an example, the AI ​​model used in the first operation is identified by the first type of identifier.

[0707] As an example, the AI ​​entity or AI function to which the first operation belongs is identified by the first type of identifier.

[0708] As an example, the AI ​​entity or AI function that performs the first operation is identified by the first type of identifier.

[0709] 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 entities / functions across multiple nodes.

[0710] As one embodiment, the first type of identifier is used to identify or indicate a set of reference resources, and the measurement of the set of reference resources is used to obtain a training dataset for the first operation.

[0711] As an example, the first type of identifier is used to identify the configuration information of the reference resource set, and the measurement of the reference resource set is used to obtain the training dataset for the first operation.

[0712] As one embodiment, the training for obtaining the first operation is identified by the first type of identifier.

[0713] As an example, the dataset used for training the first operation is identified by the first type of identifier.

[0714] As an example, the target CSI reporting configuration indicates the first operation by indicating the first type of identifier.

[0715] 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.

[0716] As an example, the first operation performs spatial beam prediction for a second resource set based on measurements of the first resource set, the second resource set depending on the first type of identifier.

[0717] As an example, the advantages of the above method include: reducing RS resource overhead and reducing feedback latency.

[0718] As one embodiment, the first operation performs channel information prediction for a second resource set based on measurements of the first resource set, the second resource set depending on the first type of identifier.

[0719] As an example, the channel information in this application includes beam information.

[0720] As an example, the first operation performs temporal beam prediction for a second resource set based on historical measurements of the first resource set, the second resource set depending on the first type of identifier.

[0721] As an example, the advantages of the above method include: reducing beam feedback delay and improving the real-time performance of beam acquisition.

[0722] As one embodiment, the first operation performs temporal channel information prediction for a second resource set based on historical measurements of the first resource set, the second resource set depending on the first type of identifier.

[0723] 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.

[0724] Example 8

[0725] Example 8 illustrates a schematic diagram of how the generation of a target CSI according to an embodiment of this application is associated with a target identifier; as shown in Figure 8.

[0726] In Example 8, the method of generating the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

[0727] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI does not include the first operation.

[0728] As an example, the method of generating the target CSI without being associated with the target identifier includes: the first operation is not associated with the target identifier.

[0729] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI includes performing a first operation, the first operation being unrelated to the target identifier.

[0730] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI includes performing a first operation, the first operation being associated with a first type identifier, the first type identifier associated with the first operation being different from the target identifier, and the target identifier being a first type identifier.

[0731] As an example, the advantages of the above method include: improving the flexibility of the system and adapting to transmission and application in different scenarios.

[0732] As an example, the benefits of the above method include: improving the reliability and robustness of the system.

[0733] As one embodiment, the first operation associated with the target identifier includes: the first operation is associated with at least one identifier, the at least one identifier including the target identifier.

[0734] As one embodiment, the first operation not being associated with the target identifier includes: the first operation being associated with at least one identifier, wherein the at least one identifier does not include the target identifier.

[0735] As an example, the advantages of the above method include: improving the flexibility of the system.

[0736] As one embodiment, the first operation being associated with the target identifier includes: the first operation being identified by the target identifier.

[0737] As an example, the first operation not being associated with the target identifier includes: the first operation not being identified by the target identifier.

[0738] As an example, the first operation associated with the target identifier includes: the first operation is associated with a first type identifier, the first type identifier associated with the first operation is the same as the target identifier, and the target identifier is a first type identifier.

[0739] As an example, the first operation not being associated with the target identifier includes: the first operation being associated with a first type identifier, the first type identifier associated with the first operation being different from the target identifier, and the target identifier being a first type identifier.

[0740] As an example, the first operation being associated with the target identifier includes: the AI ​​model used in the first operation being identified by the target identifier.

[0741] As an example, the first operation not being associated with the target identifier includes: the first operation not using the AI ​​model identified by the target identifier.

[0742] As an example, the first operation not being associated with the target identifier includes: the first operation not employing an AI model.

[0743] As one embodiment, the first operation being associated with the target identifier includes: the AI ​​entity to which the first operation belongs is identified by the target identifier.

[0744] As an example, the first operation not being associated with the target identifier includes: the AI ​​entity to which the first operation belongs is not identified by the target identifier.

[0745] As one embodiment, the first operation associated with the target identifier includes: the execution of the first operation is for an AI function identified by the target identifier.

[0746] As an example, the first operation not being associated with the target identifier includes: the execution of the first operation is not for the AI ​​function identified by the target identifier.

[0747] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0748] As an example, the advantages of the above method include: simplifying system design and reducing the complexity of implementing the solution.

[0749] As one embodiment, the first operation associated with the target identifier includes: the first operation being associated with the target identifier through the target CSI reporting configuration.

[0750] As an example, the first operation not being associated with the target identifier includes: the first operation being configured to not be associated with the target identifier through the target CSI reporting configuration.

[0751] As one embodiment, the first operation associated with the target identifier includes: the target CSI reporting configuration indicating a first type of identifier; the target CSI reporting configuration indicating the first operation; and the target identifier being the first type of identifier.

[0752] As one embodiment, the first operation not associated with the target identifier includes: the target CSI reporting configuration indicates a first type of identifier; the target CSI reporting configuration indicates the first operation; the target identifier is not a first type of identifier.

[0753] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0754] As an example, the advantages of the above method include: improving the forward and backward compatibility of the system.

[0755] Example 9

[0756] Example 9 illustrates a schematic diagram of how the generation of a target CSI is associated with a target identifier according to another embodiment of this application; as shown in Figure 9.

[0757] In Example 9, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

[0758] As an example, the method of generating the target CSI and associating it with the target identifier includes: the method of generating the target CSI is associated with the target identifier through the target CSI reporting configuration.

[0759] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI is configured not to be associated with the target identifier through the target CSI reporting configuration.

[0760] As an example, the method of generating the target CSI and associating it with the target identifier includes: the method of generating the target CSI is associated with a first type of identifier through the target CSI reporting configuration, and the first type of identifier is the same as the target identifier.

[0761] As an example, the method of generating the target CSI is not associated with the target identifier, including: the method of generating the target CSI is associated with a first type of identifier through the target CSI reporting configuration, and the first type of identifier is different from the target identifier.

[0762] As an example, the method of generating the target CSI is associated with the target identifier, which includes: the method of generating the target CSI is associated with at least one identifier through the target CSI reporting configuration, and the at least one identifier includes the target identifier.

[0763] As an example, the method of generating the target CSI without being associated with the target identifier includes: the method of generating the target CSI is associated with at least one identifier through the target CSI reporting configuration, wherein the at least one identifier does not include the target identifier.

[0764] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0765] As an example, the advantages of the above method include: improving the forward and backward compatibility of the system.

[0766] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI reporting configuration indicates a first type identifier, and the first type identifier indicated by the target CSI reporting configuration is different from the target identifier.

[0767] As an example, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates at least one identifier, and the at least one identifier includes the target identifier.

[0768] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI reporting configuration indicates at least one identifier, wherein the at least one identifier does not include the target identifier.

[0769] As an example, the advantages of the above method include: improving the flexibility of the system.

[0770] As an example, the generation method of the target CSI is associated with the target identifier, including: the target CSI reporting configuration indicates a first type of identifier; the target CSI reporting configuration indicates the generation method of the target CSI; and the target identifier is the same as the first type of identifier.

[0771] As an example, the generation method of the target CSI is not associated with the target identifier, including: the target CSI reporting configuration indicates a first type of identifier; the target CSI reporting configuration indicates the generation method of the target CSI; the target identifier and the first type of identifier are different.

[0772] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0773] Example 10

[0774] Example 10 illustrates a schematic diagram of a target information block indicating a target identifier according to an embodiment of this application; as shown in Figure 10.

[0775] In Example 10, the target information block indicates the target identifier.

[0776] As an example, the target information block explicitly indicates the target identifier.

[0777] As an example, the target information block implicitly indicates the target identifier.

[0778] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0779] As one embodiment, the target information block indicating the target identifier includes: the target information block indicating at least one identifier, the at least one identifier including the target identifier.

[0780] As one embodiment, the target information block indicating the target identifier includes: the target information block indicating a first type of identifier, wherein the first type of identifier is the same as the target identifier.

[0781] As one embodiment, the target information block indicating the target identifier includes: the target information block indicating a first type of identifier, the first type of identifier being associated with the target identifier.

[0782] As an example, the advantages of the above method include: improving the flexibility of the system and adapting to different scenarios and applications.

[0783] As one embodiment, the target information block indicates that the target identifier includes: the target information block indicates at least one AI model, AI entity, or AI function, and the at least one AI model, AI entity, or AI function is associated with the target identifier.

[0784] As one embodiment, the target information block indicates that the target identifier includes: the target information block indicates the AI ​​model, AI entity, or AI function identified by the target identifier.

[0785] As an example, the target information block indicates that the target identifier includes: the target information block indicates that the AI ​​model identified by the target identifier has failed or is ineffective.

[0786] As an example, the target information block indicates that the target identifier includes: the target information block indicates the performance metrics of the AI ​​model identified by the target identifier.

[0787] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0788] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0789] As an example, the benefits of the above method include: improving the accuracy and effectiveness of CSI reporting and improving the overall performance of the system.

[0790] As one embodiment, the target information block indicating the target identifier includes: the target information block includes first information, the first information indicating the target identifier.

[0791] As an example, the benefits of the above method include: improving the stability and robustness of the system.

[0792] Example 11

[0793] Example 11 illustrates a schematic diagram of at least one information block according to an embodiment of this application; as shown in Figure 11.

[0794] In embodiment 11, at least one information block is received, the at least one information block configuring or indicating at least one signal; wherein, the target information block is generated based on the reception or measurement of some or all of the at least one signal.

[0795] As an example, the at least one information block is indicated by a physical layer signaling.

[0796] As an example, the at least one information block is indicated by at least one physical layer signaling.

[0797] As one embodiment, the at least one information block is indicated by higher-level signaling.

[0798] As an example, the at least one information block belongs to a DCI (Downlink Control Information).

[0799] As an example, the at least one information block belongs to at least one DCI (Downlink Control Information).

[0800] As one embodiment, the target identifier is used to identify or indicate a set of resources; the at least one signal belongs to the set of resources identified or indicated by the target identifier.

[0801] As one embodiment, the target identifier is used to identify or indicate a set of resources, the measurement of which is used to obtain a training dataset; the at least one signal belongs to the set of resources identified or indicated by the target identifier.

[0802] As one embodiment, the target identifier is used to identify or indicate the training dataset; the measurement of the at least one signal is used to obtain some or all of the data in the training dataset.

[0803] As one embodiment, the target identifier is used to identify or indicate a testing dataset; the measurement of the at least one signal is used to obtain some or all of the data in the testing dataset.

[0804] As one embodiment, the target identifier is used to identify or indicate a validation dataset; the measurement of the at least one signal is used to obtain some or all of the data in the validation dataset.

[0805] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0806] As an example, the at least one signal includes at least one PDSCH.

[0807] As one embodiment, the at least one signal includes at least one PDSCH; the target information block is generated based on the reception or measurement of some or all of the at least one signal and includes: the target information block includes all HARQ-ACK bits of the at least one PDSCH.

[0808] As an example, the at least one signal includes at least one reference signal.

[0809] As an example, the at least one signal includes at least one reference signal; the measurement of the at least one reference signal is used for training the AI ​​model identified by the target identifier.

[0810] As an example, the at least one signal includes at least one reference signal; the measurement of the at least one reference signal is used for testing the AI ​​model identified by the target identifier.

[0811] As an example, the at least one signal includes at least one reference signal; the measurement of the at least one reference signal is used for the validation of the AI ​​model identified by the target identifier.

[0812] As one embodiment, the at least one signal includes at least one reference signal; the target information block is generated based on the reception or measurement of some or all of the at least one signal, including the reception quality of the at least one reference signal.

[0813] As a sub-example of the above embodiments, the reception quality is RSRP.

[0814] As a sub-example of the above embodiments, the reception quality is SINR.

[0815] As a sub-example of the above embodiments, the reception quality is BLER.

[0816] As an example, the measurement of the at least one signal is used to generate the input of the AI ​​model identified by the target identifier; the target information block is generated based on the reception or measurement of some or all of the at least one signal and includes: the target information block includes the performance metrics of the AI ​​model identified by the target identifier.

[0817] As an example, the measurement of the at least one signal is used to obtain some or all of the data in the training dataset; the target information block is generated based on the reception or measurement of some or all of the at least one signal and includes: the target information block includes the performance metrics of the AI ​​model identified by the target identifier.

[0818] As an example, the measurement of the at least one signal is used to obtain some or all of the data in the testing dataset; the target information block is generated based on the reception or measurement of some or all of the at least one signal and includes: the target information block includes the performance metrics of the AI ​​model identified by the target identifier.

[0819] As an example, the measurement of the at least one signal is used to obtain some or all of the data in the validation dataset; the target information block is generated based on the reception or measurement of some or all of the at least one signal and includes: the target information block includes the performance metrics of the AI ​​model identified by the target identifier.

[0820] As an example, the essence of the above method includes: monitoring the AI ​​model by reporting relevant performance parameters based on AI's CSI.

[0821] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0822] As an example, the target information block indicates the performance index of the AI ​​model identified by the target identifier, which is determined based on the reception or measurement of some or all of the at least one signal.

[0823] As an example, the target information block indicates that the AI ​​model identified by the target identifier has failed or is ineffective, and the failure or ineffectiveness of the AI ​​model identified by the target identifier is determined based on the reception or measurement of some or all of the at least one signal.

[0824] As an example, the target information block indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the number of times the AI ​​model identified by the target identifier has failed or malfunctioned is determined based on the reception or measurement of some or all of the at least one signal.

[0825] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0826] As an example, the benefits of the above method include: improving the stability and robustness of the system.

[0827] Example 12

[0828] Example 12 illustrates a schematic diagram of a target identifier depending on at least one information block according to an embodiment of the present application; as shown in Figure 12.

[0829] In embodiment 12, the target identifier depends on the at least one information block.

[0830] As an example, the at least one information block indicates the target identifier.

[0831] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0832] As an example, the at least one information block indicates at least one identifier, and the at least one identifier includes the target identifier.

[0833] As one embodiment, the at least one information block indicates a first type of identifier, which is the same as the target identifier.

[0834] As one embodiment, the at least one information block indicates a first type of identifier, which is associated with the target identifier.

[0835] As an example, the at least one information block indicates at least one AI model, AI entity, or AI function, which is associated with the target identifier.

[0836] As an example, the at least one information block indicates the AI ​​model, AI entity, or AI function identified by the target identifier.

[0837] As an example, the advantages of the above method include: improving the flexibility of the system and adapting to different scenarios and applications.

[0838] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used for training the AI ​​model identified by the target identifier.

[0839] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used for testing the AI ​​model identified by the target identifier.

[0840] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used for the validation of the AI ​​model identified by the target identifier.

[0841] As one embodiment, the target identifier is used to identify or indicate a set of resources; the at least one information block indicates at least one reference signal, the at least one reference signal indicated by the at least one information block belonging to the set of resources identified or indicated by the target identifier.

[0842] As one embodiment, the target identifier is used to identify or indicate a resource set, the measurement of which is used to obtain a training dataset; the at least one information block indicates at least one reference signal, the at least one reference signal indicated by the at least one information block belonging to the resource set identified or indicated by the target identifier.

[0843] As one embodiment, the target identifier is used to identify or indicate the training dataset; the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to obtain some or all of the data in the training dataset.

[0844] As one embodiment, the target identifier is used to identify or indicate a resource set, the measurement of which is used to obtain a testing dataset; the at least one information block indicates at least one reference signal, the at least one reference signal indicated by the at least one information block belonging to the resource set identified or indicated by the target identifier.

[0845] As one embodiment, the target identifier is used to identify or indicate a testing dataset; the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to obtain some or all of the data in the testing dataset.

[0846] As one embodiment, the target identifier is used to identify or indicate a set of resources, the measurement of which is used to obtain a validation dataset; the at least one information block indicates at least one reference signal, the at least one reference signal indicated by the at least one information block belonging to the set of resources identified or indicated by the target identifier.

[0847] As one embodiment, the target identifier is used to identify or indicate a validation dataset; the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to obtain some or all of the data in the validation dataset.

[0848] As an example, the advantages of the above method include: supporting AI-based CSI reporting.

[0849] As an example, the advantages of the above method include: enhancing the flexibility of the system and adapting to different scenarios and applications.

[0850] As an example, the at least one information block is used to determine the target identifier.

[0851] As an example, the at least one information block includes one or more HARQ-ACK bits, and the target identifier depends on the one or more HARQ-ACK bits.

[0852] As an example, the measurement of the at least one information block is used to determine the target identifier.

[0853] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to determine the target identifier.

[0854] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to generate a performance metric for the AI ​​model identified by the target identifier.

[0855] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to generate a failure or malfunction of the AI ​​model identified by the target identifier.

[0856] As an example, the at least one information block indicates at least one reference signal, and the measurement of the at least one reference signal indicated by the at least one information block is used to generate the number of failures or malfunctions of the AI ​​model identified by the target identifier.

[0857] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0858] As an example, the benefits of the above method include: improving the reliability and robustness of the system.

[0859] Example 13

[0860] Example 13 illustrates a schematic diagram of a first value and a first threshold according to an embodiment of the present application; as shown in Figure 13.

[0861] In Example 13, the first value is greater than the first threshold, and the first value depends on the target information block.

[0862] As an example, the first value is an integer, and the first threshold is an integer.

[0863] As an example, the first value is a positive integer, and the first threshold is a positive integer.

[0864] As an example, the first value is a real number, and the first threshold is a real number.

[0865] As an example, the first value is a positive real number, and the first threshold is a positive real number.

[0866] As an example, the first value is a non-negative real number, and the first threshold is a non-negative real number.

[0867] As an example, the first value is a positive real number not greater than 1, and the first threshold is a positive real number less than 1.

[0868] As an example, the first value is a boolean value, and the first threshold is a boolean value.

[0869] As an example, the target information block includes the first value.

[0870] As an example, the target information block includes at least one value, and the at least one value includes the first value.

[0871] As an example, the target information block indicates the first value.

[0872] As an example, the target information block indicates at least one value, the at least one value including the first value.

[0873] As an example, the advantages of the above method include: simplifying system design and reducing implementation complexity.

[0874] As one embodiment, the at least one signal includes at least one reference signal; the target information block indicates a first value, which is the reception quality of the at least one reference signal.

[0875] As one embodiment, the at least one signal includes at least one reference signal; the target information block indicates a first value, which is the difference between the received quality measured by the at least one reference signal and the predicted received quality of the at least one reference signal.

[0876] As an example, the essence of the above method includes: monitoring CSI reporting through system performance parameters.

[0877] As an example, the benefits of the above method include: improving the performance of the CSI reporting scheme and improving the overall performance of the system.

[0878] As an example, the target information block indicates a first value, which is a performance metric of the AI ​​model identified by the target identifier.

[0879] As an example, the target information block indicates a first value, which indicates the failure or malfunction of the AI ​​model identified by the target identifier.

[0880] As an example, the target information block indicates a first value, which is the number of times the AI ​​model identified by the target identifier has failed or malfunctioned.

[0881] As an example, the essence of the above method includes: monitoring the AI ​​model by reporting relevant performance parameters based on AI's CSI.

[0882] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0883] As an example, the target information block includes one or more bits, the first value depending on the number of bits in the target information block that are 0.

[0884] As an example, the target information block includes one or more bits, and the first value is the number of bits in the target information block that have a value of 0.

[0885] As an example, the target information block includes one or more bits, and the first value is equal to the number of bits in the target information block that are 0 divided by the total number of bits in the target information block.

[0886] As an example, the target information block includes one or more HARQ-ACK bits, the first value depending on the number of HARQ-ACK bits in the target information block that have a value of NACK.

[0887] As an example, the target information block includes one or more HARQ-ACK bits, and the first value is the number of HARQ-ACK bits with a value of NACK in the target information block.

[0888] As an example, the target information block includes one or more HARQ-ACK bits, and the first value is equal to the number of HARQ-ACK bits with a value of NACK in the target information block divided by the total number of HARQ-ACK bits included in the target information block.

[0889] As an example, the advantages of the above method include: minimal changes to existing standards and system design, and enhanced forward and backward compatibility of the system.

[0890] As an example, the benefits of the above method include: improving the reliability and robustness of the system.

[0891] As an example, the target information block includes N information sub-blocks, each of the N information sub-blocks includes at least one bit, and N is a positive integer greater than 1; the N information sub-blocks are used to determine a first value, the first value being greater than a first threshold.

[0892] As an example, the N information sub-blocks are transmitted on the same physical layer channel.

[0893] As an example, at least two of the N information sub-blocks are transmitted on different physical layer channels.

[0894] As an example, the N information sub-blocks are transmitted on the same PUSCH.

[0895] As an example, the N information sub-blocks are transmitted on the same PUCCH.

[0896] As an example, at least two of the N information sub-blocks are transmitted on different physical layer channels, which are PUCCH or PUSCH.

[0897] As an example, the advantages of the above method include: minimal changes to existing standards and system design, and enhanced forward and backward compatibility of the system.

[0898] As an example, any one of the N information sub-blocks includes HARQ-ACK bits.

[0899] As an example, the first value depends on the number of HARQ-ACK bits with a value of NACK in the N information sub-blocks.

[0900] As an example, the first value is the number of HARQ-ACK bits with a value of NACK in the N information sub-blocks.

[0901] As an example, the first value is equal to the number of HARQ-ACK bits with a value of NACK in the N information sub-blocks divided by the total number of HARQ-ACK bits included in the N information sub-blocks.

[0902] As an example, the advantages of the above method include: minimal changes to existing standards and system design, and enhanced forward and backward compatibility of the system.

[0903] As an example, the benefits of the above method include: improving the reliability and robustness of the system.

[0904] As an example, any one of the N information sub-blocks indicates that the AI ​​model identified by the target identifier has failed or is ineffective, and the first value depends on the failure or ineffectiveness of the AI ​​model identified by the target identifier indicated by the N information sub-blocks.

[0905] As an example, any one of the N information sub-blocks indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, and the first value is equal to the sum of the number of times the AI ​​model identified by the target identifier has failed or malfunctioned as indicated by the N information sub-blocks.

[0906] As an example, any one of the N information sub-blocks indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, and the first value is equal to the average number of times the AI ​​model identified by the target identifier has failed or malfunctioned as indicated by the N information sub-blocks.

[0907] As an example, any one of the N information sub-blocks indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, and the first value is equal to the maximum value of the number of times the AI ​​model identified by the target identifier has failed or malfunctioned as indicated by the N information sub-blocks.

[0908] As an example, any one of the N information sub-blocks indicates a performance metric of the AI ​​model identified by the target identifier, and the first value depends on the performance metric of the AI ​​model identified by the target identifier indicated by the N information sub-blocks.

[0909] As an example, any one of the N information sub-blocks indicates the performance index of the AI ​​model identified by the target identifier, and the first value is equal to the average value of the performance index of the AI ​​model identified by the target identifier indicated by the N information sub-blocks.

[0910] As an example, any one of the N information sub-blocks indicates the performance index of the AI ​​model identified by the target identifier, and the first value is equal to the maximum value of the performance index of the AI ​​model identified by the target identifier indicated by the N information sub-blocks.

[0911] As an example, any one of the N information sub-blocks indicates the performance index of the AI ​​model identified by the target identifier, and the first value is equal to the minimum value of the performance index of the AI ​​model identified by the target identifier indicated by the N information sub-blocks.

[0912] As an example, the advantages of the above method include: more precise control of the system, and improved system stability and overall performance.

[0913] Example 14

[0914] Example 14 illustrates a schematic diagram of the triggering conditions of a target information block according to an embodiment of this application; as shown in Figure 14.

[0915] In embodiment 14, the triggering condition for the target information block includes a first value greater than a first threshold; wherein,

[0916] The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer;

[0917] or,

[0918] The first value depends on the reception or measurement of some or all of the at least one signal.

[0919] As an example, the failure or ineffectiveness of the AI ​​model identified by the target identifier is determined based on the reception or measurement of some or all of the at least one signal.

[0920] As an example, when the reception quality of the at least one reference signal is worse than a second threshold, the value of the first counter is incremented by 1, where the first value is the value of the first counter.

[0921] As an example, when the difference between the received quality of the at least one reference signal and the predicted received quality of the at least one reference signal is greater than a second threshold, the value of the first counter is incremented by 1, where the first value is the value of the first counter.

[0922] As an example, the value of the first counter is the number of times the AI ​​model identified by the target identifier has failed or malfunctioned.

[0923] As an example, the essence of the above method includes: monitoring the performance of the AI ​​model, and the monitoring results affecting the transmission of the system.

[0924] As an example, the benefits of the above method include: improving the accuracy and effectiveness of AI-based CSI reporting and enhancing the overall system performance.

[0925] As an example, the target information block includes one or more HARQ-ACK bits, which are determined based on the reception or measurement of some or all of the signals in the at least one signal.

[0926] As an example, when there is a HARQ-ACK bit with a value of NACK among the one or more HARQ-ACK bits, the value of the first counter is added to the number of HARQ-ACK bits with a value of NACK among the one or more HARQ-ACK bits, and the first value is the value of the first counter.

[0927] As an example, when the number of HARQ-ACK bits with a value of NACK in one or more HARQ-ACK bits is greater than a second threshold, the value of the first counter is incremented by 1, and the first value is the value of the first counter.

[0928] As an example, when the number of HARQ-ACK bits with a value of NACK in the one or more HARQ-ACK bits is divided by the total number of bits in the one or more HARQ-ACK bits and is greater than a second threshold, the value of the first counter is incremented by 1, and the first value is the value of the first counter.

[0929] As an example, the value of the first counter is the number of HARQ-ACK bits with a value of NACK in the target information block.

[0930] As an example, the advantages of the above method include: minimal changes to existing standards and system design, and enhanced forward and backward compatibility of the system.

[0931] As an example, the benefits of the above method include: improving the reliability and robustness of the system.

[0932] As an example, the performance metric of the AI ​​model identified by the target identifier is determined based on the reception or measurement of some or all of the at least one signal.

[0933] As an example, when the performance index of the AI ​​model identified by the target identifier is less than the second threshold, the value of the first counter is incremented by 1, and the first value is the value of the first counter.

[0934] As an example, the essence of the above method includes: when the performance index of the AI ​​model (such as prediction accuracy) is less than a certain threshold, the AI ​​model fails or becomes ineffective.

[0935] As an example, when the performance index of the AI ​​model identified by the target identifier is greater than the second threshold, the value of the first counter is incremented by 1, and the first value is the value of the first counter.

[0936] As an example, the essence of the above method includes: when the performance index of the AI ​​model (such as the difference between the predicted value and the actual value) is greater than a certain threshold, the AI ​​model fails or becomes ineffective.

[0937] As an example, the value of the first counter indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned.

[0938] As an example, the essence of the above method includes: monitoring the AI ​​model by reporting relevant performance parameters based on AI's CSI.

[0939] As an example, the benefits of the above method include: improving the performance of AI-based CSI reporting schemes and enhancing the overall performance of the system.

[0940] As an example, the first counter is maintained at a higher level than the first node.

[0941] As an example, when the reception quality of the at least one reference signal is worse than a second threshold, the physical layer of the first node sends a first type of indication to a higher layer. After receiving the first type of indication, the higher layer of the first node increments the value of the first counter by 1. The first value is the value of the first counter.

[0942] As an example, when the number of HARQ-ACK bits with a value of NACK in one or more HARQ-ACK bits is greater than a second threshold, the physical layer of the first node sends a first type of indication to a higher layer. After receiving the first type of indication, the higher layer of the first node increments the value of the first counter by 1. The first value is the value of the first counter.

[0943] As an example, when the number of HARQ-ACK bits with a value of NACK in one or more HARQ-ACK bits is divided by the total number of bits in one or more HARQ-ACK bits and is greater than a second threshold, the physical layer of the first node sends a first type of indication to a higher layer. After receiving the first type of indication, the higher layer of the first node increments the value of a first counter by 1. The first value is the value of the first counter.

[0944] As an example, when there is a HARQ-ACK bit with a value of NACK among the one or more HARQ-ACK bits, the physical layer of the first node sends a first type of indication to the higher layer. After receiving the first type of indication, the higher layer of the first node adds the value of the first counter to the number of HARQ-ACK bits with a value of NACK among the one or more HARQ-ACK bits, where the first value is the value of the first counter.

[0945] As an example, when the performance index of the AI ​​model identified by the target identifier is less than the second threshold, the physical layer of the first node sends a first type of indication to the higher layer. After receiving the first type of indication, the higher layer of the first node increments the value of the first counter by 1. The first value is the value of the first counter.

[0946] As an example, when the performance index of the AI ​​model identified by the target identifier is greater than the second threshold, the physical layer of the first node sends a first type of indication to the higher layer. After receiving the first type of indication, the higher layer of the first node increments the value of the first counter by 1. The first value is the value of the first counter.

[0947] As an example, the first type of indication indicates that the AI ​​model identified by the target identifier has failed or is ineffective.

[0948] As an example, the first type of indication indicates that the reception quality of the at least one reference signal is worse than a second threshold.

[0949] As an example, the first type of indication indicates that the difference between the received quality of the at least one reference signal and the predicted received quality of the at least one reference signal is greater than a second threshold.

[0950] As an example, the first type of indication indicates that the performance index of the AI ​​model identified by the target identifier is greater than a second threshold.

[0951] As an example, the first type of indication indicates that the performance index of the AI ​​model identified by the target identifier is less than a second threshold.

[0952] As an example, the first type of indication indicates that there is a HARQ-ACK bit with a value of NACK among the one or more HARQ-ACK bits.

[0953] As an example, the first type of indication indicates the number of HARQ-ACK bits with a value of NACK among the one or more HARQ-ACK bits.

[0954] As an example, the first type of indication indicates that the number of HARQ-ACK bits with a value of NACK in the one or more HARQ-ACK bits is greater than a second threshold.

[0955] As an example, the first type of indication indicates that the number of HARQ-ACK bits with a value of NACK among the one or more HARQ-ACK bits divided by the total number of bits of the one or more HARQ-ACK bits is greater than a second threshold.

[0956] As an example, the advantages of the above method include: adopting a hierarchical structure, simplifying system design, and reducing implementation complexity.

[0957] Example 15

[0958] Example 15 illustrates a schematic diagram of a second operation according to an embodiment of this application; as shown in Figure 15.

[0959] In Example 15, the output of the first operation includes a first CSI, the target CSI carries the first CSI, and the first CSI is used as input to the second operation by the target receiver of the target CSI to generate a second CSI.

[0960] As an example, the first operation is used for CSI compression, the second operation is used for CSI recovery, and the first node and the second node adopt a two-sided AI model.

[0961] As an example, the target CSI includes the first CSI.

[0962] As an example, the first CSI is post-processed and used to generate the target CSI.

[0963] As one embodiment, the first CSI includes N sub-CSIs, and the N information blocks respectively carry the N sub-CSIs.

[0964] As an example, the first CSI includes the output of the first operation.

[0965] As one embodiment, the second CSI includes the recovery of at least a portion of the input of the first operation.

[0966] As an example, the second CSI includes one or more of the following: PMI (Precoding Matrix Indicator), CRI (CSI-RS Resource Indicator), SS / PBCH Block Resource Indicator (SSBRI), beam indicator, resource indicator, CQI (Channel Quality Indicator), RI (Rank Indicator), Layer Indicator (LI), RSRP (Reference Signal Received Power), SINR (Signal-to-noise and Interference Ratio), Capability Index, or TDCP (Time Domain Channel Properties).

[0967] As one embodiment, the second CSI includes one or more of the following: channel matrix, eigenvector, eigenvalue, or precoding matrix.

[0968] As an example, the second operation is the inverse operation of the first operation.

[0969] As an example, the second operation is based on training.

[0970] As an example, the training for obtaining the second operation is performed by the target receiver of the target CSI.

[0971] As one example, the training for obtaining the second operation is performed by the MDA function.

[0972] As an example, the training for obtaining the second operation is performed by the MDAS producer.

[0973] As an example, the training for obtaining the second operation is performed by NWDAF.

[0974] As an example, the training for obtaining the second operation is performed by the core network.

[0975] As an example, the training for obtaining the second operation is performed by an AI (Artificial Intelligence) training producer.

[0976] As an example, the first operation and the second operation are obtained through different training.

[0977] As an example, the first operation and the second operation are obtained through independent training.

[0978] As an example, the advantages of the above method include: saving air interface overhead, having better flexibility, being adaptable to different terminals, and having better forward compatibility.

[0979] As an example, the first operation and the second operation are obtained through joint training.

[0980] As an example, the benefits of the above method include: optimizing system performance.

[0981] As an example, the training of the second operation depends on the first operation.

[0982] As an example, the producer of the second operation trains the second operation based on the output of the first operation.

[0983] Example 16

[0984] Example 16 illustrates a schematic diagram of a first operation according to another embodiment of this application; as shown in Figure 16. In Example 16, the first operation includes K1 sub-operations, where K1 is a positive integer not greater than 1.

[0985] In Example 16, the K1 sub-operations are respectively represented as sub-operation #0, ..., sub-operation #(K1-1).

[0986] As an example, each of the K1 sub-operations is based on training.

[0987] As an example, at least one of the K1 sub-operations is based on training.

[0988] As an example, each of the K1 training-based sub-operations is based on the same training executor.

[0989] As an example, two of the K1 sub-operations are based on different training executors.

[0990] As an example, at least one of the K1 sub-operations needs to be deployed.

[0991] As an example, at least one of the K1 sub-operations needs to be loaded.

[0992] As an example, all the sub-operations that need to be loaded in the K1 sub-operations are loaded from the same producer.

[0993] As an example, two of the K1 sub-operations that need to be loaded are loaded from different producers.

[0994] As an example, at least one of the K1 sub-operations is not based on training.

[0995] As an example, at least one of the K1 sub-operations is based on a codebook for precoding defined in 3GPP R18 or a version prior to 3GPP R18.

[0996] As an example, one or more of the K1 sub-operations are AI-based.

[0997] As an example, one or more of the K1 sub-operations include inference.

[0998] As an example, one or more of the K1 sub-operations include AI inference.

[0999] As an example, one or more of the K1 sub-operations include AI inference for CSI.

[1000] As an example, one or more of the K1 sub-operations include preprocessing.

[1001] As an example, one or more of the K1 sub-operations include post-processing.

[1002] As an example, among the K1 sub-operations, two sub-operations are sequential, such as all the sub-operations in Figure 16(a), sub-operations #2 to #(K1-1) in 16(b), and sub-operations #0 to #(K1-4) in 16(c).

[1003] As an example, the two sub-operations being serial means that the output of one of the two sub-operations is used as the input of the other of the two sub-operations.

[1004] As an example, among the K1 sub-operations, two sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in Figure 16(b), and sub-operation #(K1-3) and sub-operation #(K1-2) in Figure 16(c).

[1005] As an example, two sub-operations being parallel means that the outputs of the two sub-operations are used together as the input of another sub-operation.

[1006] As an example, the K1 sub-operations include one or more of convolution, pooling, cascading, or activation.

[1007] As an example, one of the K1 sub-operations includes a fully connected layer.

[1008] As an example, one of the K1 sub-operations includes a pooling layer.

[1009] As an example, one of the K1 sub-operations includes at least one convolutional layer.

[1010] As an example, one of the K1 sub-operations includes at least one coding layer.

[1011] As an example, two of the K1 sub-operations include a fully connected layer and at least one coding layer.

[1012] As an example, an encoding layer includes at least one convolutional layer and one pooling layer.

[1013] Example 17

[1014] Example 17 illustrates a schematic diagram of the deployment of a first operation according to an embodiment of this application; as shown in Figure 17.

[1015] In Example 17, the first processor deploys the first operation.

[1016] As one embodiment, the deployment includes obtaining the first operation.

[1017] As one example, the deployment includes obtaining an AI entity.

[1018] As one example, the deployment includes obtaining an AI entity that performs the first operation.

[1019] As one example, the deployment includes obtaining an AI entity that includes AI functions to perform the first operation.

[1020] As one embodiment, the deployment includes loading the first operation.

[1021] As one example, the deployment includes submitting a request to load the first operation.

[1022] As an example, the request in Figure 16 is a request from the first node to load the first operation.

[1023] As an example, the response in Figure 16 is a response to the request made by the first node to load the first operation.

[1024] As an example, the first node obtains the first operation through the response shown in Figure 16.

[1025] As an example, the first operation is obtained from the serving cell of the first node.

[1026] As an example, the first operation is obtained from the sustaining base station of the serving cell of the first node.

[1027] As an example, the first operation is obtained from the core network.

[1028] As an example, the first operation is obtained from loading from the first producer.

[1029] As an example, the first producer provides the first operation to the first node via the response shown in Figure 16.

[1030] As an example, the deployment is accomplished by an AI function.

[1031] As an example, the deployment is accomplished by AI functionality deployed on the first node.

[1032] As an example, the deployment is accomplished by an AI deployment function.

[1033] As an example, the deployment is accomplished by the AI ​​deployment function deployed on the first node.

[1034] As an example, the deployment is accomplished using AI inference functionality.

[1035] As an example, the deployment is accomplished by an AI inference function deployed on the first node.

[1036] As an example, the deployment is performed by an AI entity.

[1037] As an example, the deployment is performed by an AI entity deployed on the first node.

[1038] As an example, the deployment is performed by an AI entity with a deployment function.

[1039] As an example, the deployment is performed by an AI entity with deployment capabilities deployed on the first node.

[1040] As an example, the deployment is accomplished by an AI entity with an inference function.

[1041] As an example, the deployment is performed by an AI entity with inference capabilities deployed on the first node.

[1042] As one embodiment, the deployment includes obtaining the first operation from a first producer.

[1043] As one embodiment, the deployment includes requesting a first producer to load the first operation.

[1044] As one embodiment, the deployment includes loading the first operation from the first producer.

[1045] As an example, the first producer generates and provides at least one of AL entities and AL functions.

[1046] As an example, the first producer is the producer of the first operation.

[1047] As an example, the first producer includes an AL entity producer.

[1048] As one example, the first producer includes an AL function producer.

[1049] As one example, the first producer includes an AL deployment producer.

[1050] As one example, the first producer includes an AL loading producer.

[1051] As one example, the first producer includes an AL-trained producer.

[1052] As an example, the first producer includes an AL inference producer.

[1053] As an example, the first producer includes the producer of the AL entity deployment.

[1054] As one example, the first producer includes the producer that loads the AL entity.

[1055] As an example, the first producer includes an MnS (Management Service) producer.

[1056] As an example, the sender of the target CSI reporting configuration is the first producer.

[1057] As an example, the sender of the target CSI reporting configuration is different from the first producer.

[1058] As an example, the training for obtaining the first operation is performed by the first producer.

[1059] As an example, the executor used to obtain the training for the first operation is different from the first producer.

[1060] Example 18

[1061] Example 18 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 18. The gNB in ​​Example 18 can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[1062] 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.

[1063] 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).

[1064] 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.

[1065] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[1066] In Example 18, the RAN domain ML training function 1802 is located in the RAN domain management function 1803; while the ML inference function is located in the base station, that is, the AI / ML inference function 1804 is located in gNB1805, and the AI / ML inference function 1806 is located in gNB1807.

[1067] In Figure 18, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1803, that is, data interaction with RAN domain MnS (Management Service) consumer / cross-domain management 1801 (as shown by the dashed arrow in Figure 18).

[1068] 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 1801.

[1069] It should be noted that Example 18 is merely a non-limiting implementation; 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.

[1070] As an example, one of the gNBs (or base stations) in Example 18 is the second node of this application.

[1071] As one embodiment, the second processor includes an AL / ML inference function, namely 1804 or 1806, as shown in Figure 18.

[1072] As an example, an AL / ML inference function in Figure 18 performs ML training based on the target precoding vector; the target reference signal is different from the first reference signal; any one of the plurality of reference signals other than the first reference signal is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[1073] Example 19

[1074] Example 19 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 19. The RAN domain ML training function 1905 in Figure 19 is optional.

[1075] UE function 1904 is deployed in the first node of this application, and the UE function 1904 includes AI / ML inference function 1906; the AI / ML inference function 1906 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[1076] As an example, the UE function 1904 includes a RAN domain ML training function 1905, 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.

[1077] 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.

[1078] Optionally, the UE function 1904 also includes a CN domain ML training function (not shown in Figure 19).

[1079] Optionally, the UE function 1904 also includes an AI / ML deployment function (not shown in Figure 19) for loading ML models and data.

[1080] 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.

[1081] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[1082] Optionally, the UE function 1904 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1901, and / or the RAN domain MnF 1902, and / or the cross-domain management system 1903 for management or analysis (as shown by double arrow 1907).

[1083] Optionally, the UE function 1904 is an MnS consumer that loads data from the CN domain MnF (Management Function) 1901, and / or the RAN domain MnF 1902, and / or the cross-domain management system 1903 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1907).

[1084] As an example, the first channel information in this application is obtained through inference by the AI / ML inference function 1906.

[1085] As an example, the RAN domain ML training function 1905 performs ML training based on a target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[1086] As an example, the first processor includes an AL / ML inference function 1906 in Figure 19.

[1087] As an example, the ML model is based on a neural network.

[1088] As an example, the ML model is based on CNN (Conventional Neural Networks).

[1089] As an example, the ML model is based on the Transformer architecture.

[1090] Example 20

[1091] Example 20 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 20. Figure 20 includes a third processor, a fourth processor, a fifth processor, and a sixth processor.

[1092] In Example 20, 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-class parameter set based on the first dataset, and sends the generated target first-class parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-class parameter set to obtain a first-class output, and (optionally) the fifth processor sends the first-class output to the sixth processor. In Figure 20, the first-class feedback and the second-class feedback are optional; the fourth processor includes ML training functionality; the fifth processor includes ML inference functionality.

[1093] As one embodiment, the sixth processor includes ML testing functionality.

[1094] As an example, the sixth processor includes performance monitoring / evaluation of the ML model.

[1095] As an example, the fifth processor sends a first type of feedback to the fourth processor. The first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[1096] 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.

[1097] As one embodiment, the third processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[1098] As one embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[1099] As an example, the first type of output includes the first channel information.

[1100] As an example, the first type of output includes the index of the target reference signal.

[1101] As one embodiment, the second dataset includes measurements for the first reference signal, or includes measurements for the second reference signal.

[1102] As an example, the first dataset includes training data.

[1103] As an example, the fourth processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[1104] As an example, the fourth processor belongs to the first node.

[1105] The above embodiments avoid passing the first dataset to the second node.

[1106] As one example, the fourth processor belongs to the second node.

[1107] The above embodiments support joint training and optimize system performance.

[1108] As an example, the fourth processor belongs to the core network.

[1109] The above embodiments support network-wide joint training, further optimizing system performance.

[1110] As an example, the second dataset includes inference data.

[1111] As an example, the fifth processor belongs to the first node.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] 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.

[1116] 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.

[1117] 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.

[1118] Example 21

[1119] Example 21 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 21. Figure 21 includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation; the arrowed lines indicate the sequence of the processes.

[1120] In Example 21, 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.

[1121] As an example, the third operation includes AI / ML training, the fourth operation includes AI / ML testing, the fifth operation includes AI / ML emulation, the sixth operation includes AI / ML entity loading, and the seventh operation includes AI / ML inference.

[1122] As one embodiment, 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.

[1123] As an example, the first stage includes AI / ML model training.

[1124] As an example, the first stage includes AI / ML model training and AI / ML testing.

[1125] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[1126] As an example, the training of the AI / ML model depends on training data.

[1127] As an example, the AI / ML model training includes AI / ML entity validation.

[1128] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[1129] As an example, the AI / ML entity verification relies on verification data.

[1130] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[1131] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[1132] As an example, if the AI / ML test results meet expectations, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[1133] As an example, the AI / ML test relies on test data.

[1134] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity inference in a simulation environment.

[1135] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[1136] As one embodiment, the second stage is optional.

[1137] As an example, the third stage includes AI / ML entity loading, which is to obtain trained AI / ML entities to obtain the desired AI / ML inference function.

[1138] As an example, the third stage is optional.

[1139] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[1140] As an example, the fourth stage includes AI / ML inference.

[1141] As an example, the seventh operation includes the first operation.

[1142] As an example, the seventh operation includes the second operation.

[1143] Example 22

[1144] Example 22 illustrates a structural block diagram of a processing apparatus in a first node according to an embodiment of this application; as shown in Figure 22. In Figure 22, the processing apparatus 2200 in the first node includes a first receiver 2201 and a first processor 2202.

[1145] The first receiver 2201 receives the target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI.

[1146] The first processor 2202 sends a target information block; determines whether to abandon sending the target CSI; when the first condition is met, it abandons sending the target CSI.

[1147] In Example 22, determining whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with a target identifier; the target identifier depends on the target information block.

[1148] As one embodiment, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI indicates at least one resource in a second resource set, which includes resources that do not belong to the first resource set.

[1149] As one embodiment, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the generation of the target CSI includes performing a first operation, the input of which depends on the measurement based on the first resource set, and the target CSI depends on the output of the first operation.

[1150] As an example, the method of generating the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

[1151] As an example, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

[1152] As an example, the target information block indicates the target identifier.

[1153] As one embodiment, the first receiver 2201 receives at least one information block, the at least one information block configuring or indicating at least one signal; wherein, the target information block is generated based on the reception or measurement of some or all of the at least one signal.

[1154] As one example, the target identifier depends on the at least one information block.

[1155] As an example, the first value is greater than a first threshold, and the first value depends on the target information block.

[1156] As one embodiment, the triggering condition for the target information block includes a first value greater than a first threshold; wherein,

[1157] The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer;

[1158] or,

[1159] The first value depends on the reception or measurement of some or all of the at least one signal.

[1160] As an example, the first processor 2202 deploys the first operation.

[1161] As an example, the first operation is associated with the first type of identifier.

[1162] As an example, the first operation is based on training or AI.

[1163] As one embodiment, the second processor 2301 deploys the second operation.

[1164] As one example, the second operation is based on training or AI.

[1165] As one embodiment, the second processor 2301 performs a second operation; wherein the output of the first operation includes the first CSI, the target CSI carries the first CSI, and the first CSI is used as input to the second operation by the target receiver of the target CSI to generate a second CSI.

[1166] As one example, the first node is a user equipment.

[1167] As one example, the user equipment is a terminal.

[1168] As an example, the first node is a relay node device.

[1169] As an example, the first receiver 2201 includes at least one of the following in embodiment 4: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[1170] As one embodiment, the first processor 2202 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}.

[1171] Example 23

[1172] Example 23 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 23. In Figure 23, the processing apparatus 2300 in the second node includes a second processor 2301.

[1173] The second processor 2301 sends the target CSI reporting configuration; receives the target information block; determines whether to abandon receiving the target CSI; and abandons receiving the target CSI when the first condition is met.

[1174] The target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSI is generated based on training or AI; the target receiver of the target CSI reporting configuration determines whether to abandon sending the target CSI; when a first condition is met, the target receiver of the target CSI reporting configuration abandons sending the target CSI; the determination of whether the target receiver of the target CSI reporting configuration abandons sending the target CSI depends on whether the first condition is met; the first condition includes the target CSI generation method being associated with a target identifier; the target identifier depends on the target information block.

[1175] As one embodiment, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI indicates at least one resource in a second resource set, which includes resources that do not belong to the first resource set.

[1176] As one embodiment, the target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the generation of the target CSI includes performing a first operation, the input of which depends on the measurement based on the first resource set, and the target CSI depends on the output of the first operation.

[1177] As an example, the method of generating the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

[1178] As an example, the generation method of the target CSI associated with the target identifier includes: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

[1179] As an example, the target information block indicates the target identifier.

[1180] As one embodiment, the second processor 2301 sends at least one information block, the at least one information block configuring or indicating at least one signal; wherein, the target information block is generated based on the reception or measurement of some or all of the at least one signal.

[1181] As one example, the target identifier depends on the at least one information block.

[1182] As an example, the first value is greater than a first threshold, and the first value depends on the target information block.

[1183] As one embodiment, the triggering condition for the target information block includes a first value greater than a first threshold; wherein,

[1184] The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer;

[1185] or,

[1186] The first value depends on the reception or measurement of some or all of the at least one signal.

[1187] As one embodiment, the second processor 2301 deploys the second operation.

[1188] As one example, the second operation is based on training or AI.

[1189] As one embodiment, the second processor 2301 performs a second operation; wherein the output of the first operation includes the first CSI, the target CSI carries the first CSI, and the first CSI is used as input to the second operation by the target receiver of the target CSI to generate a second CSI.

[1190] As an example, the first processor 2202 deploys the first operation.

[1191] As an example, the first operation is associated with the first type of identifier.

[1192] As an example, the first operation is based on training or AI.

[1193] In one embodiment, the second node is a base station device.

[1194] In one embodiment, the second node is a user equipment.

[1195] As one example, the user equipment is a terminal.

[1196] As one embodiment, the second node is a relay node device.

[1197] As one embodiment, the second processor 2301 includes at least one of the following in embodiment 4: {antenna 420, receiver / transmitter 418, receiving processor 470, transmitting processor 416, multi-antenna receiving processor 472, multi-antenna transmitting processor 471, controller / processor 475, memory 476}.

[1198] 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 devices, wireless sensors, internet cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, gNB (NR Node B), TRP (Transmitter Receiver Point), and other wireless communication equipment.

[1199] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any changes and modifications made based on the embodiments described in the specification, if they achieve similar partial or complete technical effects, should be considered obvious and fall within the scope of protection of this invention.

Claims

1. A method for a first node in wireless communication, characterized in that, include: Receive target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI. Send the target information block; determine whether to abandon sending the target CSI; when the first condition is met, abandon sending the target CSI; The determination of whether to abandon sending the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; The target identifier depends on the target information block.

2. The method according to claim 1, characterized in that, The target CSI reporting configuration indicates a first resource set, which is used for at least one of the channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI indicates at least one resource in a second resource set, which includes resources that do not belong to the first resource set.

3. The method according to claim 1 or 2, characterized in that, The target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI is generated by performing a first operation, the input of which depends on the measurement based on the first resource set, and the target CSI depends on the output of the first operation.

4. The method according to claim 3, characterized in that, The generation method of the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

5. The method according to any one of claims 1 to 4, characterized in that, The generation method of the target CSI is associated with the target identifier, including: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

6. The method according to any one of claims 1 to 5, characterized in that, The target information block indicates the target identifier.

7. The method according to any one of claims 1 to 5, characterized in that, include: Receive at least one information block, wherein the at least one information block configures or indicates at least one signal; The target information block is generated based on the reception or measurement of some or all of the signals in the at least one signal.

8. The method according to claim 7, characterized in that, The target identifier depends on the at least one information block.

9. The method according to claim 7 or 8, characterized in that, The first value is greater than the first threshold, and the first value depends on the target information block.

10. The method according to claim 7 or 8, characterized in that, The triggering condition for the target information block includes a first value greater than a first threshold; wherein, The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer; or, The first value depends on the reception or measurement of some or all of the at least one signal.

11. A terminal, characterized in that, The terminal includes: one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1-10.

12. A method for a second node in wireless communication, characterized in that, include: Send target CSI reporting configuration; the target CSI reporting configuration is used to configure the reporting of target CSIs; the target CSIs are generated based on training or AI. Receive the target information block; determine whether to abandon receiving the target CSI; When the first condition is met, the reception of the target CSI is abandoned; Specifically, the target receiver configured to report the target CSI determines whether to abandon sending the target CSI; when a first condition is met, the target receiver configured to report the target CSI abandons sending the target CSI; the determination of whether to abandon sending the target CSI by the target receiver configured to report the target CSI depends on whether the first condition is met; the first condition includes the generation method of the target CSI being associated with the target identifier; the target identifier depends on the target information block.

13. The method according to claim 12, characterized in that, The target CSI reporting configuration indicates a first resource set, which is used for at least one of the channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI indicates at least one resource in a second resource set, which includes resources that do not belong to the first resource set.

14. The method according to claim 12 or 13, characterized in that, The target CSI reporting configuration indicates a first resource set, which is used for at least one of channel measurement or interference resource measurement of the target CSI, and the first resource set includes one or more RS resources; the target CSI is generated by performing a first operation, the input of which depends on the measurement based on the first resource set, and the target CSI depends on the output of the first operation.

15. The method according to claim 14, characterized in that, The generation method of the target CSI is associated with the target identifier, including: the first operation is associated with the target identifier.

16. The method according to any one of claims 12 to 15, characterized in that, The generation method of the target CSI is associated with the target identifier, including: the target CSI reporting configuration indicates a first type identifier, the first type identifier indicated by the target CSI reporting configuration is the same as the target identifier, and the target identifier is a first type identifier.

17. The method according to any one of claims 12 to 16, characterized in that, The target information block indicates the target identifier.

18. The method according to any one of claims 12 to 16, characterized in that, include: Send at least one information block, wherein the at least one information block configures or indicates at least one signal; The target information block is generated based on the reception or measurement of some or all of the signals in the at least one signal.

19. The method according to claim 18, characterized in that, The target identifier depends on the at least one information block.

20. The method according to claim 18 or 19, characterized in that, The first value is greater than the first threshold, and the first value depends on the target information block.

21. The method according to claim 18 or 19, characterized in that, The triggering condition for the target information block includes a first value greater than a first threshold; wherein, The first value indicates the number of times the AI ​​model identified by the target identifier has failed or malfunctioned, the first value is a non-negative integer, and the first threshold is a positive integer; or, The first value depends on the reception or measurement of some or all of the at least one signal.

22. A base station, characterized in that, The base station includes: one or more processors and a memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the base station to perform the method as described in any one of claims 12-21.

Images