Method and device for reporting channel information in wireless communication node

Abstract

The invention discloses a method and a device for reporting channel information in a wireless communication node. The first node receives the first information block; the first information block indicates a first time domain resource and a second time domain resource; sending the first CSI on the first time domain resource, or giving up to send the first CSI on the first time domain resource; only when the first CSI is transmitted on the first time domain resource, transmitting a second CSI on the second time domain resource; wherein the first CSI and the second CSI depend on the output of the first reasoning and the output of the second reasoning, respectively; the output of the first reasoning comprises a first output and a second output, the first CSI depends on the first output, and the input of the second reasoning comprises the second output; the method and the device support CSI reporting based on AI, determine whether to send the CSI reporting and the sending mode thereof, improve the CSI reporting performance, reduce the resource overhead of the system, and improve the overall performance of the system.

Description

Technical Field

[0001] This application relates to a transmission method and apparatus in a wireless communication system, and particularly to a solution and apparatus for reporting inference-based channel information in a wireless communication system. Background Art

[0002] In traditional wireless communication, a UE (User Equipment) reports various auxiliary information obtained by measuring downlink signals and / or channels, such as channel information, auxiliary information related to beam management, auxiliary information related to positioning, and so on. The 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 indication. The UE can use this information by itself to select appropriate transmission parameters or report this information. The network device selects appropriate transmission parameters for the UE according to the UE's report, such as the resident cell, MCS (Modulation and Coding Scheme), TPMI (Transmitted Precoding Matrix Indicator), TCI (Transmission Configuration Indication), and other parameters. In addition, the UE report can be used to optimize network parameters, such as better cell coverage, switching the base station according to the UE's location, and so on.

[0003] With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the improvement of system performance requirements, etc., the traditional measurement and reporting methods will bring a large amount of redundant overhead. Therefore, in NR (New Radio) Rel-18 (Release-18), the research on AI (Artificial Intelligence) / ML (Machine Learning) technology has been established to explore its impact on CSI (Channel State Information) inference, system performance, and system design. Compared with the traditional processing method, AI / ML has characteristics such as being based on training and requiring deployment. In addition, AI / ML is also a key candidate technology for future 6G communication. Summary of the Invention

[0004] The applicant has found through research that when the CSI generated based on inference is introduced, the existing measurement mechanism, reporting mechanism, and related configuration signaling may not be able to meet the requirements. In view of the above problems, the present application discloses a solution. It should be noted that in the above problem description, the NR system is used as an example, and the present application is also applicable to scenarios such as the future 6G system, achieving technical effects similar to those of the NR system; further, although the original intention of the present application is for AI / ML scenarios, the present application can also be applied to other non-AI / ML scenarios, such as traditional CSI (Channel State Information) reporting solutions; further, adopting a unified design solution 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, non-terrestrial networks (NTN), Internet of Things (IoT), ultra-reliable low-latency communication (URLLC) networks, etc.) helps to reduce hardware complexity and cost. Without conflict, the embodiments and features in any node of the present application can be applied to any other node. Without conflict, the embodiments and features in the embodiments of the present application can be combined with each other arbitrarily.

[0005] In particular, the explanations of the terms, nouns, functions, and variables in the present application (if not otherwise specified) can refer to the definitions in the 3GPP specification protocols TS28 series, TS36 series, TS38 series, and TS37 series. If necessary, the 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 referred to for assisting in understanding the present application.

[0006] The present application discloses a method in a first node for wireless communication, characterized by including:

[0007] Receiving a first information block; the first information block indicating a first time-domain resource and a second time-domain resource;

[0008] Transmitting first CSI (Channel State Information) on the first time-domain resource, or refraining from transmitting first CSI on the first time-domain resource;

[0009] Transmit a second CSI on the second time-domain resource only when the first CSI is transmitted on the first time-domain resource;

[0010] Wherein, the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0011] According to one aspect of the present application, it is characterized in that the first node is a user equipment.

[0012] According to one aspect of the present application, it is characterized in that the first node is a terminal.

[0013] According to one aspect of the present application, it is characterized in that the first node is a relay node.

[0014] As an embodiment, the user equipment is a terminal.

[0015] As an embodiment, the problems to be solved by the present application include: for the case where the input of the inference on which the second CSI depends includes the output of the inference on which the first CSI depends, how to process the reporting of the second CSI.

[0016] As an embodiment, the advantages of the above method include: supporting the association between inferences of multiple CSIs.

[0017] As an embodiment, the advantages of the above method include: minimizing CSI reporting and effectively reducing the CSI reporting overhead.

[0018] As an embodiment, the advantages of the above method include: improving the accuracy and timeliness of channel information.

[0019] As an embodiment, the advantages of the above method include: better adapting to various different application scenarios and terminals, and improving the flexibility and adaptability of the system.

[0020] As an embodiment, the advantages of the above method include: enhancing the overall performance of the system.

[0021] According to one aspect of the present application, it is characterized in that the first inference and the second inference are training-based or AI-based.

[0022] As an embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0023] As an example, the first node deploys the first inference and the second inference.

[0024] As an example, the first inference and the second inference are obtained by loading.

[0025] As an example, the advantages of the above method include: supporting an AI / ML-based CSI reporting scheme.

[0026] As an example, the advantages of the above method include: better adapting to various different application scenarios and terminals, and improving the flexibility and adaptability of the system.

[0027] As an example, the advantages of the above method include: improving the accuracy of channel information reporting, reducing the reporting overhead, and enhancing the overall performance of the system.

[0028] According to one aspect of the present application, it is characterized in that it includes:

[0029] When the first CSI is abandoned from being transmitted on the first time-domain resource, the second CSI is abandoned from being transmitted on the second time-domain resource.

[0030] As an example, the essence of the above method includes: the input of the inference on which the second CSI depends includes the output of the inference on which the first CSI depends. If the first CSI is abandoned from being transmitted, the second CSI is also abandoned from being transmitted.

[0031] As an example, the advantages of the above method include: minimizing CSI reporting as much as possible, and effectively reducing the CSI reporting overhead.

[0032] As an example, the advantages of the above method include: enhancing the overall performance of the system.

[0033] According to one aspect of the present application, it is characterized in that it includes:

[0034] When the first CSI is abandoned from being transmitted on the first time-domain resource, part or all of the information in the first CSI and part or all of the information in the second CSI are transmitted on the second time-domain resource.

[0035] As an example, the essence of the above method includes: the input of the inference on which the second CSI depends includes the output of the inference on which the first CSI depends. If the first CSI is abandoned from being transmitted on the first time-domain resource, the first CSI and the second CSI are transmitted together on the second time-domain resource.

[0036] As an embodiment, the benefits of the above method include: for the case where there is an association between the inferences of multiple CSIs, the reporting of the multiple CSIs is effectively implemented.

[0037] As an embodiment, the benefits of the above method include: ensuring the consistency of the understanding of the transmitted information between the transceiver.

[0038] As an embodiment, the benefits of the above method include: enhancing the stability, reliability, and robustness of the system.

[0039] As an embodiment, the benefits of the above method include: better adapting to various different application scenarios and transmission conditions, and improving the flexibility and adaptability of the system.

[0040] As an embodiment, the benefits of the above method include: improving the accuracy of the channel information reporting and enhancing the overall performance of the system.

[0041] According to one aspect of the present application, it is characterized in that both the first inference and the second inference are inferences corresponding to the first identifier.

[0042] As an embodiment, the benefits of the above method include: supporting the reporting of multiple consecutive and associated CSIs.

[0043] As an embodiment, the benefits of the above method include: enhancing the performance of CSI reporting, improving the accuracy and reducing the overhead.

[0044] As an embodiment, the benefits of the above method include: enhancing the flexibility of the system and adapting to different transmission environments and application scenarios.

[0045] As an embodiment, the benefits of the above method include: enhancing the overall performance of the system.

[0046] According to one aspect of the present application, it is characterized in that the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration.

[0047] As an embodiment, the benefits of the above method include: improving the estimation accuracy of the CSI.

[0048] As an embodiment, the benefits of the above method include: simplifying the system design and ensuring the consistency of the understanding of the transmitted information between the transceiver.

[0049] As an embodiment, the benefits of the above method include: reducing the overhead of the configuration information and reducing the implementation complexity of the system.

[0050] According to one aspect of the present application, when a first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and a first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0051] As an embodiment, the essence of the above method includes: when the resource for transmitting a CSI report conflicts with the resource for transmitting other signals or downlink transmission resources, abandon transmitting the CSI report.

[0052] As an embodiment, the advantages of the above method include: effectively solving the conflict between multiple transmissions and reducing the implementation complexity of the system.

[0053] As an embodiment, the advantages of the above method include: enhancing the completeness and robustness of the system.

[0054] According to one aspect of the present application, the first information block indicates a first RS resource set; at least one of the input of the first inference and the input of the second inference depends on the measurement based on the first RS resource set.

[0055] As an embodiment, the advantages of the above method include: making small changes to the standard and enhancing the forward and backward compatibility of the system.

[0056] According to one aspect of the present application, the output of the second inference depends on the output of the first inference.

[0057] As an embodiment, the advantages of the above method include: supporting the association of multiple CSI reports.

[0058] As an embodiment, the advantages of the above method include: supporting multiple consecutive and associated CSI reports.

[0059] As an embodiment, the advantages of the above method include: improving the performance of CSI reports, enhancing accuracy and reducing overhead.

[0060] As an embodiment, the advantages of the above method include: enhancing the flexibility of the system to adapt to different transmission environments and application scenarios.

[0061] As an embodiment, the advantages of the above method include: improving the overall performance of the system.

[0062] The present application discloses a method in a second node for wireless communication, including:

[0063] Send a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; wherein, the receiver of the first information block sends a first CSI on the first time-domain resource or abandons sending the first CSI on the first time-domain resource; only when the first CSI is sent by the receiver of the first information block on the first time-domain resource, the receiver of the first information block sends a second CSI on the second time-domain resource;

[0064] When the first CSI is sent by the receiver of the first information block on the first time-domain resource, receive the first CSI on the first time-domain resource and receive the second CSI on the second time-domain resource;

[0065] Wherein, the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0066] According to one aspect of the present application, it is characterized in that the second node includes a base station.

[0067] According to one aspect of the present application, it is characterized in that the second node includes a core network.

[0068] According to one aspect of the present application, it is characterized in that the second node includes a base station and a core network.

[0069] According to one aspect of the present application, it is characterized in that the second node includes a relay node.

[0070] According to one aspect of the present application, it is characterized in that the second node includes a user equipment.

[0071] As an embodiment, the user equipment is a terminal.

[0072] According to one aspect of the present application, it is characterized in that the first inference and the second inference are training-based or AI-based.

[0073] As an embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0074] As an embodiment, the receiver of the first information block deploys the first inference and the second inference.

[0075] As an embodiment, the first inference and the second inference are obtained by loading.

[0076] According to one aspect of the present application, it is characterized in that it includes:

[0077] Monitor whether the first CSI is sent by the receiver of the first information block on the first time-domain resource.

[0078] According to one aspect of the present application, it is characterized in that it includes:

[0079] Monitor whether some or all of the information in the second CSI is sent by the receiver of the first information block on the second time-domain resource.

[0080] According to one aspect of the present application, it is characterized in that it includes:

[0081] When the first CSI is abandoned from being sent by the receiver of the first information block on the first time-domain resource, the receiver of the first information block abandons sending the second CSI on the second time-domain resource.

[0082] According to one aspect of the present application, it is characterized in that it includes:

[0083] When the first CSI is abandoned from being sent by the receiver of the first information block on the first time-domain resource, abandon receiving the second CSI on the second time-domain resource.

[0084] According to one aspect of the present application, it is characterized in that it includes:

[0085] When the first CSI is abandoned from being sent by the receiver of the first information block on the first time-domain resource, receive some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource;

[0086] Wherein, the receiver of the first information block sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0087] According to one aspect of the present application, it is characterized in that both the first inference and the second inference are inferences corresponding to the first identifier.

[0088] According to one aspect of the present application, it is characterized in that the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration.

[0089] According to one aspect of the present application, when a first condition is satisfied, the first CSI is abandoned from being sent by the receiver of the first information block on the first time-domain resource; the first condition includes that the first time-domain resource and a first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0090] According to one aspect of the present application, the first information block indicates a first RS resource set; at least one of the input of the first inference and the input of the second inference depends on measurements based on the first RS resource set.

[0091] According to one aspect of the present application, the output of the second inference depends on the output of the first inference.

[0092] The present application discloses a terminal, which includes: one or more processors and a memory;

[0093] The memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the terminal to execute the method in the first node.

[0094] As an embodiment, the terminal is a user equipment.

[0095] The present application discloses a base station, which includes: one or more processors and a memory;

[0096] The memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the base station to execute the method in the second node.

[0097] The present application discloses a first node for wireless communication, which includes:

[0098] A first processor, receiving a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; sending a first CSI on the first time-domain resource, or abandoning sending the first CSI on the first time-domain resource; sending a second CSI on the second time-domain resource only when the first CSI is sent on the first time-domain resource;

[0099] Among them, the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0100] This application discloses a second node for use in wireless communication, comprising:

[0101] A second processor, configured to send a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; wherein, the receiver of the first information block sends the first CSI on the first time-domain resource or abandons sending the first CSI on the first time-domain resource; only when the first CSI is sent by the receiver of the first information block on the first time-domain resource, the receiver of the first information block sends a second CSI on the second time-domain resource;

[0102] A second processor, configured to receive the first CSI on the first time-domain resource and receive the second CSI on the second time-domain resource when the first CSI is sent by the receiver of the first information block on the first time-domain resource;

[0103] Among them, the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0104] As an embodiment, compared with traditional solutions, this application has the following advantages:

[0105] - Ensure the consistency of understanding of the CSI reporting configuration and processing between the transceiver;

[0106] - Support AI-based CSI reporting;

[0107] - Support multiple correlated CSI reports;

[0108] - Reduce meaningless CSI reports and reduce the transmission load of the system;

[0109] - Improve the accuracy of CSI reporting, reduce reporting latency and overhead;

[0110] - Better adapt to various different application scenarios or terminals, and enhance the flexibility and adaptability of the system;

[0111] - Enhance the completeness, reliability and robustness of the system;

[0112] - Improve the forward and backward compatibility of the system;

[0113] - Simplify the system design and reduce the complexity of solution implementation;

[0114] - Improve the overall performance of the system. Description of the Drawings

[0115] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non - limiting embodiments with reference to the accompanying drawings:

[0116] Figure 1 A flowchart showing a first information block, a first CSI, and a second CSI according to an embodiment of the present application;

[0117] Figure 2 A schematic diagram showing a network architecture according to an embodiment of the present application;

[0118] Figure 3 A schematic diagram showing an embodiment of a radio protocol architecture of a user plane and a control plane according to an embodiment of the present application;

[0119] Figure 4 A schematic diagram showing a first communication device and a second communication device according to an embodiment of the present application;

[0120] Figure 5 A flowchart showing a wireless transmission according to an embodiment of the present application;

[0121] Figure 6 A schematic diagram showing operations when the first CSI is abandoned for transmission according to an embodiment of the present application;

[0122] Figure 7 A schematic diagram showing operations when the first CSI is abandoned for transmission according to another embodiment of the present application;

[0123] Figure 8 A schematic diagram showing a first inference and a second inference according to an embodiment of the present application;

[0124] Figure 9 A schematic diagram showing the configuration of a first CSI and a second CSI according to an embodiment of the present application;

[0125] Figure 10 A schematic diagram showing a first condition according to an embodiment of the present application;

[0126] Figure 11 A schematic diagram showing a first RS resource set according to an embodiment of the present application;

[0127] Figure 12Shows a schematic diagram of the outputs of the first inference and the second inference according to an embodiment of the present application;

[0128] Figure 13 Shows a schematic diagram of a first given inference according to an embodiment of the present application;

[0129] Figure 14 shows a schematic diagram of deploying a first given inference according to an embodiment of the present application;

[0130] Figure 15 Shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of the present application;

[0131] Figure 16 Shows a schematic diagram based on artificial intelligence or machine learning according to an embodiment of the present application;

[0132] Figure 17 Shows a structural block diagram of a processing device in a first node according to an embodiment of the present application;

[0133] Figure 18 Shows a structural block diagram of a processing device in a second node according to an embodiment of the present application; Detailed implementation manners

[0134] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings. It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined arbitrarily. Considering aspects such as performance, flexibility, complexity, overhead, and compatibility, those skilled in the art have the motivation to flexibly combine the embodiments in different drawings on the premise of non-conflict, for example, but not limited to the embodiments in Figure 1 and the embodiments in Figure 5 - Figure 18 and the embodiments in Figure 5 and the embodiments in Figure 6 - Figure 18 and the embodiments in

[0135] Example 1

[0136] Embodiment 1 exemplifies a flowchart of a first information block, a first CSI, and a second CSI according to an embodiment of the present application, as shown in Figure 1 shown. In 100 shown in Figure 1 each box represents a step. In particular, the order of the steps in the box does not represent a specific time sequence relationship between the steps.

[0137] In Embodiment 1, the first node in the present application receives a first information block in step 101; in step 102, sends a first CSI on the first time-domain resource, or abandons sending the first CSI on the first time-domain resource; and only when the first CSI is sent on the first time-domain resource, sends a second CSI on the second time-domain resource in step 103.

[0138] Wherein, the first information block indicates a first time-domain resource and a second time-domain resource; the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0139] As an embodiment, the first information block is carried by higher layer signaling.

[0140] As an embodiment, the first information block is carried by RRC (Radio Resource Control) signaling.

[0141] As an embodiment, the first information block includes some or all fields in at least one RRC IE (Information Element).

[0142] As an embodiment, the first information block includes a MAC CE.

[0143] As an embodiment, the first information block is carried by RRC signaling and MAC (Medium Access Control) CE (Control Element) signaling.

[0144] As an embodiment, the first information block includes DCI (Downlink Control Information).

[0145] As an embodiment, the first information block includes at least one field in DCI (Downlink Control Information).

[0146] As an embodiment, the first information block includes the Time domain resource assignment field in DCI.

[0147] As an embodiment, the first information block includes the PUCCH resource indicator field in DCI.

[0148] As an embodiment, the first information block includes one or more IEs CSI-ReportConfig.

[0149] As an embodiment, the first information block includes some or all fields in one or more IEs CSI-ReportConfig.

[0150] As an embodiment, the first information block includes some or all fields in IE ServingCellConfig.

[0151] As an embodiment, the first information block includes some or all fields in IE CSI-MeasConfig IE.

[0152] As an embodiment, the first information block includes some or all fields in IE ServingCellConfigCommon IE.

[0153] As an embodiment, the first information block includes some or all fields in IE ServingCellConfig.

[0154] As an embodiment, the first time-domain resource belongs to an uplink channel, and the second time-domain resource belongs to an uplink channel.

[0155] As an embodiment, the first time-domain resource belongs to PUSCH (Physical Uplink Shared Channel), and the second time-domain resource belongs to PUSCH.

[0156] As an embodiment, the first time-domain resource belongs to PUCCH (Physical Uplink Control Channel), and the second time-domain resource belongs to PUCCH.

[0157] As an embodiment, the first time-domain resource and the second time-domain resource each include a plurality of REs (Resource Elements).

[0158] As an embodiment, the first time-domain resource occupies at least one symbol in the time domain and at least one subcarrier in the frequency domain.

[0159] As an embodiment, the first time-domain resource occupies at least one symbol in the time domain and at least one RB (resource block) in the frequency domain.

[0160] As an embodiment, the second time-domain resource occupies at least one symbol in the time domain and at least one subcarrier in the frequency domain.

[0161] As an embodiment, the second time-domain resource occupies at least one symbol in the time domain and at least one RB (resource block) in the frequency domain.

[0162] Typically, one RE occupies one symbol in the time domain and one subcarrier in the frequency domain.

[0163] As an embodiment, the symbol is a single-carrier symbol.

[0164] As an embodiment, the symbol is a multi-carrier symbol.

[0165] As an embodiment, the multi-carrier symbol is an OFDM (Orthogonal Frequency Division Multiplexing) symbol.

[0166] As an embodiment, the symbol is obtained after the output of the transform precoding passes through OFDM symbol generation.

[0167] As an embodiment, the multi-carrier symbol is an SC-FDMA (Single Carrier-Frequency Division Multiple Access) symbol.

[0168] As an embodiment, the multi-carrier symbol is a DFT-S-OFDM (Discrete Fourier Transform Spread OFDM) symbol.

[0169] As an embodiment, the multi-carrier symbol is an FBMC (Filter Bank Multi Carrier) symbol.

[0170] As an embodiment, the multi-carrier symbol includes a CP (Cyclic Prefix).

[0171] As an embodiment, the benefits of the above method include: following the existing system design and standards.

[0172] As an embodiment, the second time-domain resource is different from the first time-domain resource.

[0173] As an embodiment, the second time-domain resource is orthogonal to the first time-domain resource.

[0174] As an embodiment, the second time-domain resource and the first time-domain resource belong to different time slots respectively.

[0175] As an embodiment, the second time-domain resource is later than the first time-domain resource.

[0176] As an embodiment, the first symbol occupied by the second time-domain resource in the time domain is after the last symbol occupied by the first time-domain resource in the time domain.

[0177] As an embodiment, the first information block indicates the time interval between the first time-domain resource and the second time-domain resource.

[0178] As an embodiment, the first information block indicates a first time interval, and the second time-domain resource is after the first time interval after the first time-domain resource.

[0179] As an embodiment, the first information block indicates the first time-domain resource and the first time interval, and the second time-domain resource is after the first time interval after the first time-domain resource.

[0180] As an embodiment, the first information block indicates the first time-domain resource, and the second time-domain resource is in the next time slot after the time slot where the first time-domain resource is located.

[0181] As an embodiment, the first information block indicates the first time-domain resource, and the second time-domain resource is in the next uplink time slot after the time slot where the first time-domain resource is located.

[0182] Typically, the "after" means: later than in the time domain.

[0183] As an embodiment, the first CSI and the second CSI are periodic.

[0184] As an embodiment, the first CSI and the second CSI are semi-persistent.

[0185] As an embodiment, the first CSI and the second CSI are aperiodic.

[0186] As an embodiment, the first CSI and the second CSI are event-triggered.

[0187] As an embodiment, the first node transmits the first CSI on the first time-domain resource.

[0188] As an example, the first node transmits the second CSI on the second time-domain resource.

[0189] As an example, transmitting a CSI on a time-domain resource includes: the CSI is used to generate a signal transmitted on the time-domain resource after channel coding.

[0190] As an example, transmitting a CSI on a time-domain resource includes: the CSI is used to generate a signal transmitted on the time-domain resource after channel coding and modulation.

[0191] As an example, transmitting a CSI on a time-domain resource includes: the CSI is used to generate a signal transmitted on the time-domain resource after bit sequence generation and channel coding.

[0192] As an example, transmitting a CSI on a time-domain resource includes: the CSI is used to generate a signal transmitted on the time-domain resource after bit sequence generation, channel coding, and modulation.

[0193] As an example, transmitting a CSI on a time-domain resource includes: the CSI is used to generate a signal transmitted on the time-domain resource after bit sequence generation (bit sequence genertion), code block segmentation, CRC attachment, channel coding, rate matching, and codeblock concatenation.

[0194] As an example, transmitting a CSI on a time-domain resource includes: the CSI is multiplexed onto the time-domain resource.

[0195] As an example, transmitting a CSI on a time-domain resource includes: the CSI is multiplexed onto the time-domain resource after bit sequence generation, code block segmentation, CRC attachment, channel coding, rate matching, and codeblock concatenation.

[0196] As an example, the advantages of the above method include: small changes to the current standards and system designs.

[0197] As an example, the advantages of the above method include: improving the flexibility of the solution and the system.

[0198] As an embodiment, the CSI described in the present application includes at least one of beam failure prediction and beam switching prediction.

[0199] As an embodiment, the CSI described in the present application includes at least one of predicted beam information, switched beam information, predicted CSI, estimated CSI, or compressed CSI.

[0200] As an embodiment, the CSI described in the present application includes at least one of predicted beam information, predicted CSI, estimated CSI, compressed CSI, confidence information, or performance monitoring results.

[0201] As an embodiment, the predicted beam information includes a beam indication or an RS resource indication.

[0202] As an embodiment, the predicted beam information includes a beam indication and RSRP (reference signal received power).

[0203] As an embodiment, the predicted beam information includes an RS resource indication and RSRP.

[0204] As an embodiment, the predicted beam information includes one or more of a beam indication, a CRI (CSI-RS Resource Indicator), an SS / PBCH block resource indicator (SSBRI), and an RSRP (reference signal received power).

[0205] As an embodiment, the benefits of the above method include: reducing channel measurement overhead and improving the overall performance of the system.

[0206] As an embodiment, the benefits of the above method include: improving the accuracy and real-time performance of channel information reporting and improving the overall performance of the system.

[0207] As an embodiment, the CSI described in the present application includes a channel impulse response.

[0208] As an embodiment, the CSI described in the present application includes small-scale characteristics.

[0209] As an embodiment, the CSI described in the present application includes one or more of delay spread, Doppler spread, Doppler shift, average delay, or average gain.

[0210] As an example, the CSI described in this application includes a channel matrix.

[0211] As an example, the channel matrix is in the spatial-frequency domain.

[0212] As an example, the channel matrix is in the angular-delay domain projection.

[0213] As an example, the CSI described in this application includes at least one of the eigenvalues or eigenvectors of the channel.

[0214] As an example, the CSI described in this application includes a beam indication.

[0215] As an example, the CSI described in this application includes a beam indication, a CRI (CSI-RS resource indicator), and an L1-RSRP (Layer 1 Reference Signal Received Power).

[0216] As an example, the CSI described in this application includes a beam indication, a CRI (CSI-RS resource indicator), an L1-RSRP (Layer 1 Reference Signal Received Power), or one or more of the performance parameters related to AI-based CSI reporting.

[0217] As an example, the CSI described in this application includes one or more of a CQI (Channel Quality Indicator), a PMI (Precoding Matrix Indicator), a CRI (CSI-RS resource indicator), an SSBRI (SS / PBCH Block Resource Indicator), an LI (Layer Indicator), an RI (Rank Indicator), an L1-RSRP (Layer 1 Reference Signal Received Power), an L1-SINR (Layer 1 Signal-to-Interference and Noise Ratio), or beam information.

[0218] As an example, the CSI described in this application includes one or more of beam information, PMI (Precoding Matrix Indicator), CRI (CSI-RS Resource Indicator), CQI (Channel Quality Indicator), RI (Rank Indicator), LI (layer indicator), SSBRI (SS / PBCH Block Resource indicator), RSRP (Reference Signal Received Power), SINR (Signal-to-Interference-plus-Noise Ratio), Capability Index, and TDCP (Time Domain Channel Properties).

[0219] As an example, the CSI described in this application is codebook-based.

[0220] As an example, the CSI described in this application is non-codebook-based.

[0221] As an example, the CSI described in this application belongs to the CSI defined in 3GPP Rel-18.

[0222] As an example, the CSI described in this application does not belong to the CSI defined in 3GPP Rel-18, nor does it belong to the CSI defined in versions prior to 3GPP Rel-18.

[0223] As an example, the CSI described in this application does not belong to the CSI defined in 3GPP Rel-19, nor does it belong to the CSI defined in versions prior to 3GPP Rel-19.

[0224] As an example, the CSI described in this application includes reporting quantities not defined in the 5G standard.

[0225] As an example, the CSI described in this application includes reporting quantities defined in the 6G standard.

[0226] As an example, the CSI described in this application is an AI- or machine learning-based CSI.

[0227] As an example, the CSI described in this application is a Neural Network-based CSI.

[0228] As an example, the CSI described in this application is a CSI based on CNN (Conventional Neural Networks, Convolutional Neural Network).

[0229] As an example, the CSI described in this application is a CSI based on Transformer.

[0230] As an example, the benefits of the above method include: supporting an AI-based CSI reporting scheme.

[0231] As an example, the CSI described in this application includes one or more of CQI, PMI, CRI, SSBRI, LI (Layer Indicator), RI (Rank Indicator), L1-RSRP, L1-SINR, beam information, or performance parameters related to AI-based CSI reporting.

[0232] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the performance parameters predicted by the AI model.

[0233] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the beam prediction accuracy (Beamprediction accuracy).

[0234] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the distribution characteristics of the input / output data of the AI model.

[0235] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the difference between the predicted and actual L1-RSRP.

[0236] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the difference between the predicted and actual L1-SINR.

[0237] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the link or system performance of the AI-based CSI reporting scheme.

[0238] As a sub-example of the above example, the performance parameters related to AI-based CSI reporting include the link or system performance of the AI-based CSI reporting scheme estimated by the first node.

[0239] As an example, the essence of the above method includes: monitoring the AI model based on the performance parameters related to AI-based CSI reporting.

[0240] As an example, the advantages of the above method include: improving the performance of the AI-based CSI reporting scheme and enhancing the overall performance of the system.

[0241] As an example, the first information block is used to configure the first CSI and the second CSI.

[0242] As an example, the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the first CSI and the second CSI.

[0243] As an example, the first information block indicates a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the first CSI and the second CSI.

[0244] As an example, the first information block includes a first CSI reporting configuration and a second CSI reporting configuration, and the first CSI reporting configuration and the second CSI reporting configuration are respectively used to configure the first CSI and the second CSI.

[0245] As an example, the first information block indicates a first CSI reporting configuration and a second CSI reporting configuration, and the first CSI reporting configuration and the second CSI reporting configuration are respectively used to configure the first CSI and the second CSI.

[0246] As an example, the first CSI reporting configuration includes some or all of the fields in the CSI-ReportConfig IE.

[0247] As an example, the first CSI reporting configuration includes some or all of the fields in the ServingCellConfig IE.

[0248] As an example, the first CSI reporting configuration includes some or all of the fields in the CSI-MeasConfig IE.

[0249] As an example, the first CSI reporting configuration includes some or all of the fields in the ServingCellConfigCommon IE.

[0250] As an example, the first CSI reporting configuration includes some or all of the fields in the ServingCellConfigCommonSIB IE.

[0251] As an example, the second CSI reporting configuration includes some or all fields in the CSI-ReportConfig IE.

[0252] As an example, the second CSI reporting configuration includes some or all fields in the ServingCellConfig IE.

[0253] As an example, the second CSI reporting configuration includes some or all fields in the CSI-MeasConfig IE.

[0254] As an example, the second CSI reporting configuration includes some or all fields in the ServingCellConfigCommon IE.

[0255] As an example, the second CSI reporting configuration includes some or all fields in the ServingCellConfigCommonSIB IE.

[0256] As an example, the first inference and the second inference are training-based or AI-based.

[0257] As an example, both the first inference and the second inference are AI inferences.

[0258] As an example, the inference includes: AI (Artificial Intelligence) inference.

[0259] In this application, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0260] As an example, the benefits of the above method include: supporting AI-based CSI reporting.

[0261] As an example, a training-based or AI-based inference includes an AI entity.

[0262] As an example, a training-based or AI-based inference includes a part of an AI entity.

[0263] As an example, a training-based or AI-based inference includes the part for inference in an AI entity.

[0264] As an example, a training-based or AI-based inference is based on a Neural Network.

[0265] As an example, a training-based or AI-based inference is based on CNN (Conventional Neural Networks).

[0266] As an example, a training-based or AI-based inference is based on Transformer.

[0267] As an example, a model of a training-based or AI-based inference is obtained through training.

[0268] As an example, a training-based or AI-based inference includes preprocessing.

[0269] As an example, the preprocessing includes one or more of quantization, DFT (Discrete Fourier Transform), matrix factorization, matrix transformation or projection, quantization, transformation from spatial domain to angular domain, transformation from angular domain to spatial domain, transformation from frequency domain to time domain, transformation from time domain to frequency domain, truncation, padding, mapping, or labeling.

[0270] As an example, the labeling refers to marking with labels.

[0271] As an example, a training-based or AI-based inference includes postprocessing.

[0272] As an example, the postprocessing includes one or more of DFT, quantization, transformation from angular domain to spatial domain, transformation from spatial domain to angular domain, transformation from time domain to frequency domain, transformation from frequency domain to time domain, truncation, and padding.

[0273] As an example, a training-based or AI-based inference includes one or more of convolution, pooling, concatenation, and activation.

[0274] As an example, a training-based or AI-based inference includes a fully connected layer.

[0275] As an example, a training-based or AI-based inference includes a pooling layer.

[0276] As an example, a training-based or AI-based inference includes at least one convolutional layer.

[0277] As an example, a training-based or AI-based inference includes at least one encoding layer.

[0278] As an example, an encoding layer includes at least one convolutional layer and one pooling layer.

[0279] As an example, in the convolutional layer, at least one convolutional kernel is used to perform convolution on 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 converts the said one vector into an output.

[0280] As an example, some or all of a convolutional kernel size, the number of convolutional layers, a convolutional stride, a pooling kernel size, a pooling kernel stride, a pooling function, an activation function, and the number of feature maps based on training or AI inference are obtained through training.

[0281] As an example, some or all of a convolutional kernel, a pooling kernel, a pooling function, an activation function, parameters of the pooling function, and parameters of the activation function based on training or AI inference are obtained through training.

[0282] As an example, the first inference and the second inference are AI inferences for obtaining CSI.

[0283] As an example, the first inference and the second inference are AI inferences for obtaining channel information.

[0284] As an example, the first inference and the second inference are AI inferences for at least one of beam management, positioning or assisted positioning, CSI prediction, CSI estimation, or CSI compression.

[0285] As an example, the first inference and the second inference are AI inferences for at least one of performance monitoring, positioning, beam management, CSI prediction, CSI estimation, CSI compression, RLF (radio link failure) prediction, cell handover prediction, or serving cell prediction.

[0286] As an example, the first inference and the second inference include CSI compression based on artificial intelligence or machine learning.

[0287] As an example, the first inference and the second inference include an encoder for CSI compression based on artificial intelligence or machine learning.

[0288] As an example, the first inference and the second inference include CSI prediction or CSI estimation based on artificial intelligence or machine learning.

[0289] As an example, the first inference and the second inference include CSI prediction and compression based on artificial intelligence or machine learning.

[0290] As an example, the first inference and the second inference include beam management based on artificial intelligence or machine learning.

[0291] As an example, the beam management includes at least one of beam prediction, beam switching, beam failure prediction, or beam failure recovery.

[0292] As an example, the first inference and the second inference are AI functions.

[0293] As an example, the first inference and the second inference are executed by the first node.

[0294] As an example, the training of the first inference and the second inference is executed by the sender of the first information block.

[0295] As an example, the training of the first inference and the second inference is executed by the core network.

[0296] As an example, the training of the first inference and the second inference is executed by an AI training producer.

[0297] As an example, the training of the first inference and the second inference is executed by an MDA function (Management Data Analytics Function).

[0298] As an example, the training of the first inference and the second inference is executed by the MDA function located at the first node.

[0299] As an example, the training of the first inference and the second inference is executed by the MDA function located at the sender of the first information set.

[0300] As an example, the training of the first inference and the second inference is executed by an NWDAF (Network Data Analytics Function).

[0301] As an example, the training of the first inference and the second inference is executed by an MDAS (Management Data Analytics Service) producer.

[0302] As an example, the training of the first inference and the second inference is executed by an MnS (Management Service) producer.

[0303] As an example, both the first inference and the second inference are inferences using the same AI model.

[0304] As an example, the advantages of the above method include: supporting multiple executions and outputs of an AI model.

[0305] As an example, the advantages of the above method include: improving the performance of AI-based CSI reporting.

[0306] As an example, the first inference and the second inference are respectively inferences using different AI models.

[0307] As an example, the advantages of the above method include: supporting joint processing of multiple AI models.

[0308] As an example, the advantages of the above method include: improving the performance of AI-based CSI reporting.

[0309] As an example, both the first inference and the second inference are inferences corresponding to the first identifier.

[0310] As an example, the first inference and the second inference respectively correspond to different identifiers.

[0311] As an example, the first inference is an inference corresponding to the first identifier, and the second inference is an inference corresponding to the second identifier.

[0312] As a sub-example of the above example, the first identifier and the second identifier are respectively used to identify different AI functions.

[0313] As a sub-example of the above example, the first identifier and the second identifier are respectively used to identify different AI models.

[0314] As a sub-example of the above example, the first identifier and the second identifier are respectively used to identify different CSI reporting configurations.

[0315] As a sub-example of the above example, the first identifier and the second identifier are respectively used to identify different RS resource sets.

[0316] As a sub-example of the above example, the first identifier and the second identifier are respectively used to identify different training data sets.

[0317] As an example, the advantages of the above method include: enhancing the completeness and flexibility of the system.

[0318] As an example, the outputs of the first inference and the second inference include channel information.

[0319] As an example, the outputs of the first inference and the second inference include a channel matrix.

[0320] As an example, the outputs of the first inference and the second inference include CSI.

[0321] As an example, the outputs of the first inference and the second inference include compressed CSI.

[0322] In one example, the outputs of the first inference and the second inference include predicted CSI.

[0323] In one example, the outputs of the first inference and the second inference include predicted and compressed CSI.

[0324] As an example, the outputs of the first inference and the second inference include non-codebook-based CSI.

[0325] As an example, the outputs of the first inference and the second inference include a channel impulse response.

[0326] As an example, the outputs of the first inference and the second inference include small-scale characteristics.

[0327] As an example, the outputs of the first inference and the second inference are used to determine one or more precoding matrices.

[0328] In one example, the outputs of the first inference and the second inference include predicted beam information.

[0329] As an example, the outputs of the first inference and the second inference include information other than channel information.

[0330] As an example, the outputs of the first inference and the second inference include at least one of channel information or information other than channel information.

[0331] As an example, the outputs of the first inference and the second inference include channel information before the current channel information.

[0332] As an example, the outputs of the first inference and the second inference include accumulated channel information.

[0333] As a sub-example of the above example, the accumulated channel information is all channel information before the current channel information.

[0334] As a sub - embodiment of the above - mentioned embodiment, the accumulated channel information is at least one channel information before the current channel information.

[0335] As a sub - embodiment of the above - mentioned embodiment, the accumulated channel information represents all channel information before the current channel information.

[0336] As a sub - embodiment of the above - mentioned embodiment, the accumulated channel information represents at least one channel information before the current channel information.

[0337] As an embodiment, the outputs of the first inference and the second inference include accumulated CSI.

[0338] As an embodiment, the outputs of the first inference and the second inference respectively include all or part of the parameters of the first inference and the second inference.

[0339] As an embodiment, the outputs of the first inference and the second inference respectively include all or part of the outputs of the intermediate processes of the first inference and the second inference.

[0340] As an embodiment, the outputs of the first inference and the second inference respectively include the status information of the first inference and the second inference.

[0341] As a sub - embodiment of the above - mentioned embodiment, the status information is the status information of the AI model corresponding to the first inference or the second inference.

[0342] As a sub - embodiment of the above - mentioned embodiment, the status information is all or part of the parameters of the AI model corresponding to the first inference or the second inference.

[0343] As a sub - embodiment of the above - mentioned embodiment, the status information is the intermediate output of the AI model corresponding to the first inference or the second inference.

[0344] As a sub - embodiment of the above - mentioned embodiment, the status information is all or part of the parameters of all or part of the layers of the neural network of the AI model corresponding to the first inference or the second inference.

[0345] As a sub - embodiment of the above - mentioned embodiment, the status information is all or part of the outputs of all or part of the layers of the neural network of the AI model corresponding to the first inference or the second inference.

[0346] As a sub - embodiment of the above - mentioned embodiment, the status information is the output of all or part of the hidden layers of the neural network of the AI model corresponding to the first inference or the second inference.

[0347] As a sub - embodiment of the above - mentioned embodiment, the status information is the output of all or part of the hidden layers of the neural network of the AI model corresponding to the first inference or the second inference.

[0348] As an embodiment, the inputs of the first inference and the second inference include measurements obtained based on at least one RS resource.

[0349] As an embodiment, the inputs of the first inference and the second inference include channel measurements obtained based on CSI - RS resources or SS / PBCH block resources.

[0350] As an embodiment, the inputs of the first inference and the second inference include interference measurements obtained based on CSI - RS resources or CSI - IM resources.

[0351] As an embodiment, the inputs of the first inference and the second inference include a matrix or vector obtained after pre - processing a channel matrix obtained from measurements based on at least one RS resource.

[0352] As an embodiment, the advantages of the above - mentioned method include: small changes to existing standards and system designs.

[0353] As an embodiment, the inputs of the first inference and the second inference include accumulated channel information.

[0354] As an embodiment, the inputs of the first inference and the second inference include accumulated CSI.

[0355] As an embodiment, the advantages of the above - mentioned method include: improving the accuracy of CSI reporting and the effectiveness of CSI compression, and enhancing the overall performance of the system.

[0356] As an embodiment, the inputs of the first inference and the second inference respectively include the status information of the first inference and the second inference.

[0357] As an embodiment, the inputs of the first inference and the second inference include measurements obtained based on at least one RS resource and accumulated channel information.

[0358] As an embodiment, the inputs of the first inference and the second inference include measurements obtained based on at least one RS resource and accumulated CSI.

[0359] As an embodiment, the input of the first inference includes measurements obtained based on at least one RS resource and the status information of the first inference.

[0360] As an embodiment, the input of the first inference includes measurements obtained based on at least one RS resource and the status information of the AI model corresponding to the first inference.

[0361] As an embodiment, the input of the second inference includes measurements obtained based on at least one RS resource and the status information of the second inference.

[0362] As an embodiment, the input of the second inference includes measurements obtained based on at least one RS resource and the status information of the AI model corresponding to the second inference.

[0363] As an embodiment, the input of the second inference includes measurements obtained based on at least one RS resource and the status information of the first inference.

[0364] As an embodiment, the input of the second inference includes measurements obtained based on at least one RS resource and the status information of the AI model corresponding to the first inference.

[0365] As an embodiment, the benefits of the above method include: introducing the correlation between multiple inferences and improving the performance of AI-based CSI reporting.

[0366] As an embodiment, the benefits of the above method include: supporting the joint operation of multiple inferences, improving the accuracy of CSI reporting, and reducing the reporting overhead.

[0367] As an embodiment, the first CSI depends on the output of the first inference.

[0368] As an embodiment, the first CSI depends on all or part of the output of the first inference.

[0369] As an embodiment, the second CSI depends on the output of the second inference.

[0370] As an embodiment, the second CSI depends on all or part of the output of the second inference.

[0371] As an embodiment, a CSI depending on an output includes: the one output is used to generate the one CSI.

[0372] As an embodiment, a CSI depending on an output includes: after the one output is post-processed, it is used to generate the one CSI.

[0373] As an example, a CSI depending on an output includes: the CSI includes the output.

[0374] As an example, a CSI depending on an output includes: the CSI includes all or part of the content of the output.

[0375] As an example, a CSI depending on an output includes: the CSI includes the result of post-processing the output.

[0376] As an example, the post-processing includes one or more of sampling, quantization, truncation, DFT (Discrete Fourier Transform), transformation from the angular domain to the spatial domain, transformation from the spatial domain to the angular domain, transformation from the time domain to the frequency domain, and transformation from the frequency domain to the time domain.

[0377] As an example, a CSI depending on an output includes: the CSI includes the result of truncating and / or quantizing the output.

[0378] As an example, a CSI depending on an output includes: after the output is truncated and / or quantized, it is used to generate the CSI.

[0379] As an example, the benefits of the above method include: enhancing the flexibility of the system and better adapting to various different transmission conditions and application scenarios.

[0380] As an example, the benefits of the above method include: enhancing the backward compatibility of the system.

[0381] As an example, the generating the CSI includes: calculating the CSI.

[0382] As an example, how the output is used to generate the CSI is determined by the manufacturer of the first node itself or is implementation-related. Some typical but non-limiting implementation manners are described below:

[0383] As an example, the output includes 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 CSI-RS resource respectively; the first node performs power adjustment on the channel parameter matrix H r×t , and the adjusted channel parameter matrix is where P is the assumed ratio of the PDSCH EPRE to the CSI-RS EPRE (i.e., the first power control offset); under the condition of using the precoding matrix W t×l , the precoded channel parameter matrix is where l is the rank or the number of layers, which is a positive integer not greater than t in one case, and in another case the precoding matrix is the identity matrix, where t = 1; for example, use SINR (Signal Interference Noise Ratio), EESM (Exponential Effective SINR Mapping), or RBIR (Received Block mean mutual Information Ratio) criteria to calculate the equivalent channel capacity of H r×t ·W t×l Then determine the CQI included in the first CSI report by looking up a table or other means based on the equivalent channel capacity. Generally speaking, calculating the equivalent channel capacity requires the first node to estimate interference (including noise), and the first node can use the measurements in the second opportunity set in this application to obtain more accurate measurement of interference. Usually, the direct mapping from the equivalent channel capacity to the CQI value depends on receiver performance, or hardware-related factors such as the modulation method.

[0384] As an example, the output of the first inference includes the first output and the second output.

[0385] As an example, the output of the first inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the accumulated channel information.

[0386] As an example, the output of the first inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the accumulated CSI.

[0387] As an example, the output of the first inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the status information of the first inference.

[0388] As an example, the output of the first inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the status information of the AI model corresponding to the first inference.

[0389] As an example, the output of the first inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes the accumulated channel information.

[0390] As an example, the output of the first inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes accumulated CSI.

[0391] As an example, the output of the first inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes the status information of the first inference.

[0392] As an example, the output of the first inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes the status information of the AI model corresponding to the first inference.

[0393] As an example, the output of the second inference includes the first output and the second output.

[0394] As an example, the output of the second inference includes the first output and the second output; the first output includes the first CSI, and the second output includes accumulated channel information.

[0395] As an example, the output of the second inference includes the first output and the second output; the first output includes the first CSI, and the second output includes accumulated CSI.

[0396] As an example, the output of the second inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the status information of the second inference.

[0397] As an example, the output of the second inference includes the first output and the second output; the first output includes the first CSI, and the second output includes the status information of the AI model corresponding to the second inference.

[0398] As an example, the output of the second inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes accumulated channel information.

[0399] As an example, the output of the second inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes accumulated CSI.

[0400] As an example, the output of the second inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes the status information of the second inference.

[0401] As an example, the output of the second inference includes the first output and the second output; the first output is used to generate the first CSI, and the second output includes the status information of the AI model corresponding to the second inference.

[0402] As an example, the advantages of the above method include: enhancing the flexibility of the system and better adapting to various different transmission conditions and application scenarios.

[0403] As an example, the advantages of the above method include: improving the performance of AI-based CSI prediction and compression.

[0404] As an example, the advantages of the above method include: improving the accuracy of CSI reporting, reducing the reporting overhead, and enhancing the overall performance of the system.

[0405] As an example, the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0406] As an example, the output of the first inference includes a first output and a second output, the first CSI depends on the first output; the input of the second inference includes a first input and a second input, the first input depends on measurements obtained based on at least one RS resource, and the second input depends on the second output.

[0407] As an example, an input depending on an output includes: an input depending on all or part of the content of an output.

[0408] As an example, an input depending on an output includes: the output being used to generate the input.

[0409] As an example, an input depending on an output includes: after post-processing the output, it is used to generate the input.

[0410] As an example, an input depending on an output includes: the input including the output.

[0411] As an example, an input depending on an output includes: the input including all or part of the content of the output.

[0412] As an example, one input depending on one output includes: the one input includes the result of post-processing the one output.

[0413] As an example, the advantages of the above method include: enhancing the flexibility of the system and better adapting to various different transmission conditions and application scenarios.

[0414] As an example, the advantages of the above method include: enhancing the backward compatibility of the system.

[0415] As an example, the output of the first inference includes a first output and a second output, and the first CSI depends on the first output; the input of the second inference includes a first input and a second input, the first input includes measurements obtained based on at least one RS resource, and the second input includes the second output.

[0416] As an example, the output of the first inference includes a first output and a second output, and the first CSI depends on the first output; the input of the second inference includes a first input and a second input, the first input includes measurements obtained based on at least one RS resource, and the second input is the second output.

[0417] As a sub-example of the above example, the second output of the first inference includes historical channel information.

[0418] As a sub-example of the above example, the second output of the first inference includes historical CSI.

[0419] As a sub-example of the above example, the second output of the first inference includes accumulated channel information.

[0420] As a sub-example of the above example, the second output of the first inference includes accumulated CSI.

[0421] As a sub-example of the above example, the second output of the first inference represents historical channel information.

[0422] As a sub-example of the above example, the second output of the first inference represents accumulated channel information.

[0423] As a sub-example of the above example, the second output of the first inference includes all or part of the parameters of the first inference.

[0424] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the output of the intermediate process of the first inference.

[0425] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes the status information of the first inference.

[0426] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes the status information of the AI model corresponding to the first inference.

[0427] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the parameters of the AI model corresponding to the first inference.

[0428] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes the intermediate output of the AI model corresponding to the first inference.

[0429] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the parameters of all layers of the neural network of the AI model corresponding to the first inference.

[0430] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the output of all layers of the neural network of the AI model corresponding to the first inference.

[0431] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the output of all hidden layers of the neural network of the AI model corresponding to the first inference.

[0432] As a sub - embodiment of the above - mentioned embodiment, the second output of the first inference includes all or part of the output of the hidden layers of the neural network of the AI model corresponding to the first inference.

[0433] As an embodiment, the advantages of the above - mentioned method include: introducing the correlation between multiple inferences and improving the performance of AI - based CSI reporting.

[0434] As an embodiment, the advantages of the above - mentioned method include: supporting the joint operation of multiple inferences, improving the accuracy of CSI reporting, and reducing the reporting overhead.

[0435] As an embodiment, the advantages of the above - mentioned method include: improving the flexibility of the system.

[0436] Example 2

[0437] Embodiment 2 exemplifies a schematic diagram of a network architecture according to an embodiment of the present application, as shown in the appendixFigure 2 as shown

[0438] Appended Figure 2Describes the network architecture 200. The network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or the network architecture 200 is a 5G+ network architecture, or the network architecture 200 is a 6G network architecture, or the network architecture 200 is a network architecture adopted in the future continuous evolution of 3GPP; the network architecture 200 can be referred to as 5GS (5G System) / EPS (Evolved Packet System), or the network architecture 200 can be referred to as 6GS (6G System); the 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 be interconnected with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the network architecture 200 provides packet switching 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 switching 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 towards UE 201. Node 203 can be connected to other nodes 204 via the Xn interface (e.g., backhaul) / X2 interface. Node 203 can also be referred to as a base station, base station transceiver, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (Transmit Receive Point), 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 an access point for UE 201 to the core network 210.Examples of the UE 201 include cellular phones, smart phones, Session Initiation Protocol (SIP) phones, laptop computers, 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 Internet of Things 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 the UE 201 as a mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable term. The node 203 is connected to the core network 210 through the S1 / NG interface. The core network 210 includes a Mobility Management Entity (MME) / Authentication Management Field (AMF) / Session Management Function (SMF) 211, other MMEs / AMFs / SMFs 214, a Serving Gateway (S-GW) / User Plane Function (UPF) 212, and a Packet Data Network Gateway (P-GW) / UPF 213. The MME / AMF / SMF 211 is a control node that processes the signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user Internet Protocol (IP) 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. The Internet service 230 includes carrier-corresponding Internet protocol services, specifically including the Internet, intranet, IP Multimedia Subsystem (IMS), and packet switching services.

[0439] As an embodiment, the first node includes the UE 201.

[0440] As an embodiment, the second node includes the node 203.

[0441] As an example, the radio link between the UE 201 and the node 203 includes a cellular network link.

[0442] As an example, the sender of the first information block includes the node 203.

[0443] As an example, the receiver of the first information block includes the UE 201.

[0444] As an example, the sender of the first CSI includes the UE 201.

[0445] As an example, the receiver of the first CSI includes the node 203.

[0446] As an example, the sender of the second CSI includes the UE 201.

[0447] As an example, the receiver of the second CSI includes the node 203.

[0448] As an example, the executor of the first inference includes the UE 201.

[0449] As an example, the executor of the second inference includes the UE 201.

[0450] Example 3

[0451] Embodiment 3 exemplifies a schematic diagram of an embodiment of a radio protocol architecture for a user plane and a control plane according to an embodiment of the present application, as shown in the appendix Figure 3 as shown.

[0452] Embodiment 3 shows a schematic diagram of an embodiment of a radio protocol architecture for a user plane and a control plane according to the present application, as shown in the appendix Figure 3 as shown. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300, Figure 3Show the radio protocol architecture of the control plane 300 for between a first communication node device (UE, gNB or RSU in V2X) and a second communication node device (gNB, UE or RSU in V2X), or between two UEs, with three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. Layer 1 will be referred to as PHY301 in this text. Layer 2 (L2 layer) 305 is above PHY301 and is responsible for the link between the first communication node device and the second communication node device, or between two UEs. The 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, and these sublayers terminate at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security by encrypting data packets, and provides handover support for the first communication node device between the second communication node devices. The RLC sublayer 303 provides segmentation and reassembly of upper layer data packets, retransmission of lost data packets, and reordering of data packets to compensate for disordered reception due to HARQ. The MAC sublayer 302 provides multiplexing between logical and transport channels. The MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) in a cell between the first communication node devices. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3 layer) of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device. The radio protocol architecture of the user plane 350 includes Layer 1 (L1 layer) and Layer 2 (L2 layer). For the physical layer 351, the PDCP sublayer 354 in the L2 layer 355, the RLC sublayer 353 in the L2 layer 355, and the MAC sublayer 352 in the L2 layer 355, the radio protocol architecture for the first communication node device and the second communication node device in the user plane 350 is generally the same as the corresponding layers and sublayers in the control plane 300, but the 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 further includes an SDAP (Service Data Adaptation Protocol) sub-layer 356. The SDAP sub-layer 356 is responsible for the mapping between QoS flows and data radio bearers (DRBs) to support the diversity of services. Although not shown, the first communication node device may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminated at the P-GW on the network side and an application layer terminated at the other end of the connection (e.g., a remote UE, server, etc.).

[0453] As an example, the Figure 3 radio protocol architecture in is applicable to the first node in this application.

[0454] As an example, the Figure 3 radio protocol architecture in is applicable to the second node in this application.

[0455] As an example, the higher layer in this application refers to the layer above the physical layer.

[0456] As an example, the first information block is generated in the RRC 306.

[0457] As an example, the first information block is generated in the MAC sub-layer 302 or the MAC sub-layer 352.

[0458] As an example, the first CSI is generated in the MAC 302 or the MAC 352.

[0459] As an example, the first CSI is generated in the PHY 301 or the PHY 351.

[0460] As an example, the second CSI is generated in the MAC 302 or the MAC 352.

[0461] As an example, the second CSI is generated in the PHY 301 or the PHY 351.

[0462] Example 4

[0463] 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 the appendix Figure 4 shown. The appendix Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 that communicate with each other in an access network.

[0464] The first communication device 410 includes a controller / processor 475, a memory 476, a receiving processor 470, a transmitting processor 416, a multi-antenna receiving processor 472, a multi-antenna transmitting processor 471, a transmitter / receiver 418, and an antenna 420.

[0465] 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.

[0466] 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 the functions of the L2 layer. In the DL, 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 operations, retransmission of lost packets, and signaling to the second communication device 450. The transmitting processor 416 and the multi-antenna transmitting processor 471 implement various signal processing functions for the L1 layer (i.e., the physical layer). The transmitting processor 416 implements 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-quadrature amplitude modulation (M-QAM)). The multi-antenna transmitting processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, to generate one or more parallel streams. The transmitting processor 416 then maps each parallel stream to subcarriers, multiplexes the modulated symbols with reference signals (e.g., pilots) in the time domain and / or frequency domain, and then uses the inverse fast Fourier transform (IFFT) to generate a physical channel carrying time-domain multi-carrier symbol streams. Subsequently, the multi-antenna transmitting processor 471 performs transmission analog precoding / beamforming operations on the time-domain multi-carrier symbol streams. Each transmitter 418 converts the baseband multi-carrier symbol streams provided by the multi-antenna transmitting processor 471 into radio frequency streams, and then provides them to different antennas 420.

[0467] 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 signals via its respective antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier, and converts the radio frequency stream into a baseband multi-carrier symbol stream and provides it to the receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 perform various signal processing functions of the L1 layer. The multi-antenna receive processor 458 performs receive analog precoding / beamforming operations on the baseband multi-carrier symbol stream from the receivers 454. The receive processor 456 uses the Fast Fourier Transform (FFT) to convert the baseband multi-carrier 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 receive processor 456, where the reference signal will be used for channel estimation, and the data signal is recovered in the multi-antenna receive processor 458 for any parallel streams destined for the second communication device 450 after multi-antenna detection. The symbols on each parallel stream are demodulated and recovered in the receive processor 456, and soft decisions are generated. Subsequently, the receive processor 456 decodes and deinterleaves the soft decisions to recover the upper layer data and control signals transmitted by the first communication device 410 on the physical channel. Subsequently, the upper layer data and control signals are provided to the controller / processor 459. The controller / processor 459 performs the functions of the L2 layer. The controller / processor 459 may be associated with a memory 460 that stores program code and data. The memory 460 may be referred to as a computer-readable medium. In the DL (DownLink), the controller / processor 459 provides demultiplexing between the transmission and the logical channel, packet reassembly, decryption, header decompression, control signal processing to recover the upper layer data packets from the core network. Subsequently, the upper layer data packets are provided to all protocol layers above the L2 layer. Various control signals may also be provided to the L3 for L3 processing. The controller / processor 459 is also responsible for error detection using the acknowledgment (ACK) and / or negative acknowledgment (NACK) protocol to support the HARQ operation.

[0468] 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 an upper layer data packet to a controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmit function at the first communication device 410 described in 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, and implements the L2 layer functions for the user plane and the control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. A transmit processor 468 performs modulation mapping and channel coding processing. A multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing. Subsequently, the transmit processor 468 modulates the generated parallel streams into multi-carrier / single-carrier symbol streams, and after passing through analog precoding / beamforming operations in the multi-antenna transmit processor 457, provides them to different antennas 452 via a transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 457 into a radio frequency symbol stream and then provides it to the antenna 452.

[0469] In the transmission from the second communication device 450 to the first communication device 410, the functions at the first communication device 410 are similar to the receive functions 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 a radio frequency signal through its corresponding antenna 420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to a multi-antenna receive processor 472 and a receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 jointly implement the L1 layer functions. A 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 a computer-readable medium. The controller / processor 475 provides demultiplexing between the transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover the upper layer data packet from the second communication device 450. The upper layer data packet from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using the ACK and / or NACK protocols to support HARQ operations.

[0470] As an example, 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 is at least configured to: receive a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; transmit a first CSI on the first time-domain resource, or refrain from transmitting the first CSI on the first time-domain resource; transmit a second CSI on the second time-domain resource only when the first CSI is transmitted on the first time-domain resource; wherein the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0471] As an example, the second communication device 450 includes: a memory storing a computer-readable instruction program, the computer-readable instruction program generating actions when executed by at least one processor, the actions including: receive a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; transmit a first CSI on the first time-domain resource, or refrain from transmitting the first CSI on the first time-domain resource; transmit a second CSI on the second time-domain resource only when the first CSI is transmitted on the first time-domain resource; wherein the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0472] As an example, 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 is at least configured to: send a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; when the first CSI is sent by the receiver of the first information block on the first time-domain resource, receive the first CSI on the first time-domain resource and receive the second CSI on the second time-domain resource; wherein, the receiver of the first information block sends the first CSI on the first time-domain resource or abandons sending the first CSI on the first time-domain resource; only when the first CSI is sent by the receiver of the first information block on the first time-domain resource, the receiver of the first information block sends the second CSI on the second time-domain resource; the first CSI and the second CSI respectively depend on the output of a first inference and the output of a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0473] As an example, the first communication device 410 includes: a memory storing a computer-readable instruction program, the computer-readable instruction program generating actions when executed by at least one processor, the actions including: sending a first information block; the first information block indicates a first time-domain resource and a second time-domain resource; when the first CSI is sent by the receiver of the first information block on the first time-domain resource, receive the first CSI on the first time-domain resource and receive the second CSI on the second time-domain resource; wherein, the receiver of the first information block sends the first CSI on the first time-domain resource or abandons sending the first CSI on the first time-domain resource; only when the first CSI is sent by the receiver of the first information block on the first time-domain resource, the receiver of the first information block sends the second CSI on the second time-domain resource; the first CSI and the second CSI respectively depend on the output of a first inference and the output of a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0474] As an example, the first node in this application includes the second communication device 450.

[0475] As an example, the second node in this application includes the first communication device 410.

[0476] 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, the data source 467} is used to receive the first information block in the present application.

[0477] As an example, at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, the memory 476} is used to transmit the first information block in the present application.

[0478] As an example, at least one of {the antenna 452, the transmitter / receiver 454, the transmitting processor 468, the multi-antenna transmitting processor 457, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, the data source 467} is used to transmit the first CSI in the present application.

[0479] As an example, at least one of {the antenna 420, the transmitter / receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, the memory 476} is used to receive the first CSI in the present application.

[0480] As an example, at least one of {the antenna 452, the transmitter / receiver 454, the transmitting processor 468, the multi-antenna transmitting processor 457, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, the data source 467} is used to transmit the second CSI in the present application.

[0481] As an example, at least one of {the antenna 420, the transmitter / receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, the memory 476} is used to receive the second CSI in the present application.

[0482] As an example, at least one of {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, the data source 467} is used to perform the first inference in this application.

[0483] As an example, at least one of {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the transmitting processor 468, the multi-antenna receiving processor 458, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, the data source 467} is used to perform the second inference in this application.

[0484] Example 5

[0485] Example 5 illustrates a flowchart of wireless transmission according to an embodiment of this application, as shown in the appendix Figure 5 as shown. In the appendix Figure 5 the second node N1 and the first node U1 are communication nodes transmitted through the air interface. In the appendix Figure 5 the steps in blocks F51 to F55 are optional respectively, the steps in blocks F51 and F52 are alternative, and the steps in blocks F53 to F55 are alternative.

[0486] For the second node N1, a first information block is sent in step S511; a first CSI is received on a first time-domain resource in step S512; a second CSI is received on a second time-domain resource in step S513; part or all of the information in the first CSI and part or all of the information in the second CSI are received on the second time-domain resource in step S514.

[0487] For the first node U1, the first information block is received in step S521; the first CSI is sent on the first time-domain resource in step S522; sending the first CSI is abandoned on the first time-domain resource in step S523; the second CSI is sent on the second time-domain resource in step S524; part or all of the information in the first CSI and part or all of the information in the second CSI are sent on the second time-domain resource in step S525; sending the second CSI is abandoned on the second time-domain resource in step S526.

[0488] In Embodiment 5, the first information block indicates a first time-domain resource and a second time-domain resource; only when the first CSI is transmitted on the first time-domain resource, the first node U1 transmits a second CSI on the second time-domain resource; the first CSI and the second CSI respectively depend on the output of a first inference and the output of a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[0489] As an embodiment, the first node U1 is the first node in this application.

[0490] As an embodiment, the second node N1 is the second node in this application.

[0491] As an embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between a base station device and a user equipment.

[0492] As an embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between a relay node device and a user equipment.

[0493] As an embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between user equipments.

[0494] As an embodiment, the second node N1 is the serving cell maintaining base station of the first node U1.

[0495] As an embodiment, the first inference does not require deployment.

[0496] As an embodiment, the first inference requires deployment.

[0497] As an embodiment, the second inference does not require deployment.

[0498] As an embodiment, the second inference requires deployment.

[0499] As an embodiment, the first node deploys the first inference.

[0500] As an embodiment, the first node deploys the second inference.

[0501] As an embodiment, deploying an inference includes: obtaining an inference.

[0502] As an example, the deployment of an inference includes: loading an inference.

[0503] As an example, the deployment of an inference includes: issuing a request to load an inference.

[0504] As an example, the advantages include: reserving sufficient freedom for the first node to adapt to various different scenarios and terminals, with adaptability and flexibility.

[0505] As an example, the deployment of the first inference and the second inference is earlier than the reception of the first information block.

[0506] As an example, the deployment of the first inference and the second inference is later than the reception of the first information block.

[0507] As an example, the models of the first inference and the second inference are obtained through training.

[0508] As an example, the first inference and the second inference are not obtained through loading.

[0509] As an example, the first inference and the second inference are obtained through loading.

[0510] As an example, the loading includes loading from the serving cell of the first node.

[0511] As an example, the loading includes loading from the serving base station of the serving cell of the first node.

[0512] As an example, the loading includes loading from the core network.

[0513] As an example, the advantages of the above method include: reducing the demand for the processing power of the first node and power consumption.

[0514] As an example, the first inference and the second inference are AI inferences.

[0515] As an example, the AI training function in the RAN (Radio Access Network) domain is located in the 3GPP RAN domain-specific management function, while the AI inference function is located in the UE.

[0516] As an example, the RAN-domain specific management function provides the management capability for the AI training function and the management capability for the AI inference function.

[0517] As an example, the AI training function is located in the RAN-domain specific management function, and the AI inference function is located locally in the gNB.

[0518] As an example, the management capability of the AI training function is provided by the RAN-domain specific management function, and the management capability of the AI inference is provided locally by the gNB.

[0519] As an example, MnF refers to ManagementFunction.

[0520] As an example, both the AI training function and the AI inference function are located in the UE, where the UE provides the capabilities for training and inference.

[0521] As an example, the RAN-domain specific management function provides the management capability for the AI training function and the management capability for the AI inference function.

[0522] As an example, both the AI training function and the AI inference function are located in the gNB.

[0523] As an example, the management capabilities of both the AI training function and the AI inference function are provided locally by the gNB.

[0524] As an example, the first inference and the second inference are performed by the physical layer of the first node.

[0525] As an example, the first inference and the second inference are performed by a higher layer of the first node.

[0526] As an example, the first node adopts a single-side AI model.

[0527] As an example, the first inference and the second inference are used for beam prediction, and the first node adopts a single-side AI model.

[0528] As an example, the first inference and the second inference are used for CSI prediction, and the first node adopts a single-side AI model.

[0529] As an example, the first node and the second node adopt a two-sided AI model.

[0530] As an embodiment, the first inference and the second inference are used for CSI compression. The first node and the second node adopt a two-sided AI model. The second node performs a third inference, and the third inference is used for CSI recovery.

[0531] As an embodiment, the first inference and the second inference are used for CSI prediction and compression. The first node and the second node adopt a two-sided AI model. The second node performs a third inference, and the third inference is used for CSI recovery.

[0532] As an embodiment, the third inference is training-based or AI-based.

[0533] As an embodiment, the third inference is AI inference.

[0534] As an embodiment, the third inference does not require deployment.

[0535] As an embodiment, the third inference requires deployment.

[0536] As an embodiment, the second node deploys the third inference.

[0537] As an embodiment, the model of the third inference is obtained through training.

[0538] As an embodiment, the third inference is not obtained by loading.

[0539] As an embodiment, the third inference is obtained by loading.

[0540] As an embodiment, the third inference is associated with the first inference and the second inference.

[0541] As an embodiment, the third inference is associated with the first inference.

[0542] As an embodiment, the third inference is associated with the second inference.

[0543] As an embodiment, the advantages of the above method include: supporting multiple inferences to complete one function.

[0544] As an embodiment, the advantages of the above method include: improving the performance of AI-based CSI reporting.

[0545] As an embodiment, the third inference corresponds to the first identifier with both the first inference and the second inference.

[0546] As an embodiment, both the third inference and the first inference correspond to a first identifier.

[0547] As an embodiment, both the third inference and the second inference correspond to a first identifier.

[0548] As an embodiment, the advantages of the above method include: simplifying system design and reducing system implementation complexity.

[0549] As an embodiment, the first node transmits the first CSI on the first time-domain resource, or the first node abandons transmitting the first CSI on the first time-domain resource.

[0550] As an embodiment, the second node monitors whether the first CSI is transmitted by the first node on the first time-domain resource.

[0551] As an embodiment, the second node monitors whether the first CSI is transmitted by the first node on the first time-domain resource; when the first CSI is transmitted by the first node, the second node receives the first CSI; when the first CSI is abandoned by the first node from being transmitted, the second node abandons receiving the first CSI.

[0552] As an embodiment, when the first CSI is transmitted by the first node on the first time-domain resource, the second node receives the first CSI on the first time-domain resource and receives the second CSI on the second time-domain resource.

[0553] As an embodiment, when the first CSI is abandoned by the first node from being transmitted on the first time-domain resource, the second node abandons receiving the second CSI on the second time-domain resource.

[0554] As an embodiment, the second node determines by itself whether to receive the first CSI on the first time-domain resource.

[0555] As an embodiment, the second node determines by itself whether to abandon receiving the first CSI on the first time-domain resource.

[0556] As an embodiment, the essence of the above method includes: enhancing the completeness of the system and the solution.

[0557] As an embodiment, when a first condition is satisfied, the first node abandons transmitting the first CSI on the first time-domain resource; the first condition includes at least one sub-condition; when none of the at least one sub-conditions is satisfied, the first condition is not satisfied; when any one of the at least one sub-conditions is satisfied, the first condition is satisfied.

[0558] As an embodiment, when the first condition is satisfied, the first CSI is not transmitted by the first node on the first time-domain resource; the first condition includes that the first time-domain resource and other signals overlap in the time domain, or, the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0559] As an embodiment, when the first condition is satisfied, the first CSI is not transmitted by the first node on the first time-domain resource; the first condition includes that the first time-domain resource and other signals overlap in the time domain.

[0560] As an embodiment, when the first condition is satisfied, the first CSI is not transmitted by the first node on the first time-domain resource; the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0561] As an embodiment, when the first condition is satisfied, the first CSI is not transmitted by the first node on the first time-domain resource; the first condition includes a first sub-condition and a second sub-condition; the first sub-condition includes that the first time-domain resource and other signals overlap in the time domain; the second sub-condition includes that the first time-domain resource includes at least one DL (downlink) symbol; when neither the first sub-condition nor the second sub-condition is satisfied, the first condition is not satisfied; when any one of the first sub-condition and the second sub-condition is satisfied, the first condition is satisfied.

[0562] As an embodiment, the advantages of the above method include: small changes to existing standards and system designs.

[0563] As an embodiment, the advantages of the above method include: improving the reliability and robustness of system transmission.

[0564] As an embodiment, the first node transmits the second CSI on the second time-domain resource, or, the first node does not transmit the second CSI on the second time-domain resource.

[0565] As an embodiment, the second node monitors whether the second CSI is transmitted by the first node on the second time-domain resource.

[0566] As an embodiment, the second node monitors whether the second CSI is sent by the first node on the second time-domain resource; when the second CSI is sent by the first node, the second node receives the second CSI; when the first node abandons sending the second CSI, the second node abandons receiving the second CSI.

[0567] As an embodiment, the second node monitors whether some or all of the information in the second CSI is sent by the first node on the second time-domain resource.

[0568] As an embodiment, the second node determines by itself whether to receive the second CSI on the second time-domain resource.

[0569] As an embodiment, the second node determines by itself whether to abandon receiving the second CSI on the second time-domain resource.

[0570] As an embodiment, the essence of the above method includes enhancing the completeness of the system and the solution.

[0571] As an embodiment, the first node sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0572] As an embodiment, when the first node abandons sending the first CSI on the first time-domain resource, the first node sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource, and the second node receives some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0573] As an embodiment, the second node monitors whether some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node on the second time-domain resource.

[0574] As an embodiment, the second node monitors whether some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node on the second time-domain resource; when some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node, the second node receives some or all of the information in the first CSI and some or all of the information in the second CSI.

[0575] As an embodiment, the second node itself determines whether to receive some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0576] As an embodiment, the essence of the above method includes enhancing the completeness of the system and the solution.

[0577] As an embodiment, whether the second CSI is abandoned by the first node from being sent on the second time-domain resource depends on whether the first CSI is sent on the first time-domain resource.

[0578] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0579] As an embodiment, when the first CSI is sent on the first time-domain resource, the first node sends the second CSI on the second time-domain resource.

[0580] As an embodiment, the benefits of the above method include reducing unnecessary or meaningless CSI reporting and reducing the system transmission overhead.

[0581] As an embodiment, the benefits of the above method include improving the overall performance of the system.

[0582] As an embodiment, whether some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node on the second time-domain resource depends on whether the first CSI is sent on the first time-domain resource.

[0583] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, the first node sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0584] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, the first node sends some or all of the information in the first CSI and the second CSI on the second time-domain resource.

[0585] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, the first node sends the first CSI and the second CSI on the second time-domain resource.

[0586] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part of the information in the first CSI and the second CSI on the second time-domain resource.

[0587] As an embodiment, the benefits of the above method include: improving the completeness and robustness of the AI-based solution.

[0588] As an embodiment, the benefits of the above method include: improving the accuracy and reliability of AI-based CSI reporting.

[0589] As an embodiment, the benefits of the above method include: improving the overall performance of the system.

[0590] As an embodiment, whether the first node transmits the second CSI on the second time-domain resource depends on whether the first CSI is transmitted on the first time-domain resource and whether a second condition is satisfied.

[0591] As an embodiment, when the first CSI is transmitted on the first time-domain resource, whether the first node transmits the second CSI on the second time-domain resource depends on whether the second condition is satisfied.

[0592] As an embodiment, when the first CSI is transmitted on the first time-domain resource, whether the first node transmits the second CSI on the second time-domain resource depends on whether the second condition is satisfied; when the second condition is satisfied, the first node abandons transmitting the second CSI on the second time-domain resource; when the second condition is not satisfied, the first node transmits the second CSI on the second time-domain resource.

[0593] As an embodiment, the second condition includes at least one sub-condition; when none of the at least one sub-conditions is satisfied, the second condition is not satisfied; when any one of the at least one sub-conditions is satisfied, the second condition is satisfied.

[0594] As an embodiment, the second condition includes that the second time-domain resource and other signals overlap in the time domain, or the second condition includes that the second time-domain resource includes at least one DL (downlink) symbol.

[0595] As an embodiment, the second condition includes a first sub-condition and a second sub-condition; the first sub-condition includes that the second time-domain resource and other signals overlap in the time domain; the second sub-condition includes that the second time-domain resource includes at least one DL (downlink) symbol; when neither the first sub-condition nor the second sub-condition is satisfied, the first condition is not satisfied; when any one of the first sub-condition and the second sub-condition is satisfied, the first condition is satisfied.

[0596] As an embodiment, the advantages of the above method include: improving the completeness and robustness of the solution.

[0597] As an embodiment, the advantages of the above method include: improving the overall performance of the system.

[0598] As an embodiment, whether some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node on the second time-domain resource depends on whether the first CSI is sent on the first time-domain resource and whether the second condition is satisfied.

[0599] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, whether some or all of the information in the first CSI and some or all of the information in the second CSI are sent by the first node on the second time-domain resource depends on whether the second condition is satisfied.

[0600] As an embodiment, when the first CSI is abandoned from being sent on the first time-domain resource, whether the first node sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource depends on whether the second condition is satisfied; when the second condition is satisfied, the first node abandons sending some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource; when the second condition is not satisfied, the first node sends some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0601] As an embodiment, the advantages of the above method include: ensuring as much as possible that CSI reporting can be sent.

[0602] As an embodiment, the advantages of the above method include: improving the completeness and robustness of the solution.

[0603] As an embodiment, the advantages of the above method include: improving the overall performance of the system.

[0604] As an example, when the first node transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource, the code rate of the CSI on the second time-domain resource is less than or equal to the maximum code rate configured by a higher-layer parameter.

[0605] As an example, when the first node transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource, the value of a first function is less than or equal to a first threshold, where the first function depends on the total number of bits transmitted on the second time-domain resource.

[0606] As an example, the value of the first function represents the total number of encoded bits, and the first threshold represents the total maximum number of encoded bits that can be carried on the second time-domain resource.

[0607] As an example, the first function is The first threshold is Or

[0608] As an example, the first function is The first threshold is Or

[0609] As an example, the first function is The first threshold is Or

[0610] As an example, the first function is (O CSI-2 +L CSI-2 ) / (N L ·Q′ CSI,2 ·Q m ), and the first threshold is

[0611] As an example, for the specific definitions of O CSI-2 , L CSI-2 , UL-SCH , K r , Q' CSI-1 , Q' ACK / CG-UCI , Q' ACK / UTO-UCI , α, N L , Q′ CSI,2 and Q m please refer to Section 6.3.2.4 of 3GPP TS 38.212.

[0612] As an example, is the CSI offset value, and its specific definition can be found in Table 9.3-2 of 3GPP TS38.213.

[0613] As an example, R is the signal coding rate in DCI (Downlink Control Information).

[0614] As an example, the benefits of the above method include: enhancing the flexibility and robustness of the system and adapting to applications in different transmission conditions and scenarios.

[0615] As an example, the benefits of the above method include: following the current system design and standards.

[0616] As an example, the benefits of the above method include: enhancing the overall performance of the system.

[0617] Example 6

[0618] Embodiment 6 exemplifies a schematic diagram of the operation when the first CSI is abandoned from being sent according to an embodiment of the present application; as shown in the appendix Figure 6 as follows.

[0619] In Embodiment 6, when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0620] As an example, the first CSI and the second CSI are associated; when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0621] As an example, the generation of the second CSI indirectly depends on the first CSI; when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0622] As an example, the generation of the second CSI depends on the information used for the first CSI; when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0623] As an example, the generation of the second CSI is based on the first CSI; when the first CSI is abandoned from being sent on the first time-domain resource, the first node abandons sending the second CSI on the second time-domain resource.

[0624] As an example, the first CSI and the second CSI are two consecutive CSI reports generated by the first node; when the transmission of the first CSI is abandoned on the first time-domain resource, the first node abandons the transmission of the second CSI on the second time-domain resource.

[0625] As an example, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration; when the transmission of the first CSI is abandoned on the first time-domain resource, the first node abandons the transmission of the second CSI on the second time-domain resource.

[0626] As an example, the essence of the above method includes: a CSI is reported only after all the CSIs related to it before are reported.

[0627] As an example, the advantages of the above method include: reducing the reporting of CSIs, reducing the reporting overhead, and improving the transmission efficiency of the system.

[0628] As an example, the advantages of the above method include: enhancing the overall performance of the system.

[0629] Example 7

[0630] Embodiment 7 exemplifies a schematic diagram of the operation when the first CSI is abandoned for transmission according to another embodiment of the present application; as shown in the attached Figure 7 figure.

[0631] In Embodiment 7, when the transmission of the first CSI is abandoned on the first time-domain resource, the first node transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0632] As an example, when the transmission of the first CSI is abandoned by the receiver of the first information block on the first time-domain resource, the first node transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource, and the second node receives some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0633] As an example, the first CSI and the second CSI are associated; when the transmission of the first CSI is abandoned on the first time-domain resource, the first node transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[0634] As an embodiment, the generation of the second CSI indirectly depends on the first CSI; when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[0635] As an embodiment, the generation of the second CSI depends on the information used for the first CSI; when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[0636] As an embodiment, the generation of the second CSI is based on the first CSI; when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[0637] As an embodiment, the first CSI and the second CSI are two consecutive CSI reports generated by the first node; when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[0638] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration; when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[0639] As an embodiment, the essence of the above method includes:

[0640] After a CSI related to a previous CSI is abandoned from being transmitted, the information of the previously abandoned CSI is carried when reporting the one CSI.

[0641] As an embodiment, the benefits of the above method include: ensuring the stability and reliability of CSI reporting as much as possible.

[0642] As an embodiment, the benefits of the above method include: enhancing the performance of AI-based CSI reporting.

[0643] As an embodiment, the benefits of the above method include: supporting the reporting of multiple consecutive or related CSIs.

[0644] As an embodiment, the benefits of the above method include: enhancing the overall performance of the system.

[0645] When the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits some or all of the information in the first CSI on the second time-domain resource.

[0646] When the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits the first CSI on the second time-domain resource.

[0647] As an embodiment, the essence of the above method includes: reporting the first CSI instead of the second CSI.

[0648] As an embodiment, the benefits of the above method include: preferentially reporting other CSIs associated with or dependent on a CSI.

[0649] As an embodiment, the benefits of the above method include: reducing the reporting of meaningless and worthless CSIs, making full use of the reporting resources, and improving the transmission efficiency of the system.

[0650] As an embodiment, the benefits of the above method include: enhancing the overall performance of the system.

[0651] When the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits some or all of the information in the first CSI and the second CSI on the second time-domain resource.

[0652] As an embodiment, the essence of the above method includes: carrying the information of the first CSI when reporting the second CSI.

[0653] As an embodiment, the benefits of the above method include: minimizing the possibility that a CSI report becomes a meaningless or worthless CSI as much as possible.

[0654] As an embodiment, the benefits of the above method include: making full use of the reporting resources and improving the transmission efficiency of the system.

[0655] As an embodiment, the benefits of the above method include: enhancing the overall performance of the system.

[0656] When the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits the first CSI and the second CSI on the second time-domain resource.

[0657] As an embodiment, the essence of the above method includes: retransmitting the first CSI when reporting the second CSI.

[0658] As an embodiment, the advantages of the above method include: making full use of reporting resources and improving the transmission efficiency of the system.

[0659] As an embodiment, the advantages of the above method include: enhancing the overall performance of the system.

[0660] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first node transmits partial information of the first CSI and partial information of the second CSI on the second time-domain resource.

[0661] As an embodiment, the advantages of the above method include: being able to report two CSIs simultaneously under resource-constrained conditions.

[0662] As an embodiment, the advantages of the above method include: being able to flexibly adjust the reporting ratio of the two CSIs and improving the flexibility of the system.

[0663] Example 8

[0664] Embodiment 8 exemplifies a schematic diagram of a first inference and a second inference according to an embodiment of the present application; as shown in the appendix Figure 8 as follows.

[0665] In Embodiment 8, both the first inference and the second inference are inferences corresponding to the first identifier.

[0666] As an embodiment, both the first inference and the second inference being inferences corresponding to the first identifier includes: both the first inference and the second inference are identified by the first identifier.

[0667] As an embodiment, both the first inference and the second inference being inferences corresponding to the first identifier includes: both the first inference and the second inference are inferences using the same AI model, and the first identifier is used to identify the same AI model.

[0668] As an embodiment, both the first inference and the second inference being inferences corresponding to the first identifier includes: both the first inference and the second inference are used for the AI function identified by the first identifier.

[0669] As an embodiment, both the first inference and the second inference being inferences corresponding to the first identifier includes: both the first inference and the second inference belong to the same AI entity, and the first identifier is used to identify the same AI entity.

[0670] As an embodiment, the advantages of the above method include: simplifying the system design and reducing the implementation complexity of the solution.

[0671] As an embodiment, the advantages of the above method include: supporting multiple inferences of an AI model or entity.

[0672] As an embodiment, the advantages of the above method include: improving the performance of AI-based CSI reporting.

[0673] As an embodiment, that the first inference and the second inference both correspond to a first identifier includes: the first inference and the second inference are two inferences of an AI model, and the first identifier is used to identify the AI model.

[0674] As an embodiment, that the first inference and the second inference both correspond to a first identifier includes: the first inference and the second inference are two inferences of an AI model, and the first identifier is used to identify the AI model.

[0675] As an embodiment, that the first inference and the second inference both correspond to a first identifier includes: the first inference and the second inference are two consecutive inferences of an AI model, and the first identifier is used to identify the AI model.

[0676] As an embodiment, the advantages of the above method include: supporting multiple consecutive inferences of an AI model.

[0677] As an embodiment, the advantages of the above method include: supporting the reporting of multiple consecutive CSIs.

[0678] As an embodiment, the advantages of the above method include: improving the performance of AI-based CSI reporting.

[0679] As an embodiment, that the first inference and the second inference both correspond to a first identifier includes: the same configuration is used to configure the first inference and the second inference, and the same configuration indicates the first identifier.

[0680] As an embodiment, that the first inference and the second inference both correspond to a first identifier includes: the same configuration is used to configure the first inference and the second inference, and the same configuration is identified by the first identifier.

[0681] As an embodiment, the first identifier is a non-negative integer.

[0682] As an embodiment, the first identifier is a string.

[0683] As an embodiment, the first identifier is used to identify an AI model.

[0684] As an embodiment, the first identifier is used to identify an AI entity.

[0685] As an example, the first identifier is used to identify the AI function.

[0686] As an example, the first identifier is used to identify the inference.

[0687] As an example, the first identifier is used to identify the AI inference.

[0688] As an example, the first identifier is a model identifier.

[0689] As an example, the first identifier is used by the first node to determine an AI model.

[0690] As an example, the advantages of the above method include: identifying an AI model / entity / function / inference by the first identifier, simplifying the system design, and unifying the understanding of different AI models / entities / functions / inferences among multiple nodes.

[0691] As an example, the first identifier is used to identify or indicate a resource set.

[0692] As an example, the first identifier is used to identify or indicate a resource set, and the measurement of the resource set is used to obtain a training data set.

[0693] As an example, the first identifier is used to identify or indicate a training data set.

[0694] As an example, the training for obtaining an AI model / entity / function / inference is identified by the first identifier.

[0695] As an example, the advantages of the above method include: identifying the inference generated by this AI training or AI training data set by identifying an AI training or an AI training data set, establishing a consensus among different AI functions, and further simplifying the system design.

[0696] As an example, the first identifier is used to identify or indicate a system configuration.

[0697] As an example, the first identifier is used to identify or indicate a system resource configuration.

[0698] As an example, the first identifier is used to identify or indicate a CSI reporting configuration.

[0699] As an example, the first identifier is used to identify the configuration information of a reference resource set, and the measurement of the reference resource set is used to obtain a training data set for an AI model / entity / function / inference.

[0700] As an embodiment, the benefits of the above method include: identifying an AI model / entity / function / inference by identifying a configuration information, simplifying the system design, and enhancing the flexibility of the system.

[0701] Example 9

[0702] Embodiment 9 exemplifies a schematic diagram of the configuration of a first CSI and a second CSI according to an embodiment of the present application; as shown in the appendix Figure 9 as follows.

[0703] In Embodiment 9, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration.

[0704] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two consecutive CSI reports configured by the same CSI reporting configuration.

[0705] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two associated CSI reports configured by the same CSI reporting configuration.

[0706] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration; the generation of the second CSI depends on the first CSI.

[0707] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration; the generation of the second CSI is based on the first CSI.

[0708] As an embodiment, the benefits of the above method include: supporting multiple consecutive or associated CSI reports.

[0709] As an embodiment, the benefits of the above method include: enhancing the performance of the system CSI reporting.

[0710] As an embodiment, the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0711] As an embodiment, the first information block indicates a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0712] As an embodiment, the first information block includes an identifier of a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0713] As an embodiment, the first information block includes an identifier of a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0714] As an embodiment, the first information block includes a first identifier, and the first identifier indicates a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0715] As an embodiment, the first information block includes at least one RRC IE, and the first CSI reporting configuration is carried by the at least one RRC IE, and the first CSI reporting configuration is used to configure the reporting of the first CSI and the reporting of the second CSI.

[0716] As an embodiment, the advantages of the above method include: better adapting to different transmission conditions and application scenarios, and improving the flexibility of the system.

[0717] As an embodiment, the first CSI reporting configuration at least indicates at least one of the RS resources for the measurement of the reporting of the first CSI and the reporting of the second CSI, the reporting type of the reporting of the first CSI and the reporting of the second CSI, or the reporting amount of the reporting of the first CSI and the reporting of the second CSI.

[0718] As an embodiment, the first CSI reporting configuration at least indicates at least one of the RS resources for the measurement of the reporting of the first CSI and the reporting of the second CSI, at least one of the RS resources targeted by the reporting of the first CSI and the reporting of the second CSI, the reporting type of the reporting of the first CSI and the reporting of the second CSI, or the reporting amount of the reporting of the first CSI and the reporting of the second CSI.

[0719] As a sub - embodiment of the above embodiment, the measurement includes at least one of channel measurement and interference measurement.

[0720] As a sub - embodiment of the above embodiment, the reporting type indicates at least one of periodic reporting, semi - persistent reporting, or aperiodic reporting.

[0721] As a sub - embodiment of the above embodiment, the reporting type indicates at least one of periodic reporting, semi - persistent reporting, aperiodic reporting, or event - triggered reporting.

[0722] As an embodiment, the first information block indicates a third configuration, which is used to configure the first inference and the second inference, and the first CSI and the second CSI respectively depend on the outputs of the first inference and the second inference.

[0723] As an embodiment, the first information block includes a first identifier, which indicates a third configuration, which is used to configure the first inference and the second inference, and the first CSI and the second CSI respectively depend on the outputs of the first inference and the second inference.

[0724] As an embodiment, the first information block includes at least one RRC IE, and the third configuration is carried by the at least one RRC IE, which is used to configure the first inference and the second inference, and the first CSI and the second CSI respectively depend on the outputs of the first inference and the second inference.

[0725] As an embodiment, the advantages of the above method include: simplifying the design of the system and improving the flexibility of the system.

[0726] As an embodiment, the third configuration includes at least one RRC IE.

[0727] As an embodiment, the third configuration includes at least one IE CSI-ReportConfig.

[0728] As an embodiment, the third configuration includes some or all fields of at least one RRC IE.

[0729] As an embodiment, the third configuration includes some or all fields of at least one IE CSI-ReportConfig.

[0730] As an embodiment, the third configuration is carried by at least one RRC IE.

[0731] As an embodiment, the third configuration is carried by at least one IE CSI-ReportConfig.

[0732] As an embodiment, the advantages of the above method include: following the current standards and system design.

[0733] Example 10

[0734] Example 10 exemplifies a schematic diagram of a first condition according to an embodiment of the present application; as shown in the appendix Figure 10 as shown.

[0735] In Embodiment 10, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and the first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0736] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and the resource carrying the first signal overlap in the time domain and / or the frequency domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0737] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and the first signal overlap in the time domain.

[0738] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[0739] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource is used for DL (downlink) transmission.

[0740] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource is disabled.

[0741] As an embodiment, when the first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and the first signal overlap in the time domain, or the first time-domain resource includes at least one DL (downlink) symbol.

[0742] As an embodiment, the first condition includes at least one sub-condition; when any one of the at least one sub-conditions is satisfied, the first condition is satisfied; when all of the at least one sub-conditions are not satisfied, the first condition is not satisfied.

[0743] As a sub-embodiment of the above embodiment, one of the at least one sub-conditions is that the first time-domain resource and the first signal overlap in the time domain.

[0744] As a sub - embodiment of the above - mentioned embodiment, one of the at least one sub - conditions is that the first time - domain resource includes at least one DL (downlink) symbol.

[0745] As a sub - embodiment of the above - mentioned embodiment, one of the at least one sub - conditions is that the first time - domain resource is used for DL (downlink) transmission.

[0746] As a sub - embodiment of the above - mentioned embodiment, one of the at least one sub - conditions is that the first time - domain resource is disabled.

[0747] As an embodiment, the essence of the above - mentioned method includes: avoiding transmission conflicts between CSI reporting and other signals.

[0748] As an embodiment, the benefits of the above - mentioned method include: improving the stability and robustness of the system.

[0749] As an embodiment, the benefits of the above - mentioned method include: improving the overall performance of the system.

[0750] As an embodiment, the first signal includes a synchronization signal.

[0751] As an embodiment, the first signal includes an SS / PBCH block.

[0752] As an embodiment, the first signal includes a PDCCH (Physical Downlink Control Channel).

[0753] As an embodiment, the first signal includes a PDSCH (Physical Downlink Shared Channel).

[0754] As an embodiment, the first signal carries HARQ - ACK.

[0755] As an embodiment, the first signal carries DCI.

[0756] As an embodiment, the first signal includes a PUCCH (Physical Uplink Control Channel).

[0757] As an embodiment, the first signal includes a PUSCH (Physical Uplink Shared Channel).

[0758] As an example, the priority of the first signal is higher than the priority of the first CSI.

[0759] As an example, the first signal includes a retransmitted CSI report.

[0760] As an example, the first signal includes a CSI that is reported repeatedly multiple times.

[0761] As an example, the first signal is a blank signal.

[0762] As an example, the first signal is a predefined signal.

[0763] As an example, the advantages of the above method include: improving the stability and completeness of the system.

[0764] As an example, the advantages of the above method include: better adapting to different transmission conditions and application scenarios, and improving the flexibility of the system.

[0765] Example 11

[0766] Example 11 illustrates a schematic diagram of a first RS resource set according to an embodiment of the present application; as shown in the appendix Figure 11 Resources #1,..., Resources #n,..., Resources #m,... represent the resources in the first RS resource set.

[0767] In Example 11, the first information block indicates the first RS resource set; at least one of the input of the first inference and the input of the second inference depends on the measurement based on the first RS resource set.

[0768] As an example, the first information block indicating the first RS resource set includes: the first information block indicates the identifier of the first RS resource set.

[0769] As an example, the first information block indicating the first RS resource set includes: the first information block indicates the identifier of the first RS resource set.

[0770] As an example, the first information block indicating the first RS resource set includes: the first information block includes the information of the first RS resource set.

[0771] As an example, the first information block indicating the first RS resource set includes: the first information block includes the configuration information of the first RS resource set.

[0772] As an example, the first information block indicating the first RS resource set includes: the first information block indicates a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the first RS resource set.

[0773] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration is used to configure the first RS resource set.

[0774] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration is used to indicate the first RS resource set.

[0775] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration includes an identifier of the first RS resource set.

[0776] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration includes an identifier of the first RS resource set.

[0777] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration indicates configuration information of the first RS resource set.

[0778] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration is used to indicate the first RS resource set from a reference resource set.

[0779] As an example, the first information block indicating the first RS resource set includes: the first information block includes a first CSI reporting configuration, and the first CSI reporting configuration indicates a first identifier, and the first RS resource set depends on the first identifier.

[0780] As an example, the first RS resource set depending on the first identifier includes: the first identifier is used to identify the first RS resource set.

[0781] As an example, the first RS resource set depending on the first identifier includes: the first identifier is used to identify a reference resource set, and the reference resource set includes the first RS resource set.

[0782] As an example, the first RS resource set depending on the first identifier includes: the first identifier is used to identify a reference resource set, the reference resource set includes the first RS resource set, and the first CSI reporting configuration is used to indicate the first RS resource set from the reference resource set.

[0783] As an example, the resources in the first RS resource set include at least one of an antenna port, a TCI (Transmission Configuration Indication) state, QCL (Quasi Co-Location) information, time-frequency resources, time-frequency code resources, a beam, an RS resource, a vector, or a matrix.

[0784] As an example, the first RS resource set includes one or more RS (Reference Signal) resource sets, and one RS resource set includes one or more RS resources.

[0785] As an example, the first RS resource set includes at least one of at least one 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.

[0786] As an example, the first RS resource set includes at least one RS resource set for channel measurement.

[0787] As an example, the first RS resource set includes at least one RS resource set for channel measurement and at least one RS resource set for interference measurement.

[0788] As an example, the first RS resource set includes at least one RS resource set for interference measurement.

[0789] As a sub-example of the above example, an RS resource set for channel measurement includes one or more RS resources.

[0790] As a sub-example of the above example, an RS resource set for interference measurement includes one or more RS resources.

[0791] As an example, a set of RS resources for channel measurement includes one or more RS resources, and any RS resource in the set of RS resources for channel measurement is a CSI-RS resource or a synchronization signal resource.

[0792] As an example, a set of RS resources for interference measurement includes one or more RS resources, and any RS resource in the set of RS resources for interference measurement is a CSI-IM resource or a NZP (non-zero power) CSI-RS resource for interference measurement.

[0793] As an example, the first set of RS resources includes one or more RS resources.

[0794] As an example, the first set of RS resources includes one or more downlink RS resources.

[0795] As an example, the first set of RS resources includes one or more RS resources, and any RS resource in the first set of RS resources is a CSI-RS (Channel State Information Reference Signal) resource or a synchronization signal resource.

[0796] As an example, the synchronization signal resource includes at least the resources occupied by the synchronization signal.

[0797] As an example, the synchronization signal resource is an SSB (Synchronization Signal Block).

[0798] As an example, the synchronization signal resource is an SS / PBCH (synchronization signal / physical broadcast channel) block resource.

[0799] As an example, the input of the first inference depends on the measurement based on the first set of RS resources.

[0800] As an example, the input of the second inference depends on the measurement based on the first set of RS resources.

[0801] As an example, the input of the first inference and the input of the second inference depend on the measurement based on the first set of RS resources.

[0802] As an example, the input of the first inference depends on the historical measurement based on the first set of RS resources.

[0803] As an example, the input dependency of the second inference is based on historical measurements of the first RS resource set.

[0804] As an example, the benefits of the above method include: reducing the channel information feedback delay and improving the real-time performance of channel information acquisition.

[0805] As an example, the input of the first inference and the input dependency of the second inference are based on historical measurements of the first RS resource set.

[0806] As an example, the input dependency of the second inference is based on the measurements of the first RS resource set and the output of the first inference.

[0807] As an example, the input dependency of the second inference is based on historical measurements of the first RS resource set and the output of the first inference.

[0808] As an example, an input depending on a measurement includes: an input depending on all or part of the content of a measurement.

[0809] As an example, an input depending on a measurement includes: the measurement is used to generate the input.

[0810] As an example, an input depending on a measurement includes: after post-processing the measurement, it is used to generate the input.

[0811] As an example, an input depending on a measurement includes: the input includes the measurement.

[0812] As an example, an input depending on a measurement includes: the input includes all or part of the content of the measurement.

[0813] As an example, an input depending on a measurement includes: the input includes the result of post-processing the measurement.

[0814] As an example, the benefits of the above method include: enhancing the flexibility of the system and better adapting to various different transmission conditions and application scenarios.

[0815] As an example, the benefits of the above method include: enhancing the backward compatibility of the system.

[0816] As an example, the measurements obtained based on the first RS resource set include at least one of channel measurements and interference measurements obtained from the first RS resource set.

[0817] As an example, the measurements obtained based on the first RS resource set include at least one of channel measurements and interference measurements obtained based on at least one reference signal transmitted in the first RS resource set.

[0818] As an example, the channel measurements obtained based on the first RS resource set include a channel matrix.

[0819] As an example, the channel measurements obtained based on the first RS resource set include a raw channel matrix.

[0820] As an example, the channel measurements obtained based on the first RS resource set include an eigenvector.

[0821] As an example, the channel measurements obtained based on the first RS resource set include an eigenvector and an eigenvalue.

[0822] As an example, the channel measurements obtained based on the first RS resource set include one or more of BLER, delay spread, Doppler spread, Doppler shift, average delay, average gain, path loss, and RSRP.

[0823] As an example, the interference measurements obtained based on the first RS resource set include at least one of interference power, interference variance, or interference power spectral density.

[0824] As an example, the interference measurements obtained based on the first RS resource set include an interference channel matrix.

[0825] As an example, the interference measurements obtained based on the first RS resource set include an interference covariance matrix.

[0826] As an example, the interference measurements obtained based on the first RS resource set include an interference eigenvector.

[0827] As an example, the interference measurements obtained based on the first RS resource set include an interference eigenvector and an interference eigenvalue.

[0828] As an example, the interference measurements obtained based on the first RS resource set include an interference beam.

[0829] Example 12

[0830] Example 12 exemplifies a schematic diagram of the outputs of a first inference and a second inference according to an embodiment of the present application; as shown in the attached Figure 12 figure.

[0831] In Example 12, the output of the second inference depends on the output of the first inference.

[0832] As an embodiment, the output of the second inference indirectly depends on the output of the first inference.

[0833] As an embodiment, the information used to generate the output of the second inference depends on the output of the first inference.

[0834] As an embodiment, the information used to generate the output of the second inference depends on the information used to generate the output of the first inference.

[0835] As an embodiment, there is a same part between the information used to generate the output of the second inference and the information used to generate the output of the first inference.

[0836] As an embodiment, there is an overlapping part between the information used to generate the output of the second inference and the information used to generate the output of the first inference.

[0837] As an embodiment, there is a part of information that is used to generate the output of the first inference and the output of the second inference at the same time.

[0838] As an embodiment, the output of the second inference is based on the output of the first inference.

[0839] As an embodiment, part of the information of the output of the first inference can be inferred according to the output of the second inference.

[0840] As an embodiment, the input of the second inference depends on the output of the first inference.

[0841] As an embodiment, the input of the second inference depends on a partial output of the first inference.

[0842] As an embodiment, the output of the first inference includes a first output and a second output, and the input of the second inference includes the second output.

[0843] As an embodiment, the first inference and the second inference correspond to the same AI model, and the output of the second inference is the next output of the same AI model after the output of the first inference.

[0844] As an example, the first inference and the second inference correspond to the same AI model, and the output of the second inference is the subsequent output of the same AI model after the output of the first inference.

[0845] As an example, the first inference and the second inference correspond to the same AI model, and the outputs of the first inference and the second inference are two outputs of the same AI model; the input of the same AI model includes a partial output of the same AI model.

[0846] As an example, the first inference and the second inference correspond to the same AI model, and the outputs of the first inference and the second inference are two consecutive outputs of the same AI model; the input of the same AI model includes a partial output of the same AI model.

[0847] As an example, the advantages of the above method include: supporting an AI model based on a recurrent neural network architecture and improving the performance of CSI reporting.

[0848] As an example, the advantages of the above method include: supporting an AI model based on a Transformer architecture and improving the performance of CSI reporting.

[0849] As an example, the advantages of the above method include: improving the overall performance of the system.

[0850] As an example, both the first inference and the second inference are inferences corresponding to a first identifier, and the first inference is executed prior to the second inference.

[0851] As an example, both the first inference and the second inference are inferences corresponding to a first identifier, the first identifier is used to identify an AI model, and the first inference is executed prior to the second inference.

[0852] As an example, the advantages of the above method include: simplifying the system design and reducing the implementation complexity of the solution.

[0853] Example 13

[0854] Example 13 exemplifies a schematic diagram of a first given inference according to an embodiment of the present application; as shown in the appendix Figure 13 In Example 13, the first given inference includes K1 sub-operations, where K1 is a positive integer not greater than 1; the first given inference is the first inference or the second inference.

[0855] In Example 13, the K1 sub-operations are respectively denoted as sub-operation #0,..., sub-operation #(K1 - 1).

[0856] As an embodiment, each of the K1 sub-operations is training-based.

[0857] As an embodiment, at least one of the K1 sub-operations is training-based.

[0858] As an embodiment, the executors of the training on which each of the training-based K1 sub-operations is based are the same.

[0859] As an embodiment, the executors of the training on which two of the K1 sub-operations are based are different.

[0860] As an embodiment, at least one of the K1 sub-operations needs to be deployed.

[0861] As an embodiment, at least one of the K1 sub-operations needs to be loaded.

[0862] As an embodiment, all the sub-operations among the K1 sub-operations that need to be loaded are loaded from the same producer.

[0863] As an embodiment, two of the K1 sub-operations that need to be loaded are loaded from different producers.

[0864] As an embodiment, at least one of the K1 sub-operations is not training-based.

[0865] As an embodiment, 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.

[0866] As an embodiment, one or more of the K1 sub-operations are AI-based.

[0867] As an embodiment, one or more of the K1 sub-operations include inference.

[0868] As an embodiment, one or more of the K1 sub-operations include AI inference.

[0869] As an embodiment, one or more of the K1 sub-operations include AI inference for CSI.

[0870] As an embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0871] As an example, one or more of the K1 sub-operations include preprocessing.

[0872] As an example, one or more of the K1 sub-operations include postprocessing.

[0873] As an example, two of the K1 sub-operations are serial, such as all the sub-operations in Figure 13 (a), sub-operations #2 to #(K1 - 1) in 13(b), and sub-operations #0 to #(K1 - 4) in 13(c).

[0874] As an example, 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.

[0875] As an example, two of the K1 sub-operations are parallel, such as sub-operations #0 and #1 in Figure 13 (b), and sub-operations #(K1 - 3) and #(K1 - 2) in Figure 13 (c).

[0876] As an example, two sub-operations being parallel means that the outputs of the two sub-operations are jointly used as the input of another sub-operation.

[0877] As an example, the K1 sub-operations include one or more of convolution, pooling, concatenation, or activation.

[0878] As an example, one of the K1 sub-operations includes a fully connected layer.

[0879] As an example, one of the K1 sub-operations includes a pooling layer.

[0880] As an example, one of the K1 sub-operations includes at least one convolutional layer.

[0881] As an example, one of the K1 sub-operations includes at least one encoding layer.

[0882] As an example, two of the K1 sub-operations respectively include a fully connected layer and at least one encoding layer.

[0883] As an example, one encoding layer includes at least one convolutional layer and one pooling layer.

[0884] Example 14

[0885] Example 14 illustrates a schematic diagram of deploying a first given inference according to an embodiment of the present application; as shown in Figure 14.

[0886] In Example 14, the first processor deploys the first given inference; the first given inference is the first inference or the second inference.

[0887] As an embodiment, the deployment includes obtaining the first given inference.

[0888] As an embodiment, the deployment includes obtaining an AI entity.

[0889] As an embodiment, the deployment includes obtaining an AI entity that executes the first given inference.

[0890] As an embodiment, the deployment includes obtaining an AI entity that includes an AI function for executing the first given inference.

[0891] As an embodiment, the deployment includes loading the first given inference.

[0892] As an embodiment, the deployment includes making a request to load the first given inference.

[0893] As an embodiment, the request in Figure 14 is a request made by the first node to load the first given inference.

[0894] As an embodiment, the response in Figure 14 is a response to the request made by the first node to load the first given inference.

[0895] As an embodiment, the first node obtains the first given inference through the response in Figure 14.

[0896] As an embodiment, the first given inference is loaded and obtained from the serving cell of the first node.

[0897] As an embodiment, the first given inference is loaded and obtained from the maintenance base station of the serving cell of the first node.

[0898] As an embodiment, the first given inference is loaded and obtained from the core network.

[0899] As an embodiment, the first given inference is loaded and obtained from a first producer.

[0900] As an example, the first producer provides the first given inference to the first node through the response in FIG. 14.

[0901] As an example, the deployment is completed by an AI function.

[0902] As an example, the deployment is completed by an AI function deployed on the first node.

[0903] As an example, the deployment is completed by an AI deployment function.

[0904] As an example, the deployment is completed by an AI deployment function deployed on the first node.

[0905] As an example, the deployment is completed by an AI inference function.

[0906] As an example, the deployment is completed by an AI inference function deployed on the first node.

[0907] As an example, the deployment is completed by an AI entity.

[0908] As an example, the deployment is completed by an AI entity deployed on the first node.

[0909] As an example, the deployment is completed by an AI entity having a deployment function.

[0910] As an example, the deployment is completed by an AI entity having a deployment function deployed on the first node.

[0911] As an example, the deployment is completed by an AI entity having an inference function.

[0912] As an example, the deployment is completed by an AI entity having an inference function deployed on the first node.

[0913] As an example, the deployment includes obtaining the first given inference from a first producer.

[0914] As an example, the deployment includes requesting the first producer to load the first given inference.

[0915] As an example, the deployment includes loading the first given inference from a first producer.

[0916] As an example, the first producer generates and provides an AL entity.

[0917] As an example, the first producer generates and provides an AL function.

[0918] As an example, the first producer is the producer of the first given inference.

[0919] As an example, the first producer includes an AL entity producer.

[0920] As an example, the first producer includes an AL function producer.

[0921] As an example, the first producer includes an AL deployment producer.

[0922] As an example, the first producer includes an AL loading producer.

[0923] As an example, the first producer includes an AL training producer.

[0924] As an example, the first producer includes an AL inference producer.

[0925] As an example, the first producer includes a producer of the deployment of an AL entity.

[0926] As an example, the first producer includes a producer of the loading of an AL entity.

[0927] As an example, the first producer includes a MnS (Management Service) producer.

[0928] As an example, the sender of the first configuration information block is the first producer.

[0929] As an example, the sender of the first configuration information block is different from the first producer.

[0930] As an example, the training for obtaining the first given inference is performed by the first producer.

[0931] As an example, the performer of the training for obtaining the first given inference is different from the first producer.

[0932] As an example, the AI includes ML (Machine Learning).

[0933] Example 15

[0934] Example 15 illustrates a schematic diagram of an artificial intelligence or machine learning-based processing system according to an embodiment of the present application; as shown in the accompanying Figure 15 drawing. The accompanying Figure 15 (a) includes a third processor, a fourth processor, and a fifth processor, and the accompanying Figure 15 (b) includes a third processor, a fourth processor, a fifth processor, and a sixth processor.

[0935] In Example 15(a), the third processor sends a first data set to the fourth processor and a second data set to the fifth processor; the fourth processor generates a target first type of parameter set according to the first data set, and the fourth processor sends the generated target first type of parameter set to the fifth processor; the fifth processor processes the second data set using the target first type of parameter set to obtain a first type of output. In the accompanying Figure 15 (a), the first type of feedback is optional.

[0936] In Example 15(b), the third processor sends a first data set to the fourth processor and a second data set to the fifth processor; the fourth processor generates a target first type of parameter set according to the first data set, and the fourth processor sends the generated target first type of parameter set to the fifth processor; the fifth processor processes the second data set using the target first type of parameter set to obtain a first type of output, and the fifth processor sends the first type of output to the sixth processor. In the accompanying Figure 15 (b), the first type of feedback and the second type of feedback are optional.

[0937] As an embodiment, in the accompanying Figure 15 (a), the fifth processor sends the first type of output to the second node in the present application.

[0938] As an embodiment, in the accompanying Figure 15 (a), a single side AI model is adopted for beam prediction or channel information prediction, and the fifth processor performs at least one of the first inference and the second inference, and at least one of the first inference and the second inference is used for beam prediction or channel information prediction.

[0939] As an embodiment, in the accompanying Figure 15(b) A two-sided AI model is adopted for CSI compression. At least one of the first inference and the second inference is used for compressing CSI, and the third inference is used for recovering CSI. The fifth processor executes at least one of the first inference and the second inference, and the sixth processor includes the third inference.

[0940] As an embodiment, append Figure 15 (b) A two-sided AI model is adopted for CSI prediction and compression. At least one of the first inference and the second inference is used for predicting and compressing CSI, and the third inference is used for recovering CSI. The fifth processor executes at least one of the first inference and the second inference, and the sixth processor includes the third inference.

[0941] As an embodiment, the fifth processor executes at least one of the first inference and the second inference.

[0942] As an embodiment, the sixth processor includes the third inference.

[0943] As an embodiment, the fifth processor sends a first type of feedback to the fourth processor, and the first type of feedback is used to trigger recalculation or update of the target first type of parameter group.

[0944] As an embodiment, the sixth processor sends a second type of feedback to the third processor, and the second type of feedback is used to generate the first data set or the second data set, or the second type of feedback is used to trigger the sending of the first data set or the sending of the second data set.

[0945] As an embodiment, the third processor generates the first data set and the second data set based on measurements of a first type of wireless signal, and the first type of wireless signal includes downlink RS.

[0946] As an embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[0947] As an embodiment, the first CSI and the second CSI belong to the first type of output.

[0948] As an embodiment, the second data set includes the input of the first inference.

[0949] As an embodiment, the second data set includes the input of the second inference.

[0950] As an embodiment, the second data set includes the inputs of the first inference and the second inference.

[0951] As an example, the second data set includes information obtained based on the first information block.

[0952] As an example, the first data set includes Training Data.

[0953] As an example, the fourth processor belongs to the producer of the first inference.

[0954] As an example, the fourth processor belongs to the producer of the second inference.

[0955] As an example, the fourth processor includes an AI training producer.

[0956] As an example, the fourth processor includes an AI training function.

[0957] As an example, the fourth processor is used for Model Training, and the trained model is described by the target first type of parameter group.

[0958] As an example, the fourth processor belongs to the first node.

[0959] The above example avoids transmitting the first data set to the second node.

[0960] As an example, the fourth processor belongs to the second node.

[0961] The above example supports joint training and optimizes system performance.

[0962] As an example, the fourth processor belongs to the core network.

[0963] The above example supports full-network joint training and further optimizes system performance.

[0964] As an example, the second data set includes Inference Data.

[0965] As an example, the fifth processor includes an AI inference producer.

[0966] As an example, the fifth processor includes an AI inference function.

[0967] As an example, the fifth processor belongs to the first node.

[0968] As an example, the fifth processor constructs a model according to the target first type of parameter group, and then inputs the second data set into the constructed model to obtain the first type of output.

[0969] As an example, the first inference is described by the target first type of parameter group.

[0970] As an example, the second inference is described by the target first type of parameter group.

[0971] As an example, the first inference and the second inference are described by the target first type of parameter group.

[0972] As an example, the target first type of parameter group is used to construct the first inference.

[0973] As an example, the target first type of parameter group is used to construct the second inference.

[0974] As an example, the target first type of parameter group is used to construct the first inference and the second inference.

[0975] As an example, the fifth processor includes the third inference.

[0976] As an example, the fifth processor generates a recovery data set according to the first type of output, and the error between the recovery data set and the second data set is used to generate the first type of feedback.

[0977] As a sub - example of the above example, the generation of the recovery data set adopts a method similar to the third inference.

[0978] 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 does not meet the requirements, the fourth processor recalculates the target first type of parameter group.

[0979] As an example, when the error is too large or there is no update for too long, the performance of the trained model is considered not to meet the requirements.

[0980] As an example, the target first type of parameter group includes one or more of: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[0981] As an example, the target first type of parameter group includes one or more of: convolution kernel, pooling kernel, pooling function, activation function, parameters of the pooling function, or parameters of the activation function.

[0982] Example 16

[0983] Example 16 exemplifies a schematic diagram based on artificial intelligence or machine learning according to an embodiment of the present application; as shown in the appendix Figure 16 shown. Appendix Figure 16 Includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation; the arrowed lines indicate the order of the process.

[0984] In Example 16, the third operation and the fourth operation 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.

[0985] As an embodiment, the third operation includes AI training, the fourth operation includes AI testing, the fifth operation includes AI emulation, the sixth operation includes AI entity loading, and the seventh operation includes AI inference.

[0986] As an 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 inference phase.

[0987] As an embodiment, the first stage includes AI model training.

[0988] As an embodiment, the first stage includes AI model training and AI testing.

[0989] As an embodiment, the AI includes ML (Machine Learning) inference.

[0990] As an embodiment, the AI model training includes the initial training and re-training of one or a group of AI entities.

[0991] As an embodiment, the AI model training depends on training data.

[0992] As an embodiment, the AI model training includes AI entity validation.

[0993] As an example, the AI entity verification is used to evaluate the performance of the AI entity.

[0994] As an example, the AI entity verification relies on verification data.

[0995] As an example, if the result of the AI entity verification does not meet the expectation, the AI model will be retrained.

[0996] As an example, the AI testing includes testing the verified AI entity to evaluate the performance of the trained AI model.

[0997] As an example, if the result of the AI testing meets the expectation, the AI entity proceeds to the next stage; otherwise, the AI model will be retrained.

[0998] As an example, the AI testing relies on test data.

[0999] As an example, the second stage includes AI simulation, and the AI simulation performs inference of the AI entity in a simulation environment.

[1000] As an example, the AI simulation estimates the performance of the AI entity inference in a simulation environment before using the AI entity.

[1001] As an example, the second stage is optional.

[1002] As an example, the third stage includes AI entity loading, and the AI entity loading is to obtain the trained AI entity to obtain the desired AI inference function.

[1003] As an example, the third stage is optional.

[1004] As an example, when the training function and the inference function are co-located, the third stage is no longer required.

[1005] As an example, the fourth stage includes AI inference.

[1006] As an example, the seventh operation includes the first inference.

[1007] As an example, the seventh operation includes the second inference.

[1008] As an example, the seventh operation includes the third inference.

[1009] Example 17

[1010] Embodiment 17 exemplifies a structural block diagram of a processing device in a first node according to an embodiment of the present application; as shown in the appended Figure 17 appendix. In the appended Figure 17 appendix, the processing device 1700 in the first node includes a first processor 1701.

[1011] The first processor 1701 receives a first information block; transmits first CSI on the first time-domain resource, or abandons transmitting first CSI on the first time-domain resource; and transmits second CSI on the second time-domain resource only when the first CSI is transmitted on the first time-domain resource.

[1012] In Embodiment 17, the first information block indicates a first time-domain resource and a second time-domain resource; the first CSI and the second CSI respectively depend on the outputs of a first inference and a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[1013] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 abandons transmitting the second CSI on the second time-domain resource.

[1014] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 transmits some or all of the information in the first CSI and some or all of the information in the second CSI on the second time-domain resource.

[1015] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 transmits the first CSI on the second time-domain resource.

[1016] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 transmits some of the information in the first CSI and some of the information in the second CSI on the second time-domain resource.

[1017] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 transmits some of the information in the first CSI and the second CSI on the second time-domain resource.

[1018] As an embodiment, when the first CSI is abandoned from being transmitted on the first time-domain resource, the first processor 1701 transmits the first CSI and the second CSI on the second time-domain resource.

[1019] As an embodiment, both the first inference and the second inference are inferences corresponding to a first identifier.

[1020] As an embodiment, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration.

[1021] As an embodiment, when a first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and a first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[1022] As an embodiment, when a first condition is satisfied, the first CSI is abandoned from being transmitted on the first time-domain resource; the first condition includes that the first time-domain resource and a first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[1023] As an embodiment, the first information block indicates a first RS resource set; at least one of the input of the first inference and the input of the second inference depends on measurements based on the first RS resource set.

[1024] As an embodiment, the output of the second inference depends on the output of the first inference.

[1025] As an embodiment, the first inference and the second inference are training-based or AI-based.

[1026] As an embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[1027] As an embodiment, the first processor 1701 deploys the first inference.

[1028] As an embodiment, the first processor 1701 deploys the second inference.

[1029] As an embodiment, the first inference and the second inference are obtained by loading.

[1030] As an embodiment, the first processor 1701 receives a signal in the first RS resource set.

[1031] As an example, the first processor 1701 receives a reference signal in the first RS resource set, and the first RS resource set includes one or more RS resources.

[1032] As an example, the first node is a user equipment.

[1033] As an example, the first node is a terminal.

[1034] As an example, the first node is a relay node.

[1035] As an example, the user equipment is a terminal.

[1036] As an example, the first processor 1701 includes at least one of {antenna 452, receiver / transmitter 454, receive processor 456, transmit processor 468, multi-antenna receive processor 458, multi-antenna transmit processor 457, controller / processor 459, memory 460, data source 467} in Embodiment 4.

[1037] Example 18

[1038] Embodiment 18 exemplifies a structural block diagram of a processing device in a second node according to an embodiment of the present application; as shown in the appended Figure 18 drawing. In the appended Figure 18 drawing, the processing device 1800 in the second node includes a second processor 1801.

[1039] The second processor 1801 sends a first information block; when the first CSI is sent by the receiver of the first information block in the first time domain resource, receives the first CSI in the first time domain resource, and receives the second CSI in the second time domain resource.

[1040] In Embodiment 18, the first information block indicates a first time domain resource and a second time domain resource; the receiver of the first information block sends the first CSI in the first time domain resource or abandons sending the first CSI in the first time domain resource; only when the first CSI is sent by the receiver of the first information block in the first time domain resource, the receiver of the first information block sends the second CSI in the second time domain resource; the first CSI and the second CSI respectively depend on the output of a first inference and the output of a second inference; the output of the first inference includes a first output and a second output, the first CSI depends on the first output, and the input of the second inference includes the second output.

[1041] As an example, the second processor 1801 monitors whether the first CSI is sent by the receiver of the first information block on the first time-domain resource.

[1042] As an example, the second processor 1801 monitors whether the second CSI is sent by the receiver of the first information block on the second time-domain resource.

[1043] As an example, the second processor 1801 monitors whether part or all of the information in the second CSI is sent by the receiver of the first information block on the second time-domain resource.

[1044] As an example, the second processor 1801 monitors whether part or all of the information in the first CSI and part or all of the information in the second CSI are sent by the receiver of the first information block on the second time-domain resource.

[1045] As an example, when the receiver of the first information block abandons sending the first CSI on the first time-domain resource, the receiver of the first information block abandons sending the second CSI on the second time-domain resource.

[1046] As an example, when the receiver of the first information block abandons sending the first CSI on the first time-domain resource, the second processor 1801 abandons receiving the second CSI on the second time-domain resource.

[1047] As an example, when the receiver of the first information block abandons sending the first CSI on the first time-domain resource, the second processor 1801 receives part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource; wherein, the receiver of the first information block sends part or all of the information in the first CSI and part or all of the information in the second CSI on the second time-domain resource.

[1048] As an example, both the first inference and the second inference are inferences corresponding to the first identifier.

[1049] As an example, the reporting of the first CSI and the reporting of the second CSI are two CSI reports configured by the same CSI reporting configuration.

[1050] As an example, when the first condition is satisfied, the first CSI is not sent by the receiver of the first information block on the first time-domain resource; the first condition includes that the first time-domain resource and the first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[1051] As an example, when the first condition is satisfied, the first CSI is not sent by the receiver of the first information block on the first time-domain resource; the first condition includes that the first time-domain resource and the first signal overlap in the time domain, or the first condition includes that the first time-domain resource includes at least one DL (downlink) symbol.

[1052] As an example, the first information block indicates a first RS resource set; at least one of the inputs of the first inference and the inputs of the second inference depends on measurements based on the first RS resource set.

[1053] As an example, the first inference and the second inference are training-based or AI-based.

[1054] As an example, the AI (Artificial Intelligence) includes ML (Machine Learning).

[1055] As an example, the first inference and the second inference are obtained by loading.

[1056] As an example, the second processor 1801 sends a signal in the first RS resource set.

[1057] As an example, the second processor 1801 sends a reference signal in the first RS resource set, and the first RS resource set includes one or more RS resources.

[1058] As an example, the second node includes a base station.

[1059] As an example, the second node includes a core network.

[1060] As an example, the second node includes a base station and a core network.

[1061] As an example, the second node includes a relay node.

[1062] As an example, the second node includes a user equipment.

[1063] As an embodiment, the user equipment is a terminal.

[1064] As an embodiment, the second processor 1801 includes at least one of {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} in Embodiment 4.

[1065] Those of ordinary skill in the art can understand that all or part of the steps in the above method can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a hard disk, or an optical disc, etc. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the above embodiments can be implemented in a hardware form or in the form of a software functional module. This application is not limited to any specific form of the 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 control aircraft, aircraft, small aircraft, mobile phones, tablets, notebooks, vehicle-mounted communication devices, wireless sensors, network cards, Internet of Things terminals, RFID terminals, NB-IOT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, network 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) NR Node B, TRP (Transmitter Receiver Point), and other wireless communication devices.

[1066] The above description is only for the preferred embodiments of this application and is not intended to limit the protection scope of this application. Any changes and modifications made based on the embodiments described in the specification, if they can achieve similar partial or all technical effects, should be regarded as obvious and fall within the protection scope of the present invention.

Claims

1. A method in a first node for wireless communication, characterized in that include: receiving a first information block; The first information block indicates a first time domain resource and a second time domain resource; Sending first CSI on the first time domain resource, or giving up sending the first CSI on the first time domain resource; Sending second CSI on the second time domain resource only when the first CSI is sent on the first time domain resource; The first CSI and the second CSI depend on the output of the first reasoning and the output of the second reasoning respectively; the output of the first reasoning includes the first output and the second output, the first CSI depends on the first output, and the input of the second reasoning includes the second output.

2. The method according to claim 1, characterized in that include: When the first CSI is abandoned from being sent on the first time domain resources, the second CSI is abandoned from being sent on the second time domain resources.

3. The method according to claim 1 or 2, characterized in that: include: When the first CSI is abandoned from being sent on the first time domain resources, part or all of the information in the first CSI and part or all of the information in the second CSI are sent on the second time domain resources.

4. The method according to any one of claims 1 to 3, characterized in that: The first reasoning and the second reasoning are both reasonings corresponding to the first identifier.

5. The method according to any one of claims 1 to 4, characterized in that: The first CSI reporting and the second CSI reporting are two CSI reports configured by the same CSI reporting configuration.

6. The method according to any one of claims 1 to 5, characterized in that: When a first condition is met, the first CSI is abandoned from being sent on the first time domain resource; the first condition includes that the first time domain resource and the first signal overlap in the time domain, or the first condition includes that the first time domain resource includes at least one DL (downlink) symbol.

7. The method according to any one of claims 1 to 6, characterized in that: The first information block indicates a first RS resource set; at least one of an input of the first inference and an input of the second inference depends on a measurement based on the first RS resource set.

8. The method according to any one of claims 1 to 7, characterized in that: The output of the second reasoning is dependent on the output of the first reasoning.

9. A terminal, characterized in that: The terminal includes: one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, where the computer program codes include computer instructions. The one or more processors call the computer instructions to enable the terminal to execute the method according to any one of claims 1 to 8.

10. A method in a second node for wireless communication, characterized in that: include: Sending a first information block; The first information block indicates a first time domain resource and a second time domain resource; wherein the receiver of the first information block sends a first CSI on the first time domain resource or gives up sending the first CSI on the first time domain resource; only when the first CSI is sent by the receiver of the first information block on the first time domain resource, the receiver of the first information block sends a second CSI on the second time domain resource; When the first CSI is sent by the receiver of the first information block on the first time domain resource, receiving the first CSI on the first time domain resource and receiving the second CSI on the second time domain resource; The first CSI and the second CSI depend on the output of the first reasoning and the output of the second reasoning respectively; the output of the first reasoning includes the first output and the second output, the first CSI depends on the first output, and the input of the second reasoning includes the second output.

11. The method according to claim 10, characterized in that include: Monitoring, on the first time domain resource, whether the first CSI is sent by the receiver of the first information block.

12. The method according to claim 10 or 11, characterized in that: include: Monitoring, on the second time domain resource, whether part or all of the information in the second CSI is sent by the receiver of the first information block.

13. The method according to any one of claims 10 to 12, characterized in that include: When the receiver of the first information block gives up sending the first CSI on the first time domain resource, the receiver of the first information block gives up sending the second CSI on the second time domain resource.

14. The method according to any one of claims 10 to 13, characterized in that include: When the receiver of the first information block gives up sending the first CSI on the first time domain resource, the receiver gives up receiving the second CSI on the second time domain resource.

15. The method according to any one of claims 10 to 14, characterized in that include: When the first CSI is abandoned by the receiver of the first information block on the first time domain resource, receiving part or all of the first CSI and part or all of the second CSI on the second time domain resource; The receiver of the first information block sends part or all of the information in the first CSI and part or all of the information in the second CSI on the second time domain resources.

16. The method according to any one of claims 10 to 15, characterized in that The first reasoning and the second reasoning are both reasonings corresponding to the first identifier.

17. The method according to any one of claims 10 to 16, characterized in that The first CSI reporting and the second CSI reporting are two CSI reports configured by the same CSI reporting configuration.

18. The method according to any one of claims 10 to 17, characterized in that When a first condition is met, the first CSI is abandoned from being sent by the receiver of the first information block on the first time domain resource; the first condition includes that the first time domain resource and the first signal overlap in the time domain, or the first condition includes that the first time domain resource includes at least one DL (downlink) symbol.

19. The method according to any one of claims 10 to 18, characterized in that The first information block indicates a first RS resource set; at least one of an input of the first inference and an input of the second inference depends on a measurement based on the first RS resource set.

20. The method according to any one of claims 10 to 19, characterized in that The output of the second reasoning is dependent on the output of the first reasoning.

21. 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, and the memory is used to store computer program codes, where the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the base station to perform the method according to any one of claims 10-20.

Images